Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks209 from public data
- Spatial–temporal convolutional neural networks for anomaly detection and localization in crowded scenes273
The proposed method for detecting and locating anomalous activities in video sequences of crowded scenes is a coupling of anomaly detection with a spatial-temporal Convolutional Neural Networks (CNN), which to the best of the knowledge has not been previously done.
- Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images206
A novel adjacent context coordination network (ACCoNet) to explore the coordination of adjacent features in an encoder–decoder architecture for RSI-SOD, which outperforms 22 state-of-the-art methods under nine evaluation metrics, and runs up to 81 fps on a single NVIDIA Titan X GPU.
- RGB-T Semantic Segmentation With Location, Activation, and Sharpening205
This paper proposes a novel feature fusion-based network for RGB-T semantic segmentation, named LASNet, which follows three steps of location, activation, and sharpening, and proposes three specific modules for better segmentation.
- The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances165
This survey article presents a comprehensive review about the recent advance of each element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved their capability of them.
- DiffusionAD: Norm-Guided One-Step Denoising Diffusion for Anomaly Detection142
DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network, is introduced and a norm-guided paradigm is proposed to integrate the benefits of multiple noise scales, enhancing the fidelity of reconstructions.
- 133
- A Deep Neural Network Combined CNN and GCN for Remote Sensing Scene Classification133
A novel two-stream architecture that combines global-based visual features and object-based location features, so as to improve the feature representation capability of features and achieves competitive accuracy against other state-of-the-art approaches is introduced.
- DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction120
The DiffMOT is the first to introduce a diffusion probabilistic model into the MOT to tackle non-linear motion prediction, and optimizes the diffusion process with much fewer sampling steps.
- Student Network Learning via Evolutionary Knowledge Distillation114
Instead of a fixed pre-trained teacher, an evolutionary teacher is learned online and consistently transfers intermediate knowledge to supervise student network learning on-the-fly to improve the transfer effectiveness of teacher knowledge.
- Detecting Deepfake Videos with Temporal Dropout 3DCNN111
A Temporal Dropout 3-Dimensional Convolutional Neural Network (TD-3DCNN) is proposed to detect deepfake videos and can enhance the representation and generalization ability, avoiding model overfitting and improving detecting accuracy.
- TMSDNet: Transformer with multi‐scale dense network for single and multi‐view 3D reconstruction108
This article proposes a novel framework TMSDNet (transformer with multi‐scale dense network) for single‐view and multi‐view 3D reconstruction with transformer to solve the problem of transformer‐based3D reconstruction.
- Improving Remote Sensing Scene Classification by Integrating Global-Context and Local-Object Features85
A novel end-to-end CNN by integrating the GCFs and local-object-level features (LOFs) that outperformed the existing scene classification methods and achieved state-of-the-art results for all three datasets.
- 82
- Deepfake Video Detection via Predictive Representation Learning64
A predictive representative learning approach termed Latent Pattern Sensing to capture semantic change characteristics for deepfake video detection, which can simultaneously describe the latent patterns of videos across frames spatially and temporally in a unified way, leading to an effective and robust deep fake video detector.
- Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking62
This work proposes to learn Occlusion-Robust Representations (ORR) based on ViTs for UAV tracking by enforcing an invariance of the feature representation of a target with respect to random masking operations modeled by a spatial Cox process.
- Deepfake Video Detection with Spatiotemporal Dropout Transformer60
This paper proposes a simple yet effective patch-level approach to facilitate deepfake video detection via spatiotemporal dropout transformer that reorganizes each input video into bag of patches that is then fed into a vision transformer to achieve robust representation.
- 55
- 53
- Multi-Scale CNN Based Garbage Detection of Airborne Hyperspectral Data53
A new hyperspectral image (HSI) classification network MSCNN (Multi-Scale Convolutional Neural Network) is proposed to classify the pixels of HSI data and generate binary garbage segmentation map and the experiment results show that the proposed algorithm has a good performance on garbage detection in large areas.
- Dual Spoof Disentanglement Generation for Face Anti-Spoofing With Depth Uncertainty Learning49
A lightweight Depth Uncertainty Module (DUM), which alleviates the adverse effects of noisy samples by depth uncertainty learning, developed without extra-dependency, thus can be flexibly integrated with any depth supervised network for face anti-spoofing.
