Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Zhengkai LiuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works356 from public data
- 924
- LightenNet: A Convolutional Neural Network for weakly illuminated image enhancement506
A trainable Convolutional Neural Network is proposed for weakly illuminated image enhancement, namely LightenNet, which takes a weakly illumination image as input and outputs its illumination map that is subsequently used to obtain the enhanced image based on Retinex model.
- Video Summarization With Attention-Based Encoder–Decoder Networks392
This paper proposes a novel video summarization framework named attentive encoder–decoder networks forVideo summarization (AVS), in which the encoder uses a bidirectional long short-term memory (BiLSTM) to encode the contextual information among the input video frames.
- Efficient HOG human detection353
Experimental results on the top-view database and the well-known INRIA data set have demonstrated the effectiveness and efficiency of the proposed HOG+SVM method.
- 325
- Photo2Trip314
This paper proposes to leverage existing travel clues recovered from 20 million geo-tagged photos collected from www.panoramio.com to suggest customized travel route plans according to users' preferences, and can provide a customized trip plan for a tourist.
- 281
- ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation276
A generic medical segmentation method, called Edge-aTtention guidance Network (ET-Net), which embeds edge-attention representations to guide the segmentation network, which outperforms current state-of-the-art segmentation methods.
- Learning Pooling for Convolutional Neural Network274
A learned pooling operation obtained by end-to-end training which is called LEAP (LEArning Pooling), inspired by the LEAP operation, and one simplified convolution operation to replace the traditional convolution which consumes many extra parameters are proposed.
- Mask-Guided Attention Network for Occluded Pedestrian Detection223
A novel mask-guided attention network is introduced that emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features and it is empirically demonstrated that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts.
- Convolution in Convolution for Network in Network222
The proposed method is called convolution in convolution (CiC), and one or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel–spatial domain, and the experimental results demonstrate the effectiveness of the proposed CiC method.
- Robust Tensor Analysis With L1-Norm206
Experimental results upon face and other datasets demonstrate the advantages of the proposed L1-norm-based tensor analysis (TPCA-L1), which is robust to outliers.
- SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation200
A fast single-stage instance segmentation method that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box, leading to improved mask predictions and a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection.
- Consensus-Aware Visual-Semantic Embedding for Image-Text Matching196
A Consensus-aware Visual-Semantic Embedding model is proposed to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching and learns the associations and alignments between image and text based on the exploited consensus.
- Equip tourists with knowledge mined from travelogues191
This paper proposes a probabilistic topic model, named as Location-Topic model, which has the advantages of differentiability between two kinds of topics, i.e., local topics which characterize locations and global topics which represent other common themes shared by various locations.
- 176
- Fully affine invariant SURF for image matching161
The proposed algorithm makes full use of the affine invariant advantage of ASIFT and the efficient merit of SURF while avoids their drawbacks and demonstrates the robustness and efficiency of the proposed algorithm.
- From Handcrafted to Deep Features for Pedestrian Detection: A Survey160
An extensive review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches is presented and it is found that hand crafted features with large freedom degrees in shape and space have better performance.
- Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation155
A new Cascaded Hierarchical Atrous Pyramid Pooling (CHASPP) module, consisting of two cascaded components, that not only rich local detail characteristics can be comprehensively presented, but also important global contextual information can be effectively exploited to improve the prediction accuracy.
- Learning Compositional Neural Information Fusion for Human Parsing141
This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing, formulate the approach as a neural information fusion framework that is extensively evaluated on four popular datasets.
- 140
- Deep neural networks with Elastic Rectified Linear Units for object recognition139
A novel Elastic Rectified Linear Unit (EReLU) that focuses on processing the positive part of input is proposed that improves model fitting with no extra parameters and little overfitting risk and is able to further improve the performance of networks.
- Deep Contextual Attention for Human-Object Interaction Detection138
This work proposes a contextual attention framework for human-object interaction detection that leverages context by learning contextually-aware appearance features for human and object instances and adaptively selects relevant instance-centric context information to highlight image regions likely to contain human- object interactions.
- Improved prototypical networks for few-Shot learning132
This work proposes an attention-analogous strategy to explore the class distribution information by distributing different weights to samples based on their representativeness and proposes a distance scaling strategy to reduce the intra- class difference while enlarge the inter-class difference.
- 130
- Patient-specific ECG classification by deeper CNN from generic to dedicated127
The proposed mechanism of fine-tuning the GCNN to TDCNN improves the efficiency for training patient-specific CNN classifier and the state-of-the-art performance on efficiency and accuracy for ECG classification over MIT-BIH dataset is achieved.
- From one tree to a forest126
A set of weak but general features to characterize vertical knowledge (including attribute-specific semantics and inter-attribute layout relationships) are designed that can be adopted in various verticals without redesign; meanwhile, they are weak enough to avoid overfitting of the learnt knowledge to seed sites.
- Toward improving ECG biometric identification using cascaded convolutional neural networks117
A new generic convolutional neural network (CNN) approach (i.e., Cascaded CNN) to realize human identification via ECG biometric identification, with strong generalization ability and real-time efficiency is proposed.
- Learning Multilayer Channel Features for Pedestrian Detection116
A unifying framework called multi-layer channel features (MCF) is proposed that integrates HOG+LUV with each layer of CNN into a multi- layer image channels and achieves the state of the art on Caltech pedestrian data set.
- Hierarchical Human Parsing With Typed Part-Relation Reasoning115
This work seeks to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures by assimilating generic message-passing networks with their edge-typed, convolutional counterparts and lays the foundation for more sophisticated and flexible human relation patterns of reasoning.
- 115
- 114
- Saliency-Guided Attention Network for Image-Sentence Matching114
A Saliency-guided Attention Network (SAN) is introduced that is characterized by building an asymmetrical link between vision and language to efficiently learn a fine-grained cross-modal correlation.
- Summarizing tourist destinations by mining user-generated travelogues and photos113
A framework which discovers location-representative tags from travelogues and then select relevant and representative photos to visualize these tags is proposed, which provides an informative summary which describes a given destination both textually and visually.
- Spectral Clustering by Joint Spectral Embedding and Spectral Rotation111
This paper proposes a joint model to simultaneously compute the optimal real matrix and binary matrix which is an orthonormal matrix for spectral clustering and demonstrates the effectiveness of the proposed method on benchmark datasets.
