Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks431 from public data
- Auto-encoder based dimensionality reduction987
The results show that auto-encoder can indeed learn something different from other methods, and its possible relation with the intrinsic dimensionality of input data.
- 740
- GRNet: Gridding Residual Network for Dense Point Cloud Completion468
This work devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information, and presents the differentiable Cubic Feature Sampling layer to extract features of neighboring points, which preserves context information.
- 466
- Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images392
Experimental results on the ShapeNet and Pix3D benchmarks indicate that the proposed Pix2Vox outperforms state-of-the-arts by a large margin, and the proposed method is 24 times faster than 3D-R2N2 in terms of backward inference time.
- Exploring Principles-of-Art Features For Image Emotion Recognition375
Experiments demonstrate the superiority of PAEF for affective image classification and regression (with about 5% improvement on classification accuracy and 0.2 decrease in mean squared error), as compared to the state-of-the-art approaches.
- Sparse coding based visual tracking: Review and experimental comparison295
This paper first analyzes the benefits of using sparse coding in visual tracking and then categorizes these methods into appearance modeling based on sparse coding (AMSC) and target searchingbased on sparse representation (TSSR) as well as their combination.
- 199
- Location Discriminative Vocabulary Coding for Mobile Landmark Search191
A Location Discriminative Vocabulary Coding (LDVC) scheme, which achieves extremely low bit rate query transmission, discriminative landmark description, as well as scalable descriptor delivery in a unified framework is presented.
- Efficient Regional Memory Network for Video Object Segmentation183
The proposed RM-Net effectively alleviates the ambiguity of similar objects in both memory and query frames, which allows the information to be passed from the regional memory to the query region efficiently and effectively.
- 181
- MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar145
This work proposes MonoGaussianAvatar (Monocular Gaussian Point-based Head Avatar), a novel approach that harnesses 3D Gaussian point representation coupled with a Gaussian deformation field to learn explicit head avatars from monocular portrait videos.
- Exploiting the complementary strengths of multi-layer CNN features for image retrieval133
A mapping function is designed to highlight the effectiveness of low-layer similarity, when measuring fine-grained similarity between query image and its nearest neighbors with similar semantic, and can achieve competitive performance on popular retrieval benchmarks.
- Robust visual tracking based on online learning sparse representation132
A tracking method that deals with appearance variations separately based on sparse representation in a particle filter framework and shows excellent performance in comparison with two latest state-of-the-art trackers.
- 126
- Predicting Personalized Emotion Perceptions of Social Images120
Rolling multi-task hypergraph learning is presented to consistently combine these factors and a learning algorithm is designed for automatic optimization to predict the personalized emotion perceptions of images for each individual viewer.
- An image fragile watermark scheme based on chaotic image pattern and pixel-pairs120
Simulation results and performance analysis show that the presented method is fast, secure and capable of detecting and localizing modification.
- Affective Image Retrieval via Multi-Graph Learning117
This work focuses on affective image retrieval and investigates the performance of different features on different kinds of images in a multi-graph learning framework, and combines the multiple graphs together in a regularization framework to learn the optimized weights of each graph to efficiently explore the complementation of different Features.
- Trajectory based event tactics analysis in broadcast sports video114
An effective tactic representation called aggregate trajectory is proposed which is constructed based on multiple trajectories using a novel analysis of temporal-spatial interaction among the players and the ball.
- 113
- 106
- 105
- Mining city landmarks from blogs by graph modeling105
A graph modeling framework to discover city landmarks by mining blog photo correlations with community supervision and achieves personalized tourist suggestions by the collaborative filtering of tourism logs and author correlations is deployed.
- 105
- 104
- Photo assessment based on computational visual attention model101
By integrating top-down supervision into the visual attention model, this work achieves personalized photo assessment to take user preference into quality evaluation, which can be extended into object or semantic oriented photo assessment scenarios.
- 98
- 94
- View-based 3D object retrieval via multi-modal graph learning82
A feature fusion method via multi-modal graph learning for view-based 3D object retrieval via multigraph learning that demonstrates the superior performance of the proposed method, as compared to the state-of-the-art approaches.
- 81
- 79
- Deep Saliency Hashing for Fine-Grained Retrieval77
This work proposes a novel deep hashing model, named deep saliency hashing (DSaH), which automatically mines salient regions and learns semantic-preserving hashing codes simultaneously, and performs the best for the fine-grained retrieval task and beats the strongest competitor by approximately 10% on both Stanford Dogs and CUB Birds.
- Improving Wheat Yield Prediction Accuracy Using LSTM-RF Framework Based on UAV Thermal Infrared and Multispectral Imagery75
The results showed that LSTM-RF considered both the time-series characteristics of the winter wheat growth process and the non-linear characteristics between remote sensing data and crop yield data, providing an alternative for accurate yield prediction in modern agricultural management.
- BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency74
The experiments on three popular cross-modal matching datasets demonstrate that the proposed BiCro method significantly improves the noise-robustness of various matching models, and surpass the state-of-the-art by a clear margin.
- 72
- 71
- 66
- 63
- 60
- Mining flickr landmarks by modeling reconstruction sparsity60
The main idea is to regard the landmark mining problem as a process to find photos whose visual signatures can be reconstructed using other photos of this landmark region with a minimal coding length, and a sparse reconstruction scheme offers a general perspective to mine the representative photos.
- 59
- Strategy for dynamic 3D depth data matching towards robust action retrieval57
An improved 3D shape context descriptor (3DSCD) is proposed to extract features of each static depth frame and the original feature matching problem is simplified into a two-histogram matching problem, which demonstrates the matching efficiency of the proposed method.
- Hierarchical semantic image matching using CNN feature pyramid55
This work proposes a hierarchal image matching method using the CNN feature pyramid, named as CNN Flow, which takes advantage of the complementarity of different layers using guidance from higher layer to lower layer, and demonstrates the superiority of CNN Flow in image dense matching under challenging variations.
- Towards low bit rate mobile visual search with multiple-channel coding55
Quantitative comparisons to the state-of-the-arts demonstrate the significant advantages in descriptor compactness and retrieval mAP in mobile landmark, product, and CD/book cover search.
- 49
- Video indexing and recommendation based on affective analysis of viewers49
This paper proposes a novel method to index and recommend videos based on affective analysis, mainly on facial expression recognition of viewers, and draws the affective curve which tells the process of affection changes.
- 48
- Video classification and recommendation based on affective analysis of viewers48
A novel method to classify and recommend videos based on affective analysis, mainly on facial expression recognition of viewers, by fusing the spatio-temporal features by embedded into the improved AdaBoost learning algorithm to obtain spatial features.
- Face detection and location based on skin chrominance and lip chrominance transformation from color images48
A new method of human face detection and location based on skin chrominance and lip chrominance transformation from color images is presented, an effective and robust way to detect the position of objects which is not influenced by the pose of objects and their complex background.
- DYNAMIC BACKGROUND SUBTRACTION BASED ON LOCAL DEPENDENCY HISTOGRAM47
A novel local dependency descriptor, called local dependency histogram (LDH), is presented, to effectively model the spatial dependencies between a pixel and its neighboring pixels and significantly outperforms traditional methods for dynamic background subtraction.
- Action recognition based on overcomplete independent components analysis46
This work proposes a simple but effective action recognition framework based on the recently proposed overcomplete ICA model that outperforms several state-of-the-art works on action recognition.