- Text detection in scene images based on exhaustive segmentation49
This paper proposes a novel method, which is based on exhaustive segmentation, to detect text in scene images, and argues that the text line grouping problem can be posed as the edge cut of the fully connected graph.
- 44
- Trustable Co-Label Learning From Multiple Noisy Annotators39
This paper proposes a data-efficient approach, called Trustable Co-label Learning (TCL), to learn deep classifiers from multiple noisy annotators when a small set of trusted data is available, which effectively uses trusted data as a guide to generate trustable soft labels (termed co-labels).
- Flexible Auto-Weighted Local-Coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering39
A novel unsupervised Robust Flexible Auto-weighted Local-coordinate Concept Factorization framework is proposed for clustering high-dimensional data, which improves the representations by enhancing the robustness of CF to noise and errors, providing a flexible constraint on the reconstruction error and optimizing the locality jointly.
- Introduction to the Special Issue on Trustworthy Multimedia Computing and Applications in Urban Scenes36
The goal of this special issue (SI) is to encourage a collaborative endeavor to explore the possibilities and obstacles associated with trustworthy multimedia analysis and gather inventive approaches, systems, and applications focused on trustworthy multimedia computing and its applications in urban environments.
- 36
- Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking35
AVTrack, an adaptive computation tracking framework that adaptively activates transformer blocks through an Activation Module (AM), which dynamically optimizes the ViT architecture by selectively engaging relevant components to address extreme viewpoint variations is proposed.
- Hyperspectral Image Denoising via Adversarial Learning35
This paper proposes an end-to-end HSI denoising model via adversarial learning that captures the subtle noise distribution from both spatial and spectral dimensions, and designs a Residual Spatial-Spectral Module and embed it in an UNet-like structure as the generator to obtain clean images.
- Talking Face Generation with Expression-Tailored Generative Adversarial Network35
An end-to-end Expression-Tailored Generative Adversarial Network (ET-GAN) to generate an expression enriched talking face video of arbitrary identity and the results show the effectiveness of the ET-GAN in generating high quality expressional talking face videos against existing state-of-the-arts.
- 34
- Super-Pixel Cloud Detection Using Hierarchical Fusion CNN34
Considering super-pixel level remote sensing images contain less semantic information compared with general object classification database, a Hierarchical Fusion CNN (HFCNN) is proposed, which takes full advantage of low-level features like color and texture information and is more applicable to cloud detection task.
- Fast cascade face detection with pyramid network33
This paper proposes a fast CNNs cascade face detector with multi-task learning and network acceleration techniques, which is comparable in performance with the-state-of-arts while the speed reaches astonishing 165 fps on Titan GPU.
- 32
- CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-Adversarial Contrastive Learning30
It is shown that the positive and negative samples can be cooperatively and adversarially learned by minimizing and maximizing the contrastive loss, respectively.
- Low-Resolution Object Recognition With Cross-Resolution Relational Contrastive Distillation30
This study proposes a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition that enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects.
- 30
- HSI-IPNet: Hyperspectral Imagery Inpainting by Deep Learning With Adaptive Spectral Extraction30
This work proposes an end-to-end inpainting framework for HSI based on convolutional neural networks, which does not require auxiliary images and makes full use of both spectral characteristics and spatial information.
- 29
- Semi-Siamese Training for Shallow Face Learning29
Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.
- 28
- Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation27
This work proposes a discriminative-generative distillation approach to learn privacy-preserving deep models, taking models as bridge to distill knowledge from private data and then transfer it to learn a student network via two streams.
- A New Simplification Algorithm for Scattered Point Clouds with Feature Preservation27
A new simplification algorithm for scattered point clouds with feature preservation, which can reduce the amount of data while retaining the features of data, is proposed and can be applied to models with different curvatures and effectively avoid the hole phenomenon in the simplification process.
- 26
- Multi-oriented text detection from natural scene images based on a CNN and pruning non-adjacent graph edges26
A novel method that effectively and robustly detects multi-oriented text in natural scene images by employing an exhaustive segmentation-based method that can extract characters in arbitrary orientations.