- Learning Regularized LDA by Clustering109
This work proposes making use of the structure of the given training data to regularize the between- and within-class scatter matrices by between-and-within-cluster scattermatrices, respectively, and simultaneously, and demonstrates the effectiveness of the proposed method.
- A Cascaded Convolutional Neural Network for Single Image Dehazing105
Qualitatively and quantitatively experimental results demonstrate that the proposed method effectively removes haze from such images, and outperforms several state-of-the-art dehazing methods.
- Neighborhood Preserving Projections (NPP): A Novel Linear Dimension Reduction Method99
A novel unsupervised linear dimension reduction method, Neighborhood Preserving Projections (NPP), is proposed, which aims to approximate the classical locally linear embedding by introducing a linear transform matrix.
- 98
- 97
- Virtual-scanning light-field microscopy for robust snapshot high-resolution volumetric imaging94
It is shown that VsLFM achieves ultrafast 3D imaging of diverse processes such as the beating heart in embryonic zebrafish, voltage activity in Drosophila brains and neutrophil migration in the mouse liver at up to 500 volumes per second.
- Robust CoHOG Feature Extraction in Human-Centered Image/Video Management System90
A framework that utilizes a novel gradient decomposition and combination strategy to make full use of the information of gradients, adopts a two-stage gradient smoothing scheme to perform efficient gradient interpolation, and employs incremental principal component analysis to reduce the large dimensionality of the CoHOG features.
- 89
- 89
- 89
- PSTR: End-to-End One-Step Person Search With Transformers88
The proposed PSTR is the first to propose an end-to-end one-step transformer-based person search framework that jointly performs person detection and re-identification (re-id) in a single architecture and sets a new state-of-the-art on both benchmarks.
- Attribute-Guided Network for Cross-Modal Zero-Shot Hashing88
A novel attribute-guided network (AgNet) is proposed, which can perform not only IBIR but also text-based image retrieval (TBIR) and bridges the gap caused by modality heterogeneity and zero-shot setting.
- Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning88
A novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions.
- 85
- 79
- 79
- Memorizing Complementation Network for Few-Shot Class-Incremental Learning77
A Memorizing Complementation Network (MCNet) is proposed to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks in few-shot Class-Incremental Learning.
- Distributed Object Detection With Linear SVMs77
This paper develops a distributed object detection framework (DOD) by making the best use of spatial-temporal correlation, and develops CHOG-DOD as an instance of DOD framework, a cell-based HOG (CHOG) algorithm, where the features in one cell are not shared with overlapping blocks.
- 76
- 74
- Triply Supervised Decoder Networks for Joint Detection and Segmentation73
A framework called TripleNet is proposed to deeply boost joint object detection and semantic segmentation and outperforms all the other one-stage methods on both two tasks by a single network.
- USER: Unified Semantic Enhancement With Momentum Contrast for Image-Text Retrieval72
A Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR is proposed, which delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules and incorporates the training mechanism of MoCo into ITR.
- Generating location overviews with images and tags by mining user-generated travelogues71
This paper proposes a location overview generation approach, which first mines location-representative tags from travelogues and then uses such tags to retrieve web images and is presented via a novel user interface which provides an informative overview for a given location.
- 70
- Classifying Discriminative Features for Blur Detection69
A new kernel-specific feature vector consisting of the information of a blur kernel and an image patch and which outperforms the state-of-the-art blur detection method.
- 67
- Deep attentive and semantic preserving video summarization67
This work incorporates the ideas of both the encoder-decoder attention and semantic preserving loss in a deep Seq2Seq framework for video summarization to enhance the robustness of the model to outliers and introduce Huber loss to replace the popular mean square error loss.
- 62
- PSC-Net: learning part spatial co-occurrence for occluded pedestrian detection61
The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a graph convolutional network (GCN).
- 60
- 59
- 58
- Ranking Graph Embedding for Learning to Rerank58
It is shown that introducing ranking information into dimensionality reduction significantly increases the performance of image search reranking.
- 57
- 56
- Speed up deep neural network based pedestrian detection by sharing features across multi-scale models56
This paper proposes to share features across a group of DNNs that correspond to pedestrian models of different sizes that can detect pedestrians of several different scales on one single layer of an image pyramid to improve detection efficiency.
- Multi-label correlation guided feature fusion network for abnormal ECG diagnosis55
The main objective of this paper is to design an ECG abnormal event detection model based on multi-label correlation guided feature fusion, and the proposed method achieves better results compared with other state-of-the-art methods.
- Outlier-resisting graph embedding54
An improved graph embedding algorithm (termed LPP-L1) is proposed by replacing L2-norm with L1-norm, which avoids small sample size problem and ensures robustness to outliers.
- Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction53
This paper proposes to let the similarities and neighbors be variables and model these in a low-dimensional space and obtains the optimal similarity and projection matrix by minimizing a unified objective function and treats the regularization parameter as a variable to be optimized.
- 51
- 51
- Query-aware sparse coding for web multi-video summarization49
A novel query-aware approach is proposed by formulating the multi-video summarization in a sparse coding framework, where the web images searched by a query are taken as the important preference information to reveal the query intent.
- Dual‐domain reconstruction network with V‐Net and K‐Net for fast MRI48
To introduce a dual‐domain reconstruction network with V‐Net and K‐Net for accurate MR image reconstruction from undersampled k‐space data.
- Cascaded Subpatch Networks for Effective CNNs48
This work argues that the representational ability of equal-size strategy is not strong enough and proposes to use subpatch filter whose spatial size is smaller than that of LaTeX, which is used for strengthening the connection between different input feature channels and for reducing the number of parameters.
- Learning Sampling Distributions for Efficient Object Detection48
This paper designs a PD so as to efficiently reject the huge number of nonobject windows and proposes the concepts of rejection, acceptance, and ambiguity windows and regions of iPW, an algorithm of fast and accurate object detection.
- 47
- Randomly translational activation inspired by the input distributions of ReLU47
Compared to the original non-linear activation, the proposed method can improve classification accuracy without increasing computation cost and can be also seen as the regularization of non- linear activation to reduce overfitting.
- 46
- 45
- NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection45
A new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features is proposed, which achieves a better trade-off for real-time and accurate object detection.
- Transductive Zero-Shot Learning With Adaptive Structural Embedding45
Two corresponding methods named Adaptive STructural Embedding (ASTE) and Self-PAced Selective Strategy (SPASS) for visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps are presented.