- 46
- 44
- 43
- Random Sampling SVM Based Soft Query Expansion for Image Retrieval43
The experiments show that the wrinkle generated by this method not only has the advantage of verisimilitude as a photograph, but also has the feature of natural ripple which is deeper in middle than in both sides.
- Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models42
A new method for scene classification based on different pre-trained Deep Features Learning Models (DFLMs) is proposed, and experimental results demonstrate the effectiveness of the proposed method, as compared to several state-of-the-art methods.
- 42
- Predicting Continuous Probability Distribution of Image Emotions in Valence-Arousal Space41
This paper proposes to predict the continuous probability distribution of dimensional image emotions represented in valence-arousal space as a Gaussian mixture model (GMM) estimated by the EM algorithm, and formulizes the emotion distribution prediction as a multi-task shared sparse regression (MTSSR) problem, which is optimized by iteratively reweighted least squares.
- 41
- Facial action unit recognition under incomplete data based on multi-label learning with missing labels40
Facial action unit recognition under incomplete data as a multi-label learning with missing labels (MLML) problem is formulated and the superiority of the proposed method in comparison with several state-of-the-art works is demonstrated.
- Robust Visual Tracking Using an Effective Appearance Model Based on Sparse Coding40
An effective appearance model based on sparse coding is proposed and applied in visual tracking to make the tracker more robust to partial occlusion, camouflage environments, pose changes, and illumination changes.
- 39
- Adaptive NormalHedge for robust visual tracking39
An improved decision-theoretic online learning algorithm, which is more robust to noise, is proposed, which exploits the historic information of each expert to perform more accurate prediction than the standard NormalHedge.
- Text image deblurring via two-tone prior38
A two-tone prior is exploited to steer the intermediate latent image towards a piece-wise constant image with only two distinct gray levels for kernel estimation, which is helpful for the process of kernel estimation to overcome undesirable local minima.
- 38
- SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation37
A novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH, to solve the above problems in a unified framework and can significantly improve state-of-the-art models on both the widely-used hashing datasets and fine-grained datasets.
- View-based 3D object retrieval with discriminative views37
This paper focuses on the 2D projective views that represent the 3D objects and proposes a boosting approach by evaluating the discriminative ability of each objects views to boost the multi-model graph learning based retrieval method.
- 36
- Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders35
Extensive experiments show that the MotionMAE outperforms significantly both supervised learning baseline and state-of-the-art MAE alternatives, under both domain-specific and domain-generic pretraining-then-finetuning settings.
- Conditional GAN based individual and global motion fusion for multiple object tracking in UAV videos35
A Conditional Generative Adversarial Networks (GAN) based model is proposed to predict complex motions in UAV videos and robust motion prediction and improved MOT performance are achieved compared with state-of-the-art methods.
- Focal CTC Loss for Chinese Optical Character Recognition on Unbalanced Datasets35
A novel deep model for unbalanced distribution Character Recognition is proposed by employing focal loss based connectionist temporal classification (CTC) function by modifying the traditional CTC by fusing focal loss with it and thus make the model attend to the low-frequent samples at training stage.
- Robust visual tracking via scale-and-state-awareness35
This work proposes to adaptively utilize the level set segmentation and bounding box regression techniques to obtain a tight enclosing box, and design a CNN to recognize whether the target is occluded.
- 35
- Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors34
A novel multi-scale trajectory-pooled 3D convolutional descriptor (MTC3D) for action recognition in this paper that has two advantages: 3D CNN has the ability to extract high-level semantic information from videos and multi- scale trajectory pooling method utilizes the temporal information of videos subtly.
- 34
- 34
- 34
- Fusion of UAV-Acquired Visible Images and Multispectral Data by Applying Machine-Learning Methods in Crop Classification33
This study provides a comprehensive analysis from feature extraction to model evaluation, identifying the optimal combination of features to improve crop classification and providing valuable insights for advancing precision agriculture through data fusion and machine learning techniques.
- Actor-independent action search using spatiotemporal vocabulary with appearance hashing33
A generalized action retrieval framework is introduced, which achieves fully unsupervised, robust, and actor-independent action search in large-scale database and an appearance hashing strategy is presented to address the performance degeneration caused by divergent actor appearances.
- 33
- Flexible Presentation of Videos Based on Affective Content Analysis32
This work proposes a novel method to present general videos of different genres based on affective content analysis, and extracts rich audio-visual affective features and selects discriminative ones to construct affective video presentation with a flexible and changeable type and length.
- Uncertainty-aware pseudo-label filtering for source-free unsupervised domain adaptation31
This work introduces a sample selection module named Adaptive Pseudo-label Selection (APS), which is responsible for filtering noisy pseudo labels, and incorporates Class-Aware Contrastive Learning (CACL) to mitigate the memorization of pseudo-label noise by learning robust pair-wise representation supervised by pseudo labels.
- Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation29
A parallel hop-aware graph attention network (PHGANet) for 3D human pose estimation, which learns enrichedHop-aware correlation of the skeleton joints while maintaining the spatially-precise representations of the human graph is proposed.
- Temporal Action Proposal Generation with Background Constraint29
This paper innovatively proposes a general auxiliary Background Constraint idea to further suppress low-quality proposals, by utilizing the background prediction score to restrict the confidence of proposals, and introduces an Action-Background Interaction module for reliable confidence evaluation.
- 29
- 29
- Multi-source domain adaptation for panoramic semantic segmentation28
A novel framework, Deformation Transform Aligner for Panoramic Semantic Segmentation (DTA4PASS), which converts all pinhole images in the source domains into distorted images and aligns the source distorted and panoramic images with the target panoramic images.
- Unsupervised semantic deep hashing28
The proposed method, namely unsupervised semantic deep hashing (USDH), uses semantic information preserved in the CNN feature layer to guide the training of network to improve the usage of each bit in hashing codes by using maximum information entropy.
- Dimensionality reduction strategy based on auto-encoder28
The results show that auto-encoder can indeed learn something different from other methods, and its ability to reduce the dimensionality and understand the difference between auto- Encoder and state-of-the-art dimensionality reduction methods is investigated.
- Multi-modal microblog classification via multi-task learning28
A multi-modal microblog classification method in a multi-task learning framework that is evaluated on Brand-Social-Net to classify the contained 100 brands and demonstrates the superiority of the proposed method, as compared to the state-of-the-art approaches.
- Nighttime image enhancement based on image decomposition27
This work implements an improved retinex image enhancement algorithm to enhance the structure layer and uses mask-weighted least squares method to suppress noise and artifact in the texture layer.
- 27
- Cross-media manifold learning for image retrieval & annotation27
A manifold-based cross-media optimization scheme to achieve visual & textual fusion within a unified framework and presents the Isomorphic Manifold Learning to map the annotation affection in image visual space onto keyword semantic space by manifold shrinkage.
- 27
- 26
- An efficient way to refine DenseNet26
Experimental results demonstrate that moderate connection trimming achieves the significant performance for DenseNet, but requires almost less than half of the GPU memories, i.e., 40% fewer parameters and about 40% less time for prediction.
- 25
- Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification25
The dynamic instance sampling and reinforcement learning are integrated into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more cred-ible decision-making.
- 25
- 24
- Toward 3D object reconstruction from stereo images24
A new deep learning framework for reconstructing the 3D shape of an object from a pair of stereo images, which reasons about the3D structure of the object by taking bidirectional disparities and feature correspondences between the two views into account is proposed.
- Sketch-specific data augmentation for freehand sketch recognition24
A novel sketch-specific data augmentation (SSDA) method that leverages the quantity and quality of the sketches automatically and can be integrated with any convolutional neural networks, it has a distinct advantage over the existing methods.