- 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly23
This work proposes a new large-scale anomaly detection dataset called 3CAD, which is derived from real 3C production lines and introduces a simple yet effective framework for unsupervised anomaly detection: a Coarse-to-Fine detection paradigm with Recovery Guidance (CFRG).
- 23
- Column-Spatial Correction Network for Remote Sensing Image Destriping21
A multi-scaled column-spatial correction network (CSCNet) is proposed for remote sensing image destriping, in which the local structural characteristic of stripe noise and the global contextual information of the image are both explored at multiple feature scales.
- Portable System for Box Volume Measurement Based on Line-Structured Light Vision and Deep Learning20
A novel 2 × 2 laser line grid projector, a sensor, and software modules, with which only two laser-modulated images of boxes are required for volume measurement, based on line-structured light vision and deep learning.
- Model and error analysis for coded structured light measurement system20
A new concise and efficient mathematical model for coded structured light measurement system to obtain depth information and the system model based on optimal parameters is utilized to implement reconstruction for two objects.
- EFDCNet: Encoding fusion and decoding correction network for RGB-D indoor semantic segmentation19
A novel Encoding Fusion and Decoding Correction Network (EFDCNet) for RGB-D indoor semantic segmentation that establishes the global dependencies between RGB and depth features via the self-attention mechanism to enhance the cross-modal feature interactions, extracting discriminant and powerful features.
- 19
- Proposal pyramid networks for fast face detection19
Results on several public benchmarks show that the proposed face detector achieves comparable accuracy to the-state-of-arts while the detection speed reaches 60 FPS with an i5 CPU, which significantly exceeds previous DCNN-based face detectors.
- Bag of Shape Features with a learned pooling function for shape recognition19
The pooling function is formulated as a weighted sum of max pooling and average pooling, where the weight is expressed by an activation function of the input shape features, and fed into a SVM classifier to minimize a shape classification loss.
- Accurate UAV Tracking with Distance-Injected Overlap Maximization18
This work is improving the accuracy of target localization by deriving a conceptually simple target localization loss and a global feature recalibration scheme in a mutual reinforced way, and its minimal solution can alleviate the drift problem caused by camera motion.
- 17
- 16
- 16
- Hyperspectral image classification based on spectral and spatial information using ResNet with channel attention16
Experimental results with widely used hyperspectral image datasets demonstrate that, the proposed HSI classification framework based on the CNN has achieved better performance in comparison with state-of-the-art classifiers and conventional deep learning-based classifiers.
- 15
- 15
- Latent Pattern Sensing: Deepfake Video Detection via Predictive Representation Learning15
This work proposes a predictive representative learning approach termed Latent Pattern Sensing to capture semantic change characteristics for deepfake video detection, which cascades a CNN-based encoder, a ConvGRU-based aggregator and a single-layer binary classifier.
- 15
- Volumeter: 3D human body parameters measurement with a single Kinect14
A novel method is presented to measure the volume and perimeter of human body with the truncated signed distance function values of voxels, and the proposed method achieves comparable accuracy to the state of the arts.
- SDFC dataset: a large-scale benchmark dataset for hyperspectral image classification13
A large-scale benchmark dataset for conducting hyperspectral image classification to address issues raised by existing datasets, and a comprehensive review and analysis of the representative classification models on both existing and proposed datasets demonstrate the advantages and challenges of the proposed dataset.
- 13
- NPCFace: A Negative-Positive Cooperation Supervision for Training Large-scale Face Recognition.13
A novel Negative-Positive Cooperation loss, named NPCFace, is formulated, which emphasizes the training on both the negative and positive hard cases via a cooperative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation.
- A spatial-spectral clustering-based algorithm for endmember extraction and hyperspectral unmixing13
The proposed SP2C adopts a local spatial-spectral clustering strategy to obtain a set of spatially homogenous regions and exploits a spectral purity index calculation strategy to choose pure pixels on the regions to mitigate the effect of spectral variability on unmixing.
- Dimension Measurement and Key Point Detection of Boxes through Laser-Triangulation and Deep Learning-Based Techniques13
This work studies a hand-held structured light vision system for boxes that measures dimension information through laser triangulation and deep learning using only two laser-box images from a camera and a cross-line laser projector.