- Relevance Preserving Projection and Ranking for Web Image Search Reranking45
An HRPP is a spectral embedding algorithm to transform an original high-dimensional feature space into an intrinsically low-dimensional hypersphere space by preserving the manifold structure and a relevance relationship among the images and an H-Rank is a simple but effective ranking algorithm to sort the images by their distances to the hyperspheres center.
- Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification44
A new model that employs a multi-layer convolutional neural network to process the context parallelly and model the context multiple times, where the neural network is able to explicitly learn the sentiment intermediate representation via an attention mechanism is proposed.
- An Improved Nyquist–Shannon Irregular Sampling Theorem From Local Averages43
An improved Nyquist–Shannon sampling theorem from general local averages is obtained and two exact dual frames from local averages are obtained, one of which improves a result by Sun and Zhou.
- 41
- Incremental Learning With Saliency Map for Moving Object Detection41
This paper proposes to incorporate a saliency map into an incremental subspace analysis framework in which theSaliency map makes the estimated background have less of a chance than the foreground to contain salient objects.
- 40
- Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry40
This work proposes two new types of non-neighboring features (NNF): side-inner difference features (SIDF) and symmetrical similarity features (SSF), which can characterize the difference between the background and pedestrian and the differenceBetween the pedestrian contour and its inner part.
- DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer Decoding39
DCMSTRD solves dense captioning by set matching and prediction instead and introduces a multi-scale module, termed multi-scale language decoder (MSLD), to enhance the discriminative quality of the multi-scale representations during caption generation.
- Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects39
A joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder–decoder network that learns to emphasize defect features and suppress background noise during feature fusion, which is beneficial for detecting low-contrast defects.
- Manifold regularized cross-modal embedding for zero-shot learning37
A Manifold regularized Cross-Modal Embedding (MCME) approach for ZSL is proposed by formulating the manifold constraint for intrinsic structure of the visual features as well as aligning pairwise consistency in order to preserve the locally visual structure in the embedding process.
- Hypergraph dominant set based multi-video summarization36
A novel framework with Hypergraph Dominant Set (HDS), termed MVS-HDS is presented, which clearly outperforms the state-of-the-art methods on the multi-Video Summarization (MVS) task.
- 35
- 35
- Count- and Similarity-Aware R-CNN for Pedestrian Detection35
A count-weighted detection loss function that assigns higher weights to the detection errors occurring at highly overlapping pedestrians, and a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity to identify distinct proposals.
- Cascade Learning by Optimally Partitioning35
An optimal cascade learning algorithm (iCascade) which iteratively partitions the strong classifiers into two parts until predefined number of stages are generated and proves in theory why more new weak classifiers in the current stage are required compared to that of the previous stage.
- Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning34
A Modal-Alternating Propagation Network (MAP-Net) is proposed to supplement the absent semantic information of unlabeled samples and design a Relation Guidance (RG) strategy to guide the visual relation vectors via semantics so that the propagated information is more beneficial.
- Scene segmentation based on IPCA for visual surveillance33
Instead of segmenting moving objects in a conventional frame by frame manner, the newly proposed method segments a scene into unchanged background zone (UBZ) and moving object zone (MOZ), so that moving objects normally appear in MOZs rather than UBZs, and therefore, detection and behaviours analysis can be performed inMOZs.
- Deep intra-image contrastive learning for weakly supervised one-step person search32
This paper argues that current intra- image contrast is shallow, which suffers from spatial-level and occlusion-level variance, and presents a novel deep intra-image contrastive learning using a Siamese network.
- Pedestrian attribute recognition based on multiple time steps attention32
A new multiple time steps attention mechanism is proposed to boost the modeling of the relations between images and attributes and it is demonstrated to be effective on two benchmark datasets, i.e., PETA and RAP.
- 32
- A Novel Gabor-LDA Based Face Recognition Method32
A novel face recognition method based on Gabor-wavelet and linear discriminant analysis (LDA) is proposed that performs better than traditional approaches in terms of both efficiency and accuracy.
- ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection31
This work proposes an efficient stereo geometry network (ESGN), which achieves a best trade-off between accuracy and speed, and introduces a deep geometry-aware feature distillation scheme to guide stereo feature learning with a LiDAR-based detector.
- GlanceNets — efficient convolutional neural networks with adaptive hard example mining31
The proposed GlanceNets with several bypasses addresses the problem of how easy samples can be correctly classified with low-level features, just as one can recognize common items at a glance.
- Class-specific synthesized dictionary model for Zero-Shot Learning31
This work proposes a novel synthesized approach for addressing ZSL within a dictionary learning framework that learns both a dictionary matrix and a class-specific encoding matrix for each seen class to synthesize pseudo instances for unseen classes with auxiliary of seen class prototypes.
- Attentive Alignment Network for Multispectral Pedestrian Detection30
An attentive alignment network, consisting of an attentive position alignment (APA) module and an attentive modality alignment (AMA) module, is proposed, which surpasses the current state-of-the-art performance on both datasets.
- CGNet: cross-guidance network for semantic segmentation30
The CGNet attempts to extract segmentation, edge, and salient features, simultaneously, and transfers them into the cross-guidance module (CGM) to generate the pre-knowledge features based on the modeled information, optimizing the context feature extraction process.
- Enhancement for Dust-Sand Storm Images30
Experimental results illustrate that enhanced images have natural colors, more clear details and better visual effect than original degraded images.
- Motion Blur Detection With an Indicator Function for Surveillance Machines30
A theorem is presented, according to which, motion blur can be efficiently detected and segmented, and a one-class classifier is developed, which is more effective than the indicator function and has comparable computational cost of the indicatorfunction.
- Learning optimal spatial filters by discriminant analysis for brain–computer-interface30
Each class in Common Spatial Pattern is divided into many sub-classes (clusters) and formulated the problem in a re-designed graph embedding framework where the vertexes are cluster centers, which helps developing and understanding the proposed method.
- DSMENet: Detail and Structure Mutually Enhancing Network for under-sampled MRI reconstruction29
A Detail and Structure Mutually Enhancing Network (DSMENet), which benefits from the complementary of the Structure Reconstruction UNet (SRUN) and the Detail Feature Refinement Module (DFRM), which can achieve promising performance on qualitative and quantitative results.
- 29
- DFormer: Diffusion-guided Transformer for Universal Image Segmentation28
DFormer takes deep pixel-level features along with the noisy masks as inputs to generate mask features and attention masks, employing diffusion-based decoder to perform mask prediction gradually and directly predicts the masks and corresponding categories from a set of randomly-generated masks.