- Beyond particle flow: Bag of Trajectory Graphs for dense crowd event recognition24
The experimental results of abnormality detection and event recognition on public datasets demonstrate the effectiveness of the proposed BoTG on characterizing the group behaviors in dense crowd.
- 24
- 24
- 23
- Unsupervised fast anomaly detection in crowds23
As the only unsupervised approach, this method outputs competitive results with near real-time processing speed and is compared against several state-of-the-art approaches on UCSD dataset.
- 23
- 23
- 2D Semantic-Guided Semantic Scene Completion22
A Semantic-guided Semantic Scene Completion framework, dubbed SG-SSC, which involves Semantic-guided Fusion (SGF) and Volume-guided Semantic Predictor (VGSP), which outperforms existing state-of-the-art methods on the NYU, NYUCAD, and SemanticKITTI datasets.
- 22
- 22
- 21
- 20
- 20
- 20
- Crop Classification from Drone Imagery Based on Lightweight Semantic Segmentation Methods19
A pyramid pooling module is designed in this paper, which integrates adaptive mean pooling and CSPC (Convolutional Spatial Pyramid Pooling) techniques to handle high-resolution features and effectively utilizes UAV RGB data and lightweight deep semantic segmentation models to provide valuable insights for crop classification and UAV field monitoring.
- 19
- A novel spectral-spatial classification technique for multispectral images using extended multi-attribute profiles and sparse autoencoder19
The approach based on EMAP and deep learning (DL), proves its huge potential to achieve a high classification accuracy in reasonable running time and outperforms traditional classifiers and others classification approaches.
- Distinctive action sketch for human action recognition19
This paper proposes an approach to discover the most distinctive sketches for action recognition, and presents four kinds of sketch pooling methods to get a uniform representation for action videos.
- Synthetic data generation technique in Signer-independent sign language recognition19
The mean shift algorithm is able to obtain the directions of maximum increase and decrease in the density function, so it is used to control the direction and the intensity of synthetic data generation.
- Online Selection of Discriminative Features Using Bayes Error Rate for Visual Tracking19
Online feature selection using Bayes error rate is proposed to address visual tracking problem, where the appearances of the tracked object and scene background change during tracking.
- 18
- 18
- Anomaly detection based on spatio-temporal sparse representation and visual attention analysis18
This paper proposes a unified framework for anomaly detection and localization in crowed scenes by extracting the spatio-temporal sparse features of 3D blocks and generating the saliency map using a block-based center-surround difference operator.
- Context-Aware Semi-Local Feature Detector18
A context-aware semi-local detector (CASL) framework that integrates the context of interest points to recurrently refine their detections and produces more category-aware features which substantially benefits the subsequent visual categorization process.
- 17
- 17
- 16
- Unsupervised discovery of crowd activities by saliency-based clustering16
A novel unsupervised crowd activity discovery algorithm aiming to automatically explore latent action patterns among crowd activities and partition them into meaningful clusters is developed and a spatio-temporal saliency-based representation is presented to simulate visual attention mechanism and encode human-focused components in an activity stream.
- DNN Flow: DNN Feature Pyramid based Image Matching16
The coarse to fine matching based on DNN feature pyramid is formulated as a series of optimization problems considering the guidance from top level, and extensive experiments demonstrate the superiority of DNN Flow in image matching under challenge variations.
- Where should I stand? Learning based human position recommendation for mobile photographing16
This paper proposes a learning-based method to summarize the photographing knowledge from massive social images to improve the robustness and effectiveness and proposes a 3D reconstruction- based method to align the background region and human region into a uniform coordinate system.
- 16
- Online multiple object tracking via exchanging object context15
This paper proposes an efficient and accurate online multiple object tracking algorithm with a novel affinity measure to associate detections, and implements an Exchanging Object Context (EOC) model which takes full advantage of the context information.
- 15
- 15
- DRM: dynamic region matching for image retrieval using probabilistic fuzzy matching and boosting feature selection15
A novel region-based retrieval framework—dynamic region matching (DRM) to bridge the semantic gap in content-based image retrieval from two aspects: irrelevant visual contents and unsupervised feature extraction and similarity ranking method.
- 15
- 14
- TVENet: Temporal variance embedding network for fine-grained action representation14
This paper constructs a fine-grained action dataset, i.e., Figure Skating, which can be used for end-to-end network training and presents a framework for the joint optimization of classification and similarity constraints, and proposes a temporal variance embedding network (TVENet) embedding temporal context variances into the feature embeddings during the joint network training.
- Discriminative Features for Bird Species Classification14
This paper introduces discriminative features for bird species classification based on parts of birds, and shows the effectiveness of the discrim inative features on the CUB-200-2011 dataset.
- A modular latching chain14
To extend a mathematical model of latching dynamics beyond the simple unstructured auto-association Potts network, delayed structured connectivity and hetero-associative connection weights are introduced and their effects on the dynamics are explored.
- 14
- Contour-motion feature (CMF): A space–time approach for robust pedestrian detection14
This paper presents a contour-motion feature for robust pedestrian detection that can outperform Viola's well-known pedestrian detector in both detection accuracy and generalization ability and has been extended to human activity recognition application and remarkable performance has been achieved.
- 14
- EFFECTIVE AND AUTOMATIC CALIBRATION USING CONCENTRIC CIRCLES14
This approach utilizes the characteristics of concentric circles' tangent lines to locate the center of these circles, and finds the geometric constraints for calibration based on the orthogonality formed by a point on the circle and the two intersected points of the circle with the line through the centerof the circle.
- 14
- 14
- Limb-Aware Virtual Try-On Network With Progressive Clothing Warping13
Lb-aware Virtual Try-on Network named PL-VTON is proposed, which performs fine-grained clothing warping progressively and generates high-quality try-on results with realistic limb details and introduces Limb-aware Texture Fusion that focuses on generating realistic details in limb regions.
- Towards more efficient and flexible face image deblurring using robust salient face landmark detection13
Extensive experimental results demonstrate that the proposed face deblurring method can better handle various complex face poses, shapes and expressions while greatly reducing computation time, as compared with existing state-of-the-art approaches.
- Robust object tracking based on sparse representation13
A novel and robust object tracking algorithm based on sparse representation that is more effective than the widely used mean shift tracker and effective on two challenging test sequences.
- Scalable and Credible Video Watermarking towards Scalable Video Coding13
Whether watermark exists or not can be judged by adaptive detection which guarantees the proposed method has a good legal credibility, since its False Alarm Rate (FAR) closes to zero.
- Location sensitive indexing for image-based advertising13
The architecture of the location sensitive indexing model used in a platform designed to deliver advertisements to users who primarily utilize images as queries instead of textual keywords is introduced, which enables effective and efficient functionality in large-scale scenarios.
- Image Evaluation Factors13
The method employs three new measures that evaluate the definition of contours, uniform intensity distribution, and noise rate in determining the image quality, making them suitable for automated ranking of image quality in personal digital imaging devices, such as digital cameras.
- 12
- Weighted voxel12
A new voxel representation, named Weighted Voxel, is defined, which provides more abundant information, facilitating the subsequent learning and generalization steps, and makes full use of the structure information of voxels.
- HIT-AVDB-II: A New Multi-view and Extreme Feature Cases Contained Audio-Visual Database for Biometrics12
A multi-language and multiview database HIT-AVDB-II with a corpus of various common and special sentences include Chinese and English poems, tongue twister, digits, Greek alphabet and music is constructed.