- Cloud Detection Using Super Pixel Classification and Semantic Segmentation13
This paper introduces a cloud detection method based on super pixel level classification and semantic segmentation and shows that compared with other cloud detection methods, the proposed method achieves better performance.
- 12
- Three-Dimensional Measurement Method of Four-View Stereo Vision Based on Gaussian Process Regression12
A three-dimensional measurement method of four-view stereo vision based on Gaussian process (GP) regression based on Bayesian inference method for point cloud data that is superior to the traditional methods in measurement accuracy and reconstruction effect is proposed.
- Neighborhood geometry based feature matching for geostationary satellite remote sensing image12
Experimental results on 25 pairs of newly annotated images show that the proposed method is competitive to several prior arts with respect to matching accuracy, and significantly more efficient than others.
- Augmented Feature Fusion for Image Retrieval System12
This work adopts the reciprocal neighbor based graph fusion approach for feature fusion and explicitly augments the original approach with the following two strategies: 1) investigates the most suitable feature combinations on various datasets, including the deep learning feature, which has been popular for image retrieval recently; 2) further improves the robustness of originalgraph fusion approach by the SVM prediction strategy.
- 12
- 11
- 11
- 11
- 11
- Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models10
This paper introduces a novel VLM-guided cascaded framework, which treats the segmentation output as a soft spatial prior via the alpha channel, which retains the full image context while providing precise spatial guidance, leading to more accurate and context-aware classification of camouflaged objects.
- 10
- 10
- 10
- GLCSA-Net: global–local constraints-based spectral adaptive network for hyperspectral image inpainting10
A Global-Local Constraints-based Spectral Adaptive Network (GLCSA-Net) for HSI inpainting is proposed, which outperforms the state-of-the-art methods in quantitative and qualitative assessments and constrain the generation of missing areas from both global and local perspectives.
- Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation10
Experimental results on the open dataset NUS48E show that both the vibrato modeling and the latent energy representation could significantly improve the expressiveness of singing voice.
- Convolutional Neural Network-Based Radar Antenna Scanning Period Recognition10
A method using the convolutional neural network to recognize the antenna scanning period of radar under the condition that antennas of the radar and EW system both scan circularly, where the average recognition accuracy is at least 90% when the signal to-noise ratio (SNR) is not less than 30 dB, significantly higher than the recognition accuracy of NAC and AFT methods based on adaptive threshold detection.
- Slope-Restricted Multi-Scale Feature Matching for Geostationary Satellite Remote Sensing Images10
This paper proposes a novel algorithm named slope-restricted multi-scale feature matching, which is based on local geometric similarity to enhance the matching performance, and shows that the proposed method is more accurate and efficient than other algorithms.
- 9
- 9
- Precision in pursuit: a multi-consistency joint approach for infrared anti-UAV tracking9
This work presents a multi-consistency joint approach tailored for infrared anti-UAV tracking that dynamically selects alternate templates to ensure feature consistency, thereby maintaining stable tracking even in the face of drastic pose changes.
- 9
- 9
- A 3D Mask Presentation Attack Detection Method Based on Polarization Medium Wave Infrared Imaging9
Experimental results show that, compared with conventional thermal infrared imaging, polarization-based MWIR imaging is more suitable for the PAD method of 3D silicone masks and shows a certain robustness in the change of facial temperature.
- 9
- 8
- 8
- Attention Modulated Multiple Object Tracking with Motion Enhancement and Dual Correlation8
It is demonstrated that the proposed MAC-MOT can achieve a better performance than the baseline state of the arts (SOTAs) and is evaluated on the popular multiple object tracking benchmarks MOT16 and MOT17.
- 8
- 8
- 7
- Learning motion blur robust vision transformers for real-time UAV tracking7
A significant enhancement introduced in this paper is the improved effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both, by acquiring motion blur robust representations through enforcing invariance in the feature representation of the target with respect to simulated motion blur.
- 7
- Goal or Miss? A Bernoulli Distribution for In-Game Outcome Prediction in Soccer7
IGSOP provides a novel perspective to solve the problem of in-game outcome prediction in soccer, which has a potential ripple effect on related research.