- Triple discriminator generative adversarial network for zero-shot image classification28
This paper presents a new triple discriminator GAN for ZSC called TDGAN, which incorporates a text-reconstruction network into a dual discriminators GAN (D2GAN), allowing to realize cross-modal mapping from text descriptions to their visual representations.
- 28
- CLIPeR: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation27
A novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP and includes an early-layer fusion and a fine-grained compensation module to compensate local details using the self-attention maps of diffusion model.
- Teachers cooperation: team-knowledge distillation for multiple cross-domain few-shot learning27
This paper distill knowledge from the cooperation of teacher networks to a single student network in a meta-learning framework and incorporates task-oriented knowledge distillation and multiple cooperation among teachers to train an efficient student with better generalization ability on unseen tasks.
- Lightweight group convolutional network for single image super-resolution27
Experimental results on four popular datasets show that the proposed LGCN not only outperforms the state-of-the-art SISR methods, but also achieves faster speed.
- Generalized KPCA by adaptive rules in feature space27
A novel algorithm, named iterative robust KPCA (IRKPCA), which works well in dealing with outliers, and can be carried out in an iterative manner, which makes it suitable to process incremental input data.
- Visual-quality-driven unsupervised image dehazing26
This paper proposes a novel unsupervised dehazing (lightweight) network without any reference images to directly predict clear images from the original hazy images, which consists of an interactive fusion module (IFM) and an iterative optimization module (IOM).
- 26
- 26
- Self-taught cross-domain few-shot learning with weakly supervised object localization and task-decomposition25
This work proposes a task-expansion-decomposition framework for CD-FSL, called Self-Taught (ST) approach, which alleviates the problem of non-target guidance by constructing task-oriented metric spaces and employs Weakly Supervised Object Localization and self-supervised technologies to enrich task- oriented samples by exchanging and rotating the discriminative regions.
- 24
- Semi-supervised LPP algorithms for learning-to-rank-based visual search reranking24
Two feature dimensionality reduction methods for search reranking are proposed and a novel visual search re ranking scheme is presented based on the proposed SSLPP/PCC-SSLPP and learning-to-rank algorithms.
- The state-of-the-art in cardiac MRI reconstruction: Results of the CMRxRecon challenge in MICCAI 202323
A comprehensive overview of the challenge design, a summary of the submitted results, a review of the employed methods, and an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models are presented.
- 23
- Non-linear perceptual multi-scale network for single image super-resolution23
A novel non-linear perceptual multi- scale module (NLPMSM) is developed to learn more discriminative multi-scale feature correlation by using high-order channel attention mechanism, so as to adaptively extract image features at different scales.
- Small and Dense Commodity Object Detection with Multi-Scale Receptive Field Attention23
A one-stage detecting framework, dubbed CommodityNet, is proposed that achieves a superior performance on small dense object detection and a new loss function named ω-focal loss is presented, which significantly improves the detection accuracy of the categories with few objects.
- Fusion-Attention Network for person search with free-form natural language23
This work develops an end-to-end fusion-attention structure, called Description-Strengthened Fusion-Attention Network (DSFA-Net) to tackle the challenging task of searching persons from surveillance videos or large scale image dataset.
- Scale invariant image matching using triplewise constraint and weighted voting23
A novel triple-wisely geometric constraint formed by three potential correspondences with one being the candidate and the other two being voters is proposed, which is robust to scale variation.
- Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification22
A transfer-based dual contrastive network (DCN) is proposed, which incorporates two auxiliary supervised contrastive learning branches during the training process, which focus on interclass discriminability and intraclass invariance.
- HIWDNet: A hybrid image-wavelet domain network for fast magnetic resonance image reconstruction22
A Hybrid Image-Wavelet Domain Reconstruction Network (HIWDNet) for fast MRI reconstruction is proposed, which employs Cross-scale Dense Feature Fusion Module in the image domain to reconstruct the basic structure of MR images, while introducing Region Adaptive Artifact Removal Module (RAARM) to remove aliasing artifacts in large areas.
- Multi-video summarization with query-dependent weighted archetypal analysis22
This work develops a Multi-Video Summarization via Multi-modal Weighted Archetypal Analysis (MVS-MWAA) method to extract a concise summarization that is both representative and informative and presents a Ranking from Bottom to Top (RBT) approach to make it understandable.
- CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation21
A simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation, which adopts frozen CLIP and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification.
- Eliminate Before Align: A Remote Sensing Image-Text Retrieval Framework with Keyword Explicit Reasoning21
This work devise an innovative Eliminate Before Align (EBA) strategy to filter out the weakly correlated sample pairs to mitigate their deviations from optimal embedding space during alignment, and introduces a Keyword Explicit Reasoning (KER) module to facilitate the positive role of subtle key concept differences.
- NTK-Guided Few-Shot Class Incremental Learning21
A novel conceptualization of anti-amnesia in terms of mathematical generalization, leveraging the Neural Tangent Kernel (NTK) perspective is presented, ensuring optimal NTK convergence and minimizing NTK-related generalization loss, which serve as the theoretical foundation for cross-task generalization.
- A new nonlinear feature extraction method for face recognition21
A nonlinear feature extraction method that makes full use of both the nonlinear structure and class-specific information of the training data and demonstrates the effectiveness of the proposed method on the AR face database.
- 20
- 20
- Dual triplet network for image zero-shot learning20
A novel deep metric learning framework called Dual-Triplet Network (DTNet) for image ZSL, which first projects the semantic information into the visual space with a mapping network and then employs two triplet networks for learning the visual-semantic mapping.
- 19
- Hierarchical matching and reasoning for multi-query image retrieval19
A novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR is proposed, which substantially surpasses the current state-of-the-art methods on the benchmark dataset.
- 19
- Context and detail interaction network for stereo rain streak and raindrop removal19
A general coarse-to-fine deraining framework for stereo rain streak and raindrop removal, called CDINet, comprising a stereo rain removal subnet and a stereo detail recovery subnet to restore images progressively and demonstrates that this method sets new state-of-the-art deraining performance in terms of both quantitative and qualitative metrics with faster speed.
- 19
- Zero-shot classification with unseen prototype learning19
This paper proposes a novel Unseen Prototype Learning (UPL) model, which is a simple yet effective framework to learn visual prototypes for unseen categories from the corresponding class-level semantic information, and the learned features are treated as latent classifiers directly.