- 12
- 11
- End-to-End Human Instance Matting11
A novel End-to-End Human Instance Matting (E2E-HIM) framework for simultaneous multiple instance matting in a more efficient manner and a large-scale human instance matting dataset comprising over 100,000 human images with instance alpha matte labels is constructed.
- Asynchronous Teacher Guided Bit-wise Hard Mining for Online Hashing11
A novel online hashing method to handle the catastrophic forgetting problem, and a novel semantic loss (termed bit-wise attention loss) to dynamically focus on hard samples of each bit during training.
- Handling missing labels and class imbalance challenges simultaneously for facial action unit recognition11
A convex approximation based on the Lovasz extension is presented, which leads to a linear program that can be efficiently solved by the alternative direction method of multipliers (ADMM) and demonstrates the superiority of the proposed method compared to state-of-the-art.
- Self-balance Motion and Appearance Model for Multi-object Tracking in UAV11
This paper proposes a novel self-balance method fusing appearance similarity and motion consistency and demonstrates the effectiveness of the proposed method with comparisons to several state-of-the-art trackers.
- 11
- Age classification based on back-propagation network11
The influence of gender is studied and it is found that considering gender independently in age classification is advisable and the approach can achieve the goal of age classification well.
- 11
- Local Spatial Co-occurrence for Background Subtraction via Adaptive Binned Kernel Estimation11
A nonparametric background subtraction method that uses the local spatial co-occurrence correlations between neighboring pixels to robustly and efficiently detect moving objects in dynamic scenes is presented.
- A refined particle filter method for contour tracking11
A refined particle filter method for contour tracking based on a binary level set model and the computational efficiency is greatly improved due to the simple form of the level set function.
- 11
- Visual & textual fusion for region retrieval: from both fuzzy matching and bayesian reasoning aspects11
A novel visual & textual information fusion framework for region-based image retrieval from both Bayesian Reasoning and Fuzzy Region Matching aspects to bridge the semantic gap.
- 11
- 11
- 11
- 11
- HPnet: Hybrid Parallel Network for Human Pose Estimation10
A hybrid parallel network is developed by parallelizing the self-attention modules and the convolution modules, which conduce to leverage the complementary capabilities effectively effectively and is on par with the state-of-the-art human pose estimation models.
- 10
- Learning Cross Space Mapping via DNN Using Large Scale Click-Through Logs10
A unified DNN model for image-query similarity calculation by simultaneously modeling image and query in one network is proposed, named the cross space mapping (CSM) model, which contains two parts, a convolutional part and a query-embedding part.
- Representing dense crowd patterns using bag of trajectory graphs10
Each clip of crowd event can be further described by BoTG as the occurrences of behavior patterns, which provides critical clues for categorizing specific crowd event.
- 10
- 10
- Vision-Based Semi-supervised Homecare with Spatial Constraint10
This paper presents a vision-based semi-supervised homecare system to automatically monitor the exceptional behaviors of self-helpless persons in home environment and proposes a Spatial Field constraint strategy to assist SVM-based exception action decision with a Bayesian inference model.
- Place retrieval with graph-based place-view model10
A novel unsupervised framework for efficient place retrieval in movies and sitcoms is presented, leveraging face detection to filter out close-up frames from video dataset, and adopting saliency map analysis to partition background places from foreground actions.
- Overview of manifold learning10
The results show that compared with traditional linear method, manifold learning can discover the intrinsic dimensions of nonlinear high-dimensional data effectively, helping researchers to reduce dimensionality and analyze data better.
- Shape from silhouette outlines using an adaptive dandelion model10
This paper reconstructs a 3D model using only the outmost silhouette contours and produces a solid called the ''bounding hull'' which is composed of a pencil of organized line segments emitted from a common point which samples the bounding hull surface in regularly distributed orientations with the ending points serving as sampling points.
- FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation9
A novel approach, FrozenSeg, designed to integrate spatial knowledge from a localization foundation model and semantic knowledge extracted from a ViL model, in a synergistic framework, which advances state-of-the-art results across various segmentation benchmarks.
- 9
- Soul Dancer9
This article makes the first attempt to generate an action video with a specific emotion from a single person image and proposes an emotion-based pose sequence generation approach (EPOSE-GAN) for translating the emotion to a pose sequence.
- Dynamic multi-cue tracking using particle filter9
A novel particle filter approach for robust object tracking using multi-cue association that commands all the spaces and their corresponding judgments in a global boosting view, which is implemented in an incremental manner to strengthen the ability of separating the target and background classes.
- 9
- DTW/ISODATA Algorithm and Multilayer Architecture in Sign Language Recognition with Large Vocabulary9
- 8
- OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning8
An Online Pseudo-Supervision and Dynamic Mutual Learning (OODML) framework that enhances pseudo-label generation and feature representation while exploring their mutual learning to improve bag-level prediction is proposed and a Dynamic Decision-Making (DDM) module is developed to harmonize explicit and implicit representations of bag information for more robust decision-making.
- 8
- 8
- Discovering discriminative patches for free-hand sketch analysis8
This paper proposes a weak supervised approach to discover the most discriminative patches for different categories of sketches, which perhaps grasp the key to a good free-hand sketch.
- Eating activity detection from images acquired by a wearable camera8
An eating activity detection method via automatic detecting dining plates from images acquired chronically by a wearable camera that determines the presence/absence of an eating event in an image sequence by analyzing successive frames.
- 8
- Robust object tracking combining color and scale invariant features8
A robust object tracking algorithm which exploits both global color and local scale invariant (SIFT) features in a particle filter framework and adopts a speed-up variation of SIFT, SURF, to extract local features.
- Local Histogram of Figure/Ground Segmentations for Dynamic Background Subtraction8
A novel feature, local histogram of figure/ground segmentations, is proposed for robust and efficient background subtraction (BGS) in dynamic scenes (e.g., waving trees, ripples in water, illumination changes, camera jitters, etc.).
- 8
- 8
- 7
- 7
- Visual attention modeling based on short-term environmental adaption7
A novel principle for modeling visual attention mechanism named short-term environmental adaption is proposed, which adaptively extract sparse features and treats saliency as the features' conditional self-information, which is more accurate in saliency measurement and more sparse with respect to visual signal representation.
- 7
- 7
- Learning heterogeneous data for hierarchical web video classification7
An AdaBoost-Like transfer learning algorithm is proposed to transfer the knowledge learned from Flickr images to YouTube video domain and thus it facilitates video classification, and a bottom-up semantic forest of video concepts by learning from meta-data is constructed.
- 7
- 7
- Shape from silhouettes based on a centripetal pentahedron model7
A novel volumetric shape from silhouette (SfS) algorithm based on a centripetal pentahedron model (pent-model) that has the combined advantages of robustness, speediness and preciseness is presented.
- Attention-driven action retrieval with DTW-based 3d descriptor matching7
A content-based action retrieval framework to enable effective search of near-duplicated actions in large-scale video database is presented and a prototype system VILAR is presented to facilitate action search within "Friends" soap operas with excellent accuracy, efficiency, and human perception revealing ability.
- Texture and Motion Pattern Fusion for Background Subtraction7
A novel background subtraction algorithm, which takes both texture and motion information into account, and combines the texture pattern- based and motion pattern-based background model.