- SCRnet: A Spatial Consistency Guided Network Using Contrastive Learning for Point Cloud Registration7
This work proposes a spatial consistency guided network using contrastive learning for point cloud registration (SCRnet), in which its overall stage is symmetrical.
- Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks7
Inspired by the human “visual tracking” capability which leverages motion cues to distinguish the target from the background, a Two-Stream Residual Convolutional Network (TS-RCN) for visual tracking is proposed, which successfully exploits both appearance and motion features for model update.
- One-shot monochromatic symbol pattern for 3D reconstruction using perfect submap coding7
The symbol density spectrum (SDS) and its features are used to choose symbols for improving resolution and decreasing decoding error of perfect submap symbol patterns.
- 6
- Hyperspectral anomaly detection with vision transformer and adversarial refinement6
This paper proposes a hyperspectral anomaly detector based on vision-transformer, which outperforms state-of-the-art competitors and uses an adversarial strategy to suppress the reconstruction of anomalies and refine the results based on suppressed images.
- Analyzing and Combating Attribute Bias for Face Restoration6
It is argued that FR should consider not only image quality as in existing works but also attribute bias, and the DebiasFR framework is proposed to produce HR faces with high image quality and accurate facial attributes.
- A New Dataset and Deep Residual Spectral Spatial Network for Hyperspectral Image Classification6
An HSI classification framework named deep residual spectral spatial setwork (DRSSN) is proposed, which can be deeper to extract features with better discrimination and alleviate insufficient training caused by unbalanced sample sizes between easily and hard classified samples.
- Abnormal events detection in crowded scenes by trajectory cluster6
Experimental results indicated that the proposed algorithm could be used to reliably locate the abnormal events in crowded scenes.
- Regularity Guaranteed Human Pose Correction6
The experimental results demonstrate that the proposed pose correction approach not only improves the accuracy, but also outputs more regular poses, compared to the-state-of-the-art.
- 6
- PKI: Prior knowledge-infused neural network for few-shot class-incremental learning5
This work retains more prior knowledge and proposes a prior knowledge-infused neural network (PKI) to facilitate FSCIL, and designs two variants of the prior knowledge-infused neural network to trade off a balance between resource consumption and performance by reducing the number of projectors.
- Enhancing UAV tracking: a focus on discriminative representations using contrastive instances5
This paper has shown that the DRCI (discriminative representation with contrastive instances) tracker outperforms current state-of-the-art UAV tracking methods, underscoring its potential to effectively tackle the persistent challenges in this field.
- 5
- 5
- Multi-Agent Semi-Siamese Training for Long-Tail and Shallow Face Learning5
The theoretical and empirical analysis is given that, given the long-tail (or shallow) data and training loss, MASST smooths the loss landscape and satisfies the Lipschitz continuity with the help of multiple agents and the updating gallery queue.
- Efficiency and Precision Trade-offs in UAV Tracking with Filter Pruning and Dynamic Channel Weighting5
This paper proposes a dynamic channel weighting strategy to improve the rank-based pruning method which uses the average rank of each filter response as the pruning criterion and achieves better precisions when compressing the original model SiamFC++ with a global pruning ratio.
- Defending Against Adversarial Examples via Soft Decision Trees Embedding5
This paper extracts the semantic features of adversarial examples with a feature extraction network and embeds a specific soft decision tree embedded to select the key semantic features for each feature map from convolutional layers and the selected features are fed to a light-weight classification network.
- 5
- Integrating Low-Level Visual Cues for Enhanced Unsupervised Semantic Segmentation4
This work proposes integrating low-level visual cues to complement high-level visual cues derived from self-supervised pre-training branches to enhance consistent feature learning and introduces contrast loss functions based on color invariance and luminosity invariance, which improve the learning of features from different semantic categories.
- 4
- 4
- Personalized Federated Learning via Backbone Self-Distillation4
A backbone self-distillation approach to facilitate personalized federated learning that involves learning two components: the shared backbone for common representation and the private head for local personalization, which enables effective global knowledge transfer.
- Region-guided network with visual cues correction for infrared small target detection4
A Region-Guided Network with visual cues correction (RGNet) with Region Guidance Module embedded in shallow layers to generate the foreground mask by leveraging rich visual details contained in low-level features for IRSTD detection.
- Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation4
This paper presents an effective teacher-student learning approach to train privacy-preserving deep learning models via differentially private data-free distillation, and proposes a label differential privacy algorithm termed selective randomized response to protect the label information.
- MS-AFF: a novel semantic segmentation approach for buried object based on multi-scale attentional feature fusion4
A multi-scale attentional feature fusion module for infrared image semantic segmentation and a global spatial information attention module is employed to let the model focus on the target region and reduce disturbance in infrared images’ background.
- 4
- 4
- Robust and efficient method for matching features in omnidirectional images4
Experiments show that TPBRIEF greatly improves the feature matching accuracy and ALPGMS robustly removes wrong matches, and the proposed method outperforms the state-of-the-art methods.
- STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection3
A novel Superpixel Token Enhancing Network (STENet) is proposed, which introduces superpixels into cross-modal interaction and updates the superpixel generation method by expanding the neighborhood range of each superpixel, allowing for flexible transformation between pixels and superpixels.
- 3
- 3DBench: A scalable benchmark for object and scene-level instruction-tuning of 3D large language models3
The Bench-model is introduced, which integrates advanced detection models to significantly enhance MLLM performance and is compared against open-sourced 3D LLMs, analyzing the impact of different model architectures, training protocols, and public datasets.
- 3
- TLtrack: Combining Transformers and a Linear Model for Robust Multi-Object Tracking3
A motion-based algorithm named TLtrack is presented, which adopts a hybrid strategy to make motion estimates based on confidence scores, and can not only consider the historical information of the trajectory, but also analyze the latest movements.
- 3
- Geometry-Based Global Alignment for GSMS Remote Sensing Images3
A geometry-based global alignment method to align landmarks and non-landmarks in the GSMS images with high accuracy, recall and significantly low computation complexity is proposed.
- Face database generation based on text–video correlation3
A face database generation framework based on text-video correlation, which is able to reduce 90% of the human effort in face database construction, is proposed and introduced.
- 2
- 2
- 2
- MCFINet: A Cost-Efficient Multi-Channel Feature Integration Network for Surface Scenarios Image Super-Resolution2
A Multi-Channel Feature Integration Network (MCFINet), designed to maximize input pixel utilization while minimizing computational overhead, and integrates both local and global features within the channels, thereby exploiting their complementary advantages.
- 2
- ED2IF2-Net: Learning Disentangled Deformed Implicit Fields and Enhanced Displacement Fields from Single Images Using Pyramid Vision Transformer2
This paper proposes the first end-to-end single-view 3D reconstruction network based on the Pyramid Vision Transformer (PVT), called ED2IF2-Net, which disentangles the reconstruction of an implicit field into the reconstructionof topological structures and the recovery of surface details to achieve high-fidelity shape reconstruction.
- Combating spatial redundancy with spectral norm attention in convolutional learners2
This work proposes spectral norm attention (SNA), a novel yetcient attention block to help convolutional neural networks (CNNs) highlight informative features and adopts the power iteration algorithm to approximate the spectral norm to reduce the matrix computation overhead during training, thus keeping inference speed on par with vanilla CNNs.
- 2
- Boosting Relationship Detection in Images with Multi-Granular Self-Supervised Learning2
This article integrates the standard relationship detection objective with a series of proposed self-supervised proxy tasks, which is named as Multi-Granular Self-Supervised learning (MGS), appealing in view that it is pluggable to any neural relationship detection models by simply including the proxy tasks during training, without increasing the computational cost at inference.
- 2
- 2
- Accurate per-pixel hand detection from a single depth image2
A per-pixel hand detection system using one single depth image is introduced, a circle sampling depth-context feature is proposed for hand regions representation, and a multilayered hand detection model is built forHand regions detection.
- A Triangle Division Based Point Matching for Image Registration2
A simple and robust method to get more accurate matching points by using the structural information of divided triangles using Delaunay Triangulation and an algorithm called K-Nearest Neighbor Dis-ratio is presented.
- 2
- Rheology-based facial animation realistic face model2
Experimental results show that this rheology-based approach to animate realistic face model can realistically simulate the mechanical properties and motion characteristics of human face, and performance of this method is satisfactory.