- Preserving details in semantics-aware context for scene parsing19
This work proposes a semantics conformity module to make low-level features variations agnostic and introduces semantics into the conformed low level features through guidance from semantically aware features, and institute the availability of various possible contextual features at feature fusion to enrich context information.
- Efficient image matching using weighted voting19
Experimental results on real-data demonstrate that the proposed method is more than one hundred times faster than the classical spectral method while does not decrease the matching accuracy.
- Visualizing textual travelogue with location-relevant images19
A general framework and four approaches to extract location names and other location-related information from a travelogue (or a set of travelogues) and retrieve candidate images together with their tags from Flickr are proposed.
- Face Recognition Using Neighborhood Preserving Projections19
A novel unsupervised subspace learning method, Neighborhood Preserving Projections (NPP), is proposed, which aims to modify the classical locally linear embedding by introducing a linear transform matrix.
- 18
- Deep Learning in Object Detection18
This chapter firstly introduces some typical CNN-based architectures in details, and pedestrian detection, as a classical subset of object detection, is further introduced.
- Dual-Path in Dual-Path Network for Single Image Dehazing18
A DPDP-Net (Dual-Path in Dual-Path network) framework by employing a hierarchical dual path network that achieves competitive performance against the state-of-the-art methods on both synthetic and real-world images.
- Rank canonical correlation analysis and its application in visual search reranking18
Experimental results show that Rank-CCA is superior to standard CCA and semi-supervised CCA (Semi- CCA) algorithm, and achieves comparable performance with several state-of-the-art reranking methods while preserving the superiority of low dimensional features.
- A semi-supervised zero-shot image classification method based on soft-target17
A novel Soft-Target Semi-supervised Classification (STSC) model with an autoencoder network is leveraged, where both labeled seen data from the seen categories and unlabeled ancillary data collected from Internet or other datasets are employed as two branches, respectively.
- 17
- Cross-modal guidance based auto-encoder for multi-video summarization17
This work employed sparse auto-encoder as the main model to generate the final summarization of Multi-Video Summarization, where the input was the multiple videos, the output was the keyframes set and the CAE-MVS clearly outperforms the state-of-the-art methods.
- SGAP-Net: Semantic-Guided Attentive Prototypes Network for Few-Shot Human-Object Interaction Recognition17
A Semantic-Guided Attentive Prototypes Network (SGAP-Net) is proposed to learn a semantic-guided metric space where HOI recognition can be performed by computing distances to attentive prototypes of each class.
- Footwear for Gender Recognition17
Preliminary experimental results suggest that footwear appearance is a promising resource for gender recognition and has the potential to be used jointly with other developed biometrics resources to boost performance.
- Hierarchical and complementary experts transformer with momentum invariance for image-text retrieval16
- 16
- iSeg: An Iterative Refinement-Based Framework for Training-Free Segmentation15
The iSeg introduces an entropy-reduced self-attention module that utilizes a gradient descent scheme to reduce the entropy of self-attention map, thereby suppressing the weak responses corresponding to irrelevant global information and stably improves cross-attention map with iterative refinement.
- 15
- 15
- Heterogeneous memory enhanced graph reasoning network for cross-modal retrieval15
This paper proposes a heterogeneous memory enhanced graph reasoning network, named HMGR, to connect the semantic correlations between vision and language, and designs a novel dual-path network architecture to generate relationship enhanced global representations by employing modality-specific graph reasoning on extracted local features for each instance.
- 15
- Stacked squeeze-and-excitation recurrent residual network for visual-semantic matching15
A Stacked Squeeze-and-Excitation Recurrent Residual Network (SER2-Net) for visual-textual matching is introduced and a novel objective namely Cross-modal Semantic Discrepancy (CMSD) loss, which is characterized by exploiting the interdependency among different semantic levels to narrow the cross- modal distribution discrepancy is proposed.
- Semantic softmax loss for zero-shot learning15
This letter proposes a nonlinear approach to impose ZSL as a multi- class classification problem via a Semantic Softmax Loss by embedding the class semantic descriptors into the softmax layer of multi-class classification network.
- Zero-shot learning with regularized cross-modality ranking15
This paper employs the hinge ranking loss to exploit the structures among different modalities and devise efficient regularizers to constrain the variation of the samples in the identical modality.
- 15
- Flexible sliding windows with adaptive pixel strides15
This paper proposes to scan the image using adaptive instead of fixed (unchanged) strides, which results in the reduction of total computation cost without loss of detection accuracy, and applies sparsely sampling on background and densely sampling on potential object regions.
- Robust probabilistic tensor analysis for time-variant collaborative filtering15
This paper describes the data as a three-order tensor and forms the collaborative filtering as a problem of probabilistic tensor decomposition with a time-periodical constraint and achieves robustness and superiority on movie recommendation.
- 14
- Lane-change path planning and control method for self-driving articulated trucks14
A novel safety lane-change path planning and tracking control method for articulated vehicles and a feedback linearization controller, combined with a multi-objective decision-making mode, to improve the comprehensive performance of intelligent vehicles are proposed.
- Special focus on deep learning for computer vision14
The attention mechanism for cross-domain product image retrieval is discussed and 3D blendshape information is proposed to effectively leverage 3D blendshape information for facial expression recognition.
- Zero-shot learning with Multi-Battery Factor Analysis14
This paper develops an algorithm named Multi-Battery Factor Analysis (MBFA) to build a unified semantic space, and then employs multiple types of side information in it to achieve the ZSL.
- 13
- 13
- 13
- 13
- Incremental threshold learning for classifier selection13
An incremental algorithm for incrementally learning the threshold-based classifiers that can not only incrementally model the features but also estimate the threshold and training error in a close form is proposed.
- TRAVELOGUE ENRICHING AND SCENIC SPOT OVERVIEW BASED ON TEXTUAL AND VISUAL TOPIC MODELS13
A framework of travelogue enriching, exploiting both textual and visual information generated by different users, to select the most relevant images from automatically collected candidate image set to enrich the given travelogue, and form a comprehensive overview of the scenic spot.
- 12
- 12
- 12
- 12
- Incrementally Detecting Moving Objects in Video with Sparsity and Connectivity12
The proposed incremental method for detecting moving objects in video not only incrementally models the subspace for background reconstruction but also takes into account the sparsity and connectivity of the foreground.