- Spatial Video Watermarking Based on Stability of DC Coefficients7
This paper presents a novel blind video watermarking algorithm based on the stability of the direct current (DC) coefficient values in blocks that has strong robustness against some attacks such as frame deleting, frame inserting, frame shifting, frame statistical average and collusion attack.
- 6
- 6
- 6
- 6
- Formation Period Matters6
This work develops a socially motivated representation by modeling the formation period probability in a Bayesian manner, which results in social and temporal consistency for group member interactions and employs graph shift optimization to detect groups by finding all the dense subgraphs due to its robust performance.
- 6
- Minimizing the Distortion Spatial Data Hiding Based on Equivalence Class6
The proposed hiding strategy can resolve the issue of tradeoff between distortion and length of information efficiently and can meet such applications where the size of message is very unstable.
- 6
- Online Learning Objectionable Image Filter Based on SVM6
An on-line learning system for objectionable image filtering that preserves not only support vectors but also the cases with longest distance from the decision surface, because the more representative patterns are the farthest examples away from the hyperplane.
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation5
A novel framework termed Bridge then Begin Anew (BBA), which consists of two steps: domain-bridged model generation (DMG) and target-related model adaptation (TMA), which achieves remarkable performance gains compared with state-of-the-art SFDA methods and outperforms representative unsupervised domain adaptation approaches.
- 5
- 5
- 5
- Multi-modal Emotion Recognition Based on Speech and Image5
The experimental results demonstrate that emotion recognition based on fusion of speech and image achieved high recognition accuracy than emotion recognition from single modal, and also the decisionlevel fusion methods show superior to feature level fusion methods in this work.
- Multi-level Semantic Representation for Flower Classification5
This paper proposes a fine-grained classification approach with multi-level semantic representation that achieves the best performance over other state-of-the-art approaches.
- Gradual recovery based occluded digit images recognition5
The main application in this paper is occluded digit images recognition, though the proposed framework can be generalized to other problems easily and nicely, and the effectiveness, extendibility and generalizability of the method are shown.
- Off-the-shelf CNN features for 3D object retrieval5
This paper proposes to combine the off-the-shelf deep model and graph model to retrieve unseen objects by employing the powerful deep classification models which are trained from millions of images, and achieves significant improvements compared with state of the art methods.
- Strategy for aesthetic photography recommendation via collaborative composition model5
A collaborative composition model for automatically recommending suitable positions and poses in the scene of photography taken by amateurs is proposed, which exploits the strength of visual saliency to explicitly encode the spatial correlation of the professional photos.
- Efficient Face Image Deblurring via Robust Face Salient Landmark Detection5
Extensive experimental results demonstrate that the proposed face deblurring method can better handle various complex face poses while greatly reducing computation time, as compared with state-of-the-art approaches.
- Video stabilization based on saliency driven SIFT matching and discriminative RANSAC5
A modified version of RANSAC method is achieved using the discriminative features to estimate the trajectory of inter-frame motion and reduce the errors caused by the foreground vector.
- A robust texture descriptor using multifractal analysis with Gabor filter5
A novel robust texture descriptor on variance in rotation, scale and illumination, which combines the dominant orientation analysis and multifractal analysis base on Gabor filter is proposed.
- 5
- 5
- 5
- 5
- 5
- A Fragile Image Watermarking Based on Mass and Centroid5
Experimental results show that this fragile watermarking can detect and locate any change made to an image and successfully avoid the drawback of cryptographic hash function, which suffers the famous birthday attack.
- Multilayer architecture in sign language recognition system5
A multilayer architecture of sign language recognition for large vocabulary is proposed in this paper for the purpose of speeding up the recognition process and experiment results indicate that it is an effective algorithm for Chinese signlanguage recognition.
- Augmenting and contrasting distortion for open panoramic segmentation4
A novel framework named augmenting and contrasting distortion for open panoramic segmentation (ACD4OPS), consisting of random Gaussian deformation augmentation (RGDA) and distortion-aware contrastive learning (DaCL), which reduces gaps in the feature space between pinhole images and panoramas.
- 4
- Use Self-Training Random Forest for Predicting Winter Wheat Yield4
A self-training random forest algorithm capable of automatically expanding the annotated dataset using a small amount of annotated data is developed, thereby enhancing the prediction accuracy of ML models in winter wheat yield forecasting.
- 4
- Center-push loss for joint view-based 3D model classification and retrieval feature learning4
It is argued that although the classification and retrieval focus on different characteristics of embedding features, they are compatible rather than opposed to each other, and a novelty loss named center-push loss for joint feature learning is proposed.
- Image editing with varying intensities of processing4
The hypothesis is that the part of parameters that correspond to the intensity of processing of the network are implicitly embedded in the whole parameter set and can be explicitly extracted and utilized, even with limited supervision, in image editing with Varying Intensities of Processing.
- Feature extraction based on extended multi-attribute profiles and sparse autoencoder for remote sensing image classification4
Experiments show that this new scheme can achieve better performance of feature learning than the primitive features, traditional classifiers and ordinary autoencoder and has huge potential to achieve higher accuracy for classification in short running time.
- How many zero crossings? A method for structure-texture image decomposition4
An efficient method for evaluating the proximity operator of the number of zero crossings to solve the resulting optimization problem is proposed and validated with applications in inverse halftoning, smoothing photos captured from screen, and text image deblurring.
- Rediscover flowers structurally4
It is argued that structural cues are essential for flower recognition and a novel approach is presented that explores structural cues to extract features and outperforms the state-of-the-arts which employ specific designed features and metric learning.
- Locally aggregated histogram-based descriptors4
The locally aggregation strategy is introduced into the design of hand-crafted features to address this issue, and several locally aggregated histogram-based descriptors, including LA-HOG,LA-HOF and LA-MBH, based on HOG, HOF and MBH are put forward.
- Exploring Discriminative Views for 3D Object Retrieval4
This paper focuses on the 2D projective views that represent the 3D objects and proposes a boosting approach by evaluating the discriminative ability of each object's views to boost the multi-model graph learning method.
- 4
- 4
- From Seed Discovery to Deep Reconstruction4
This paper proposes a saliency prediction model dedicated for crowd videos with two novelties, which can effectively explore crowd saliency mechanism in two-stage SDAEs and achieve significantly better results than state-of-the-art methods, with robustness to parameters.
- 4
- 4
- Bidirectional-isomorphic manifold learning at image semantic understanding & representation4
A Bidirectional- Isomorphic Manifold learning strategy to optimize both visual feature space and textual space, in order to achieve more accurate comprehension for image semantics and relationships and promising results show that the model attains a significant improvement over state-of-the-art algorithms.
- Robust object tracking via inertial potential based mean shift4
Experimental results on several challenging video sequences have verified that the proposed method is compared very robust and effective with the traditional mean shift based trackers in many complicated scenes.
- 4
- 4
- 4
- VisualCor system4
This work presents a context-based actor correlations graph search framework for TV series with excellent ranking accuracy, efficiency, and the ability to reveal human perception, and deploys it onto an online actor correlation search system, VisualCor, which could be viewed as a visualized, content-based simulation of the Renlifang search engine.
- Effort analysis in signer-independent sign gestures4
Based on the principles of movement observation science, specifically Laban Movement Analysis (LMA), a summary of the factors causing sign language data variation is presented, and a method for describing, sign language effort elements is proposed and then a strategy for standardizing signer-independent signlanguage data is provided.
- Real-time image annotation by manifold-based biased Fisher discriminant analysis4
A novel Manifold-based Biased Fisher Discriminant Analysis (MBFDA) algorithm to address the Small Sample Size (3S) problem in keyword classifier/model learning and keyword filtering and real-time annotation accuracy with a large margin.