- 1
- 1
- 1
- 1
- 1
- 1
- SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking1
The proposed SAMViTrack sets a new baseline, especially by combining Mamba and ViT, for UAV tracking by offering a balance between speed, accuracy, and adaptability in dynamic environments.
- 1
- 1
- Multi-view contextual adaptation network for weakly supervised object detection in remote sensing images1
This work proposes a model termed the Multi-View Contextual Adaptation Network (VCANet), which incorporates an contextual adaptation perception, within a multi-view learning framework, and integrates a pseudo-label filtering process to eliminate inaccurate pseudo-labels.
- 1
- 1
- 1
- Adaptive filter based on FPGA implementation of LMS algorithm1
An adaptive filter based on Cyclone IV EP4CE6 series FPGA is adopted to realize the minimum mean square error (LMS) adaptive algorithm and the peripheral hardware circuit to solve the automatic updating of the filter weight coefficient.
- 1
- AI-SAS: Automated In-match Soccer Analysis System1
This work presents an Automated In-match Soccer Analysis System (AI-SAS), using a domain-knowledge-based multi-view global tracking, providing real-time in-match team- and individual-level statistics and analyses.
- 1
- 1
- Compressing Deep Neural Network for Facial Landmarks Detection1
This work proposes a method to compress large deep neural networks, which includes importance-based neuron pruning, and introduces weights correlations to prune unimportant neurons, which can reduce index storage and inference computation costs.
- Fast large-scale object retrieval with binary quantization1
This paper proposes a feature quantization algorithm called binary quantization, which converts a scale-invariant feature transform (SIFT) feature into a descriptive and discriminative bit-vector, which allows itself to adapt to the classic inverted file structure for box indexing.
- Three-dimensional deformation in curl vector field1
This paper presents a new method to construct a vector field for volume-preserving mesh deformation of free-form objects and introduces distance field into vector field construction; as a result, the shape of the curl vector field is closely related to the object shape.
- 1
- 1
- –
- –
- –
- –
- From part to whole: Structural semantic knowledge guided airplane detection in remote sensing images–
- –
- –
- –
- SFusion: Energy and Coding Fusion for Ultra-Robust Low-SNR LoRa Networks–
SFusion is presented, a software-based coding framework that jointly leverages signal-level aggregation and coding-level redundancy to enhance LoRa's robustness and achieves up to 15 dB gain over SF12 and up to 13 dB improvement over state-of-the-art solutions.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- A superpixel region merging based nonuniformity correction method for hyperspectral images–
The experimental results confirm that the proposed NUC-SRM method can effectively eliminate the nonuniformity of HS images without any significant information loss compared with the state-of-the-art techniques.
- –
- –
- Mi-Based Tencent Micro-Blog Research–
A dual research scheme of macro and micro to analyze the key indicators that affect user experience and show that Tencent Micro-blog should adjust the service resources properly according to its own business characteristics and save network overhead from the perspective of the system optimization.
- Robust multi-planar region detection for image mosaic based on hierarchical clustering mechanism–
A robust detection method that can detect multi-planar regions correctly without pre-determining the number of regions, and the corresponding clustered feature point pairs can be easily utilised for image mosaic.
- Indication position estimation method using the homography between planes–
To get a rapid estimation of the user′s indication position in the computer vision based non-contact human-computer interaction (HCI) system, an indication position estimation method without explicitly calculating the camera parameters was proposed.
- Ghost-free condition for light field rendering of multi-layer scenes–
The ghost-free condition is proposed to avoid the ghosting effect caused by the insufficient sampling rate when rendering the multi-layer scenes by the light-field method and the results sufficiently support the theoretical analysis.
- Ghost-free reconstruction of multi-layer scenes using light-field method–
It is shown that the optimal constant depth and the maximum camera interval can be determined by the scene geometry and the camera resolution.
- –
- Multi-curve spectrum representation of facial movements and expressions–
This paper presents a method of multi-curve spectrum representation of facial movements and expressions based on 3DMCF (3D muscle-controlled facial) model, and the performance of the proposed method is among the best.
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 2026-10-15. 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.