- 12
- 12
- Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning11
This work proposes a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods, and demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks, showcasing its potential in adapting VLMs to evolving data distributions.
- 11
- 11
- 11
- Efficient object detection by prediction in 3D space11
This paper proposes to explore both the scaling capacity and translation capacity of object detector to accelerate detection speed, without loss of detection accuracy, and presents an interlaced scanning method called diamond grid scanning which can reduce redundant evaluation.
- Phantom-metasurface cooperative system trained by a deep learning network driven by a bound state for a magnetic resonance-enhanced system10
The experimental results show that the combination of deep neural network and electromagnetic metasurface significantly improves the design efficiency of metasurface and has great application potential in the MRI system.
- 10
- 10
- Modality-experts coordinated adaptation for large multimodal models10
A modality-experts coordinated adaptation (ModeX) method for the multimodal domain is proposed, offering an effective, plug-and-play, and lightweight adaptation architecture for diverse LMMs, which demonstrates superior stability and offers higher training efficiency, both in terms of training parameters and training duration.
- Complementary Feature Pyramid Network for Object Detection10
A Spatial Complementary Module (SCM) and a Channel Complementaries Module (CCM) are designed and embedded in CFPN to enhance useful information and suppress irrelevant information during feature fusions along spatial and channel dimensions, respectively.
- 10
- Learning intensity and detail mapping parameters for dehazing10
Experimental results demonstrate that the proposed hazy image enhancement framework, called IMDM, is superior to both the enhancement and model-based methods in terms of improving the visibility and preserving color fidelity.
- Dual-domain faster Fourier convolution based network for MR image reconstruction9
This study proposes Faster Inverse Fourier Convolution (FasterIFC), a frequency domain convolutional operator that significantly expands the receptive field of k-space domain reconstruction networks, and introduces a novel softer Data Consistency layer, which achieves an enhanced balance between data consistency and smoothness.
- 9
- 9
- Edge pattern based demosaicking algorithm of color filter array9
Simulations showed that the proposed method outperformed the other four demosaicking methods for average color peak signal to noise ratios and maintained a relatively low complexity owing to constant color-difference interpolation step and a reasonable terminating condition of iteration.
- Energy-saving object detection by efficiently rejecting a set of neighboring sub-images9
This paper focuses on developing an energy-saving object detection algorithm which can reject a bundle of neighboring sub-images with only one inner-product operation and an acceptable number of addition ones, which is more energy- saving and efficient.
- On the Approximation Risk of Few-Shot Class-Incremental Learning8
This work thoroughly explore the approximation risk of FSCIL, encompassing both transfer and consistency risks, and derives practical guidelines for designing and training FSCIL models.
- Non-invasive, intelligent, and continuous monitoring of human blood glucose with UWB dual-antenna and cascade CNN8
The feasibility of the proposed non-invasive and intelligent dual-sensing system has been verified using glucose solution, animal serum, and human trials, and the detection signal exhibited a high correlation with blood glucose levels.
- 8
- Breast tumor detection by 1D-convolutional neural network based on ultra-wide-band microwave technology8
A 1D-convolution neural network is proposed to detect the presence of breast tumors directly from raw time-domain microwave signals, avoiding complex microwave image reconstruction and time-consuming feature engineering.
- Frequency Domain Directional Filtering Based Rain Streaks Removal from a Single Color Image8
Experimental results demonstrate that the proposed algorithm can deal with rain steaks of any directions, and maintains more details than existing algorithms.
- Truncation Error Analysis on Reconstruction of Signal From Unsymmetrical Local Average Sampling8
This work proposes using the Taylor expansion of sinc function to reconstruct signal sampled from unsymmetrically local averages and give the upper bound of the reconstruction error (i.e., truncation error).
- 7
- Spatial attention-guided deformable fusion network for salient object detection7
A spatial-attention-guided deformable fusion network for salient object detection, which consists of a contour enhancement module (CEM), an SADFM and a gate module (GM), aiming to reduce the loss of high-level features in the transfer process.
- 7
- 7
- Semantic segmentation with hybrid pyramid pooling and stacked pyramid structure7
A Hybrid Pyramid Pooling (HPP) structure is designed to explicitly exploit the channel-wise features and another Stacked Pyramid Structure (SPS) is designed, which contains stacked pyramid pooling structures, to investigate the beneficial effect of channel- wise feature on improving details representation ability.
- Relevance and irrelevance graph based marginal Fisher analysis for image search reranking7
A novel "Ranking Dimensionality Reduction" scheme specifically designed for learning-to-rank based image ranking, which aims at not only discovering the intrinsic structure of data but also keeping the ordinal information in ranking and retrieval is presented.
- 7
- Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective6
This work recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization.
- Raformer: Redundancy-Aware Transformer for Video Wire Inpainting6
The research proposes the Redundancy-Aware Transformer (Raformer) method, which employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting, and outperforms other state-of-the-art methods.
- Accurate blood glucose level monitoring using microwave imaging6
Results show that microwave imaging offers a promising new approach for noninvasive BGL monitoring and a high correlation coefficient (R) of 0.9254 was achieved between the results of microwave imaging and invasive BGL.
- 6
- 6
- Response to Comments on “Detection and Localization of Breast Cancer Using UWB Microwave Technology and CNN-LSTM Framework”6
A composite end-to-end framework that consists of convolutional neural network (CNN) and long-short-term memory (LSTM) is proposed, which can realize the tasks of detecting and quadrant locating the breast tumor simultaneously without any complicated microwave imaging processing.
- Filling the Gaps in Atrous Convolution: Semantic Segmentation With a Better Context6
It is argued that a rich set of cues exist at multiple stages of the network, encapsulating low, mid and high-level scene details, and an optimal scene parsing model must aggregate multi-scale context at all three levels of the feature hierarchy.
- 6
- 6
- 6
- X-Ray Luggage Image Enhancement Based on CLAHE6
The experimental results show that the proposedCLAHE-based X-ray luggage image enhancement algorithm is fast and effective in enhancing the contrast of X-Ray luggage images and highlighting luggage details.
- 6
- Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts5
A Few-Shot Prototypical Concept Classification (FSPCC) framework that systematically mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment and introduces a geometry-aware concept discrimination loss that enforces orthogonality among concepts, paving the way for more transparent visual recognition systems.