- Visual Sign Language Recognition Based on HMMs and Auto-regressive HMMs4
A hybrid structure to combine ARHMMs with HMMs based on the trick of using an ambiguous word set is presented and the advantages of both models are revealed in such a frame work.
- An Information Acquiring Channel —— Lip Movement4
It could be easily got that lip-reading channel is an effective one and can be applied independently and the reasoning is given by describing two kinds of valid applications, which are constructed on lip movement information only.
- Artistic image synthesis with tag-guided correlation matching3
The tag-guided correlation matrix for matching the tag with the content code from the source image as better guidance on the style code is presented as better guidance on the style code for controllable synthesis.
- Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition3
A multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint to constrain the Batch Nuclear-norm of the classification matrix improves the discriminative properties of the classification model and increases its diversity at the same time.
- Hierarchical pose net: spatial hierarchical body tree driven multi-person pose estimation3
This paper defines a Spatial Hierarchical Body Tree (SHBT) that encodes the location and association information of the body center, parts, and joints for each human instance and builds Hierarchical Pose Net (Heap-net), which explicitly defines the corresponding output order and the feature fusion aggregation.
- Object contour tracking via adaptive data-driven kernel3
This adaptive kernel can continually seize the target shape to give a better estimation bias and produce accurate shift of the mean and can successfully avoid the performance loss stemmed from pollution of background pixels hiding inside the kernel.
- Exploring part-aware segmentation for fine-grained visual categorization3
This work designs a hybrid part localization method, which generates accurate part proposals with moderate computation and iteratively update the segmentation outputs and the part proposals, which obtains better foreground segmentation results.
- Event patches: Mining effective parts for event detection and understanding3
This paper proposes to mine effective parts for event detection and understanding by trying to mine the definite parts (Event Patches) that mostly contribute to defining an event.
- Shallow and Deep Model Investigation for Distinguishing Corn and Weeds3
The experiment results demonstrate that detection based on improved Faster R-CNN model can better handle the problem and design a specific module to improve the processing speed and ensure the accuracy at the same time.
- Style Transfer with Content Preservation from Multiple Images3
This work proposes a framework based on neural patches matching that combines the content structure and style textures in a fusion layer of the network that is capable to extract the style from a group of images, such as the paintings of specific painter.
- Training samples-optimizing based dictionary learning algorithm for MR sparse superresolution reconstruction3
The gray-consistency & gradient joined diversity-based dictionary representation method is proposed to select the optimal images for the dictionary training and results show that the proposed dictionary selection framework is feasible and effective to improve the quality of sparse reconstruction-based MR super-resolution.
- Breaking video into pieces for action recognition3
This work partitions the input video into small clips and formulate action recognition as a joint decision-making task, and builds an aggregated representation for the original full-length video by integrating the elements of the DVM.
- Latching chains inK-nearest-neighbor and modular small-world networks3
The main findings include: with decreasing threshold coefficient and rewiring probability, both the K-nearest-neighbor network and the modular network experience quantitatively similar phase change processes, and the modules exhibits selectively enhanced latching in the small-world range of connectivity.
- 3
- Edge-Respecting Image Smoothing via Extrema Interpolation3
This work proposes anextrema interpolation formulation for edge-aware smoothing, in which the extrema of the sought signal are fixed and the final smoothing result is the one that has the least distance with the original signal.
- 3
- 3
- Video watermarking algorithm for resisting collusion attacks3
Experimental results have been shown that the performance of the proposed strategy can resist effectively two types of linear collusion attacks while still being robust, stable and imperceptible.
- A rotation and scale invariant texture description approach3
A novel Local Haar Binary Pattern based framework to ensure invariance in global rotation, scale, and light change, and Evaluation results on Outex and Brodatz databases illustrate the significant advantages of the proposed approach over existing algorithms.
- A Determined Binary Level Set Method Based on Mean Shift for Contour Tracking3
This paper proposes a novel contour tracking algorithm using a determined binary level set model (DBLSM) based on mean shift procedure that is efficient and effective in many complicated scenes.
- What is a complete set of keywords for image description & annotation on the web3
This paper presents a complete set framework for image annotation, which is motivated by the existence of semantic ontology, and presents a Gaussian-Kernel-Generative process based keyword generation procedure, which analogizes keyword annotation in a probabilistic generative manner.
- Text Particles Multi-band Fusion for Robust Text Detection3
A robust text detection method based on text particles (TP) multi-band fusion to solve problems of weak contrast and text-background variance in state-of-the-art text detection algorithms.
- A Novel Retrieval Refinement and Interaction Pattern by Exploring Result Correlations for Image Retrieval3
A novel retrieval refinement and feedback framework is presented that provides users a novel perceptual-similar interaction pattern for topic-based image retrieval and excellent feedback efficiency enhancements are gained comparing to traditional SVM-based feedback learning methods.
- 3
- The Bunch-Active Shape Model3
A novel method, called Bunch-Active Shape Model (Bunch-ASM), based on the standard ASM, to automatically locate facial feature points in Face Recognition, where eyes are localized by a face detector and the matching strategy used in Elastic Bunch Graph Matching is introduced.
- A Fragile Watermarking Based on Knapsack Problem3
A new fragile watermarking scheme is proposed that can effectively resist the birthday attack with a higher resolution than the algorithm before and good property of localization.
- Fast Moving Region Detection Scheme in Ad Hoc Sensor Network3
A simple yet effective temporal differencing based moving region detection scheme which can be used in limited resource condition such as in ad-hoc sensor network to achieve real-time detection in these low-end image sensor nodes.
- Visual Features Extracting & Selecting for Lipreading3
A way to select and extract visual features effectively for lipreading and proves that visual speech information can reinforce the loss of acoustic information effectively by improving recognition rate from 10% to 30% various with the different amount of noises in speech signals.
- Fusion of Biometrics Based on D-S Theory3
Experimental results show that the recognition accuracy of the fusion system is much higher than the single channel, and D-S theory is one of the method often used in integrating multiple clues to undraw the basic probability of each class after fusion.
- 2
- 2
- 2
- 2
- Image Decomposition Based Nighttime Image Enhancement2
The experimental results demonstrate that the proposed approach can improve the perceptual quality of nighttime image while suppressing noise and artifact, and avoiding excessive reinforcement.
- 2
- Illustrate your travel notes2
An automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process is presented and an adaptive visual representation is constructed from the discovered image regions which can automatically link phrase-image pairs.
- Actor identification via mining representative actions2
This work proposes to mine representative actions of each actor, and shows the remarkable power of such actions for actor identification, and proposes two novel methods to rank the shots and obtain the representative actions.
- User-Centric Affective Computing of Image Emotion Perceptions2
Different factors that may influence emotion perceptions, including visual content, social context, temporal evolution, and location influence are jointly investigated via the presented rolling multi-task hypergraph learning.
- Part-Aware Segmentation for Fine-Grained Categorization2
This work designs a hybrid part localization method, which combines parametric and non-parametric models, and iteratively update the segmentation outputs and the part proposal, which can get better foreground segmentation results.
- "Clustering of Dancelets"2
This paper proposes to recommend dance videos based on the automatically discovered ``Dance Styles'', which play a significant role in characterizing different types of dances, and takes advantage of a mid-level action representation method to bridge the semantic gap between video content and mid- level concept, style.