- 5
- 5
- Multispectral remote sensing object detection via selective cross-modal interaction and aggregation5
This work proposes a novel framework, termed Selective cross-modal Interaction and Aggregation (SIA), which comprises two key components: the Selective Cross-modal Interaction (SCI) module and the Selective Feature Aggregation (SFA) module, which addresses the inefficiency of traditional cross-modal attention mechanisms by selectively prioritizing the most informative long-range dependencies.
- A unified circular-polarization metamaterial-inspired resonator for increasing SNR in breast MRI5
The proposed unified circular-polarization metamaterial-inspired resonator (CPMR) can simultaneously enhance the two orthogonal linearly polarized components of a circularly polarized magnetic field, which will be accomplished by a single integrated resonator.
- 5
- 5
- Dual Distillation Discriminator Networks for Domain Adaptive Few-Shot Learning5
This work proposes Dual Distillation Discriminator Networks (D3Net) from the perspective of the lack of labeled target domain style samples in DA-FSL and realizes the distribution alignment between the source domain and the target domain and constraints the FSL task distribution by prototype distributions on the mixed domain.
- 5
- COREN: Multi-Modal Co-Occurrence Transformer Reasoning Network for Image-Text Retrieval5
This paper proposes a unified multi-modal Co-Occurrence transformer Reasoning Network, dubbed as COREN, to comprehensively discover the semantic correlations of the two modalities and proposes a novel Adaptive Similarity Aggregation (ASA) module to achieve a more accurate cross- modal similarity measurement.
- Detail-preserving single nighttime image dehazing5
An effective single nighttime image haze removal approach based on multiscale fusion that recovers a high-quality, haze-free, and noise-free image with vivid details.
- 5
- 5
- 4
- 4
- 4
- Implicit and Explicit Language Guidance for Diffusion-Based Visual Perception4
This paper proposes an implicit and explicit language guidance framework for diffusion-based visual perception, named IEDP, which comprises an implicit language guidance branch and an explicit language guidance branch that can jointly guide feature learning.
- DIRECTION: Deep cascaded reconstruction residual-based feature modulation network for fast MRI reconstruction4
This paper introduces a novel Reconstruction Residual-Based Feature Modulation Mechanism (RRFMM) which utilizes the reconstruction residual of the previous subnetwork to guide the next subnetwork at the feature level and significantly outperforms other compared state-of-the-art methods quantitatively and qualitatively.
- 4
- Multi-feature self-attention super-resolution network4
A multi-feature self-attention super-resolution network (MFSN) to embed multi-scale encoding information into the attention mechanism and demonstrates the superiority of the MFSN network in terms of both quantitative metrics and visual quality.
- 4
- Zero-Shot Learning with Deep Canonical Correlation Analysis4
A novel deep embedding model for ZSL is proposed, which formulates the embedding space with Deep Canonical Correlation Analysis (DCCA) and transforms the side information and the visual representation via two independent deep neural networks, and then they are highly linearly correlated in the final output layer.
- ECG Waveform Extraction from Paper Records4
An improved ECG waveform extraction algorithm from paper records is proposed and is used to get accurate ECG trajectory information with a serious of adaptive image processing techniques, including skew correction, waveform segmentation, and tracking.
- 4
- 4
- 3
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport3
A novel self-supervised Heterogeneous graph neural network with Optimal Transport (HGOT) method which is designed to facilitate self-supervised learning for heterogeneous graphs without graph augmentation strategies and employs the optimal transport mechanism to relieve the laborious sampling process of positive and negative samples.
- 3
- SSNet: a joint learning network for semantic segmentation and disparity estimation3
Stereo Semantic Network (SSNet) is the first Transformer based end-to-end joint learning model for semantic segmentation and disparity estimation which is designed to separate features for segmentation prediction and disparity regression according to the characteristics of the two tasks.
- 3
- 3
- 3
- 3
- 3
- Learning Sampling Functions for Efficient Object Detection3
This paper designs the proposal distribution so as to efficiently reject the huge number of non-object windows and proposes the concepts of rejection, acceptance, and ambiguity windows and regions of MPW.
- Special issue on dimensionality reduction for visual big data3
This special issue aims at bringing together the state-of-the-art research results on dimensionality reduction for visual big data, with a focus on the marriage between “dimensionality reduction” and “visual big data”.
- Active Histogram of Oriented Gradient Based Learning for Free Palm Tracking3
A novel feature that is called active Histogram of Oriented Gradient (aHOG) for palm detection in unconstrained grey-level images is developed and local PCA is applied to original HOG feature sets to overcome the limitation of HOG.
- 3
- STDec: Spatio-Temporal Stability Guided Decoding for dLLMs2
This work proposes a simple spatio-temporal stability guided decoding approach, named STDec, which includes spatial-aware decoding and temporal-aware decoding and dynamically generates the token-adaptive threshold by aggregating the decoded states of nearby tokens.
- Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification2
A novel Optimal Transport Adapter Tuning (OTAT) framework aimed at constructing an ideal Platonic representational space through optimal transport (OT) theory, which seeks to harmonize rich visual information with less dense textual cues, enabling effective cross-modal information transfer and complementarity.
- 2
- 2
- 2
- 2
- 2
- Supervised biadjacency networks for stereo matching2
A Supervised Biadjacency-based (SuperB) module is proposed to improve stereo matching quality by employing supervised biadjacency matrices to embed stereo information into both unary features and adaptively enhance matched features and suppress unmatched features.
- EVOLVE: Learning volume-adaptive phases for fast 3D magnetic resonance scan and image reconstruction2
- 2
- 2
- Active Phase-Encode Selection for Slice-Specific Fast MR Scanning Using a Transformer-Based Deep Reinforcement Learning Framework2
A light-weight transformer based deep reinforcement learning framework for generating high-quality slice-specific trajectory consisting of a small number of phases, which has remarkable superiority in phase-encode selection efficiency and image reconstruction accuracy.
- 2
- 2
- Special issue on image feature detection and description2
The aim of this special issue is to bring together the state-of-the research results on image feature detection and description and its applications and to accept about 30-40 papers.
- Image Search Reranking with Semi-supervised LPP and Ranking SVM2
This paper studies the task of image search reranking, and proposes a novel system scheme based on Locality Preserving Projections (LPP) and RankingSVM and improves LPP by incorporating the relevance degree information into it, and names it as semi-supervised LPP (Semi-LPP).
- 2
- 2
- 2
- 1
- Underlying Semantic Diffusion for Effective and Efficient In-Context Learning1
This work proposes Underlying Semantic Diffusion (US-Diffusion), an enhanced diffusion model that improves underlying semantics learning, computational efficiency, and in-context learning capabilities on multi-task scenarios, and introduces Separate & Gather Adapter (SGA), which decouples input conditions for different tasks while sharing the architecture, enabling better in-context learning and generalization across diverse visual domains.
- 1
- 1
- 1
- 1
- Domino volumetric metamaterial resonator for very‐low‐field MRI1
It is urgent to explore a low‐cost, simple and convenient approach to boost the signal‐to‐noise ratio (SNR) of VLF‐MRI system to make medical diagnosis more accurate.
- 1
- EEUR-Net: End-to-End Optimization of Under-Sampling and Reconstruction Network for 3D Magnetic Resonance Imaging1
A deep neural network called EEUR-Net is proposed, realized by optimizing specific under-sampling patterns for the fully sampled 3D k-space data and considerably improves the reconstruction quality of under-sampled MRI images.
- LEAPS: End-to-End One-Step Person Search With Learnable Proposals1
The proposed LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing, and introduces a diverse re-ID sample matching strategy, instead of bipartite matching in detection head.
- DMFF-Net: Densely Macroscopic Feature Fusion Network for Fast Magnetic Resonance Image Reconstruction1
This work rethought the feature utilization method of the encoder and decoder network from a macroscopic point of view and proposes a densely Macroscopic feature fusion network for fast magnetic resonance image reconstruction which is lighter than many previous methods, but achieves better performance.
- Multi-scale Feature Aggregation for Crowd Counting1
Extensive experiments on four challenging datasets demonstrate the proposed easy-to-implement MSFANet can achieve promising results when compared with the previous state-of-the-art approaches.
- 1
- 1
- 1
- Range Images1
An overview of range imaging techniques is given with an aim to let the reader better understand how the difficult issue, such as the registration of overlapping range images, can be approached and solved.
- Zero-Shot Leaning with Manifold Embedding1
A Manifold Embedding based ZSL (ME-ZSL) approach is proposed by formulating the manifold structure for the visual to textual embedding with the intra-class compactness, the inter-class separability, and the locality preservation.
- Weighted Deformable Part Model for Robust Human Detection1
This paper proposes a novel human detection approach capable of handling partial occlusion by combining the deformable part model and mean-shift algorithm, and dramatically decreases the effect of HOG feature of any occluded part during the decision-making process.
- Face recognition based on DCT and linear regression1
A method based on discrete cosine transform and linear regression classification for face recognition that is more robust in the case of real-time recognition is satisfied when confront these problems.
- 1
- 1
- SUBSPACE LEARNING BASED ON LAPLACIAN EIGENMAPS AND LDA FOR FACE RECOGNITION1
Subspace-based face recognition method aims to find a low-dimensional subspace of face appearance embedded in a high-dimensional image space by combining the ideas of linear Laplacian eigenmaps and linear discriminant analysis.
- –
- –
- Probabilistic von Mises–Fisher representation learning for few-shot remote sensing scene classification–
A probabilistic reformulation of FS-RSISC that moves beyond rigid point-based prototypes by modeling each class as a probability distribution over the hyperspherical feature space and adopts the von Mises–Fisher (vMF) distribution to capture both semantic uncertainty and feature diversity.
- –
- –
- –
- Symmetrical quadrature coil for enhancing circularly polarized magnetic fields in vertical-field MRI–
- –
- –
- SD2-SNN: Self-distillation and structural decomposition framework for SNNs in continual learning–
This study proposes SD2-SNN, a framework employing Self-Distillation and Structural Decomposition to enhance knowledge retention without external supervision, and achieves strong and stable performance across both image-based and event-based settings.
- –
- –
- –
- –
- –
- –
- Concept agent network for zero-base generalized few-shot learning–
The Concept Agent Network is proposed, a novel framework that interprets visual features as affinity features, thereby effectively diminishing feature overlap by aggregating feature embeddings of the novel classes according to their similarity with the base classes.
- –
- –
- –
- –
- –
- Decoupling isolator inspired by conformal metasurface for significant MRI enhancement–
A conformal metasurface decoupling isolator for magnetic field enhancement in 1.5T surface coil MRI systems is proposed using conformal optical theory and polarization conversion mechanisms to eliminate the coupling between metamaterial and radio frequency surface coil.
- –
- –
- Retinex decomposition and fusion dehazing network–
A novel Retinex decomposition-fusion dehazing network consisting of a dual-branch decomposition module and a fusion optimization module is proposed that has better generalization and visual effects than existing fully data-driven methods and can be applied successfully to real-world scenarios.
- –
- –
- –
- –
- Cross-Modal Retrieval with Discriminative Dual-Path CNN–
The approach, named Discriminative Dual-Path CNN (DDPC), achieves the state-of-the-art results on the MS-COCO dataset, improving IBTR by 4.9% and TBIR by 5.8% based on Recall@1 on the 5K test set.
- Marginal Fisher Regression Classification for Face Recognition–
The MFRC aims at minimizing the within-class compactness over the between-class separability to find an optimal embedding matrix for the LRC so that the L RC on that subspace achieves a high discrimination for classification.
- Interactive Head 3D Reconstruction Based Combine of Key Points and Voxel–
A method based the combine of key points and voxel is presented to reconstruct head models and can reconstruct the hair better than the traditional 3D reconstruction method based key points.
- Balance between Diversity and Relevance for Image Search Results–
A DIR (DDrank-based Image search Rerank) algorithm, which can enrich the topic coverage while keeping the relevance with minimal impact, is proposed, which is based on vertex reinforced random walk and can automatically balance the relevance and diversity of the top ranked vertices in a principle way.
- Multi-video abstraction:approaches,applications and challenges–
A comprehensive overview of the state-of-the-art approaches and study progress is given,and some potential applications are discussed, and some challenges and trends are proposed.
- –
- –
- An even component based face recognition method–
Experimental results show that the proposed face recognition algorithm outperforms in terms of accuracy the conventional eigen face method which applies PCA on original images and the eigenface method which uses both the original image and their mirror images as training set.
- Feature extraction using filtered projections and fractal dimensions–
Results have demonstrated that the proposed approach is a promising method for feature extraction, and the fractal dimensions of all the filtered projections are computed to form a feature vector from which pattern recognition can be done easily.
- Preprocessing X-ray Digital Radiographs of