- 2
- 2
- 2
- A refined particle filter based on determined level set model for robust contour tracking2
A refined particle filter method for contour tracking based on a determined binary level set model (DBLSM) which adds prior knowledge of the target model to the implementation of curve evolution which improves the curve acting principle and ensures a more accurate convergence to the target.
- Weakly supervised codebook learning by iterative label propagation with graph quantization2
A weakly supervised codebook learning framework, which integrates image labels to supervise codebook building with two steps: the Label Propagation step propagates image labels into local patches by multiple instance learning and instance selection and the Graph Quantization step integrates patch labels to build codebook using Mean Shift.
- Learning from mobile contexts to minimize the mobile location search latency2
This work combines location related side information from the mobile devices to adaptively supervise the compact visual descriptor design in a flexible manner, which is very suitable to search locations or landmarks within a bandwidth constraint wireless link.
- 3D silhouette tracking with occlusion inference2
A 3D silhouette tracking framework to resolve occlusions and recover the appearances in 3D space, which enhances tracking effectiveness and the experiments under the public LAB and SCULPTURE datasets validate the feasibility and effectiveness.
- 2
- Adaptive Particle Filter Based on Energy Field for Robust Object Tracking in Complex Scenes2
An adaptive particle filter based on energy field (EPF), which makes good use of moving information of previous frames adaptively to track the target to ensure the target region is accurate.
- Partial occlusion robust object tracking using an effective appearance model2
This work proposes a novel local descriptor, named local color texture pattern (LCTP), to model the appearance of the object with color and texture information simultaneously, and is more robust to partial occlusion than two state-of-the-art algorithms.
- 2
- Combining Global and Local Classifiers for Lipreading2
This paper mainly focuses on how to choose more efficient features for lipreading, and how to build lipreading models.
- 2
- Static Gesture Quantization and DCT Based Sign Language Generation2
A novel sign language generation algorithm combining the static gesture quantization and Discrete Cosine Transform is introduced, which can generate the new signers’ sign words according to the existed signers' sign words.
- 2
- CMPF: Harmonizing Cross-Model Prior Fusion for Open-Vocabulary Segmentation1
A novel Cross-Model Prior Fusion (CMPF) framework is introduced, an innovative framework that fuses visual knowledge from a localization foundation model and text knowledge from a ViL model, leveraging their complementary knowledge priors to overcome inherent limitations in mask proposal generation.
- Content-aware Information Compression and Selection for Whole Slide Image Analysis1
CICS is an efficient and general framework that performs compact information compression and selection for high-efficiency WSI analysis and achieves 2.5%, 7.7%, and 3.9% accuracy gain over the state-of-the-art Transformer-based TransMIL, Mamba-based MambaMIL, and graph-based WIKG methods on the ESCA dataset.
- 1
- 1
- 1
- Emotion in a Bottle: Information Bottleneck Guided Disentanglement for Emotion Domain Adaptation1
A CLIP-based emotion disentanglement (EmoD) framework designed for EDA that implements a disentangler network that extracts emotion-specific features while removing redundant emotion-agnostic information and incorporates cross-domain feature alignment to reduce the affective gap between domains.
- 1
- 1
- 1
- 1
- RetrievFace: Retrieval-Enhanced Diffusion for Controllable Text-Guided Face Editing1
This work proposes RetrievFace, a retrieval-enhanced text-driven face editing framework that integrates multimodal retrieval, automated face detection, and diffusion-based fine-grained editing, and offers a scalable and interpretable solution for text-guided face manipulation.
- Correction to: Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation1
Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation with Huawei Cloud & AI is shown.
- Artistic image synthesis from unsupervised segmentation maps1
This work uses unsupervised segmentation maps to build on training pairs and learn the generator with the proposed spatially adaptive instance normalization block to reduce the artifact in synthetic images.
- 1
- Iterated shape-bias graph cut with application to ellipse segmentation1
This work presents a novel graph cut method for iterated segmentation of objects with specific shape bias (SBGC), which takes the shape preference of the interested object into account to drive the segmentation and achieves joint estimation of the optimal segmentation.
- Actionness-pooled Deep-convolutional Descriptor for fine-grained action recognition1
The visual attention mechanism is introduced into the proposed descriptor, termed Actionness-pooled Deep-convolutional Descriptor (ADD), and instead of pooling features uniformly from the entire video, it aggregate features in sub-regions that are more likely to contain actions according to actionness maps.
- An Effective Way to Boost Black-Box Adversarial Attack1
The experimental results show that the proposed strategy can significantly improve success rates of fooling models in a black-box manner and outperforms the momentum iterative method (MI-FSGM), which won the first places in NeurIPS Non-targeted Adversarial Attack and Targeted AdVERSarial Attack competitions.
- Object Discovery and Cosegmentation Based on Dense Correspondences1
This work proposes to do object discovery and cosegmentation in noisy datasets with utilization of CNN features and adopts VGG features to do unsupervised clustering and find representative candidates as a prior knowledge.
- RS-MSSF Frame: Remote Sensing Image Classification Based on Extraction and Fusion of Multiple Spectral-Spatial Features1
This study extracted multiple features from spectral and spatial domains where they utilized texture and shape features, as well as spectral features, in order to obtain high classification accuracy and tested the proposed framework on hyperspectral and multispectral images.
- Trajectory-Pooled 3D Convolutional Descriptors for Action Recognition1
This paper calculates dense trajectories from the input video and performs trajectory pooling on feature maps of 3D CNN and presents a novel trajectory-pooled 3D convolutional descriptor (TC3D) for action recognition.
- 1
- 1
- Affective Computing and Applications of Image Emotion Perceptions1
This research of the PhD thesis focuses on image emotion computing (IEC), which aims to predict the emotion perceptions of given images, and aims to find features that can express emotions better to bridge the affective gap.
- Tree-guided Group Sparse based Representation for Person Re-identification1
This work considers the structural information of human body along with supervision, and introduces the Tree-guided Group Sparse (TGS) method for feature selection before dimension reduction, demonstrating TGS can effectively remove noise and redundancy in person representation.
- Boost sparse coding based abnormal event detection via explicitly applying temporal continuity constraint1
This paper proposes to explicitly apply temporal continuity constraint on sparse coding based local feature representation method, not just enlarging the scale of local features representation, to achieve more stable and smooth results, thus more high detection accuracy.
- 1
- Dual-mode video stabilization based on adaptive motion clustering1
A novel approach to stabilize the videos containing large dynamic object, which can realize the normal stabilization task and describe the target motion path at the meantime and gives a flexible choice in stabilizing background motion as traditional algorithms or foreground motion for salient target surveillance.
- 1
- 1
- 1
- 1
- 1
- A Progressive Quality Hiding Strategy Based on Equivalence Partitions of Hiding Units1
A novel hiding strategy based on an equivalence relation, which not only provides the progressive quality characteristic but also enhances remarkably the quality of stego image without sacrificing the security and capacity compared with original steganography schemes is designed.
- An Image Data Hiding Method Using Pixel-Based JND Model1
A spatial data hiding using pixel-based JND (Just-Noticeable Distortion) model to modify the difference image between host image and predictive image to hide the data and shows that the stego-image is visually indistinguishable from the original cover-image and has better quality for Stego image.
- Visual topic model for web image annotation1
A novel Visual Topic Model framework is proposed, via unsupervised clustering techniques, that aims at analyzing image semantics fusing both content and context, by considering tag correlations and ambiguities.
- 1
- 1
- A novel feature-level multiple HMMs classifier for Lipreading based on Ada-Boost Gabor kernels selection1
A novel feature-level Multiple HMMs classifier for lipreading is presented that subdivides mouth images into four non-overlapping subblocks and uses AdaBoost to adaptively select optimal Gabor kernels from four sub-blocks convolved with different Gabor kernel functions and corresponding HMMs are trained.
- 1
- 1
- Using Visual Dictionary to Associate Semantic Objects in Region-Based Image Retrieval1
Experimental comparisons of the proposed inference method over Visual-only region matching method indicate its effectiveness in enhancing the performance of region retrieval and bridging the semantic gap.
- Illumination Invariant Feature Selection for Face Recognition1
A novel hybrid illumination invariant feature selection scheme for face recognition, which is a combination of geometrical feature extraction and linear subspace projection, and the NHE+DFLD yields the best performance.
- Mapping Energy Video Watermarking Algorithm Based on Compressed Domain1
The experimental results indicate that the scheme has strong robustness to the attacks such as re-encoding, frame dropping, frame rate changing and sharpening and high watermark payload and low time complexity are advantages of the scheme.
- 1
- 1
- Inter-frame Differential Energy Video Watermarking Algorithm Based on Compressed Domain1
The experimental results indicate that the scheme has several advantages including low computational complexity, strong robustness to re-encoding, low visual degradation and high watermark payload in the low bit rate environment compared with other watermarking systems in the compressed domain.
- STEGANALYSIS OF IMAGES CREATED IN WAVELET DOMAIN USING QUANTIZATION MODULATION1
A novel method to reveal existence of hidden communication in stego medium according statistics discrepancies in images, which had been hidden message is proposed.
- A High Capacity Data Hiding Scheme Based on DFT1
This paper presents a new data hiding scheme for still images based on embedding information in the transform domain; the DFT coefficients of the original image are modified to embed information bits.
- 1
- 1
- 1
- –
- Retrieval-Augmented Camera Control for Video Diffusion–
A novel training-free framework that shifts the paradigm to ”Retrieve-and-Refine”, and introduces Retrieval Augmented Patch Inpainting, which achieves state-of-the-art performance, surpassing both training-free baselines and fully optimized methods in visual fidelity and camera control accuracy.
- –
- –
- –
- –
- M2DAO-Talker: Harmonizing Multi-Granular Motion Decoupling and Alternating Optimization for Talking-Head Generation–
M2DAO-Talker is proposed, a novel framework integrating Multi-granular Motion decoupling and Dynamic Alternating Optimization that significantly outperforms state-of-the-art approaches both qualitatively and quantitatively.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- In-use calibration: improving domain-specific fine-grained few-shot recognition–
This study is the first work on the fine-grained “Coarse-to-Fine” few-shot plant disease classification, which classifies “fine-grained novel classes” based on “coarse-grained base classes” (specific to plant species) and a complete two-stage in-use calibration strategy is presented.
- –
- –
- Searching by parts: Towards fine-grained image retrieval respecting species correlation–
A new fine-grained retrieval task that searches for similar instances from different species based on body parts using a deep convolutional neural network and formulating a novel ranking function that balances between the similarity of the candidates to the queried parts, while decreasing the similarity to the query species.
- –
- –
- ASMMC-MMAC 2018–
Affective social multimedia computing is an emergent research topic for both affective computing and multimedia research communities and urgently demands advanced techniques on the management, retrieval, and understanding of these data.
- –
- Multi-scale Discriminative Patches for Fined-Grained Visual Categorization–
The feedback mechanism of CNN to extract multi-scale discriminative patches to solve fine-grained visual categorization (FGVC) and shows more significance than the whole object region.
- Sketch Based Model-Like Standing Style Recommendation–
A method to recommend custom model-like standing style based on model sketches by translating the real images of splendid models into sketches by fast person detection and model sketching and introduces a novel method to score the standing posture of the input image through multi-Gaussian functions.
- –
- Magnetic Resonance Super-resolution Imaging Measurement with Dictionary-optimized Sparse Learning–
This work proposes a framework of dictionary-optimized sparse learning based MR super-resolution method to solve the problem of sample selection for dictionary learning of sparse reconstruction and shows that the dictionary- optimized sparse learning improves the performance of sparse representation.
- –
- Why does the sketch look so vivid?–
This paper explores the key to a good sketch by a weak supervised approach to discovery discriminative patches for different categories of sketches and analyses the visual results and gives a reasonable discussion about good and bad sketches.
- Blur Detection Using Multi-method Fusion–
A new methodology for blur detection with multi-method fusion that not only models the contribution from individual blur detection result but also the interrelation between neighbouring pixels is presented.
- Using Label Propagation to Get Confidence Map for Segmentation–
A novel algorithm to segment objects from the existed segmentation results of the co-segmentation algorithms that adopts mask transformation from multiple images and discriminatively enhancement from multiple object categories, which can effectively ensure a good performance in both scenarios.
- –
- –
- Latching Dynamics in Potts Network–
The main findings in the paper includes: 1) an appropriate rewiring probability promotes the intra-modular latching transitions, and 2) the average latching chain length and inverse switching ratio are insensitive to the noise and feedback connections.
- Memorable basis–
This paper is able to quantitatively characterize an image's memorability which allows us to train sparse bases from the most memorable images instead of randomly selected natural images and demonstrates the superior performance of the Memorable Basis compared to traditional sparse basis trained from unselected images.
- –
- Modular Scale-Free Function Subnetworks in Auditory Areas–
To explore the microscopic subnetworks in auditory modality, the mean shift algorithm is proposed to cluster the fMRI time courses in the corresponding activation areas and several heuristic conclusions are obtained.
- Stable Fast Rewiring Depends on the Activation of Skeleton Voxels–
This work is the first to observe that skeleton voxels may be essential for the fast rewiring process, and its analysis on the structure of functional network supports the scale-free hypothesis.
- Probe the Potts States in the Minicolumn Dynamics–
A model is proposed to analyze the dynamics of minicolumn and it is found that Potts states may originate from the temporary high synchronization of neuronal subsets, and a novel and important assumption that, intrinsically-busting neurons may play a critical role in stabilizing the PottsStates.
- A spatiotemporal context phrase description for general dynamic texture–
This paper proposes a novel dynamic texture description method base on spatiotemporal context phrase for general dynamic texture, and presents a space time constraint and salience rank strategies to extract the representative interest points.
- Contextual dictionaries for image super resolution–
Through adopting discriminative features instead of common features, the method train and use contextual dictionary in the SR process and uses the first-order and second-order gradients of patch as representation, which ensures the neighbor information is introduced in theSR processing.
- –
- –
- –
- –
- –
- –
- –
- GEOMETRIC AND ALGEBRAIC APPROACHES OF PLANAR STRUCTURE RECOVERY BASED ON PROPERTIES OF DUAL CONIC–
In this article, approaches of planar Euclidean Structure recovery are proposed based on the geometric and algebraic characteristics of the dual conic, to attain a generalized framework for the problem.
- Visual and textual fusion for semantically supervised region-based retrieval–
Better annotation and retrieval performance than current methods were reported on both COREL 10,000 and Flickr web image database, which demonstrated the effectiveness of the proposed framework.
- –
- –
- –
- Improved AdaBoost method to increase recognition rate of traditional lip-reading system based on HMM method–
A lip-reading recognition method based on AdaBoost is proposed in this paper, which solves the overlap problem of sample space, and improves the performance of recognition by strengthening training the samples that are difficult to be classified correctly.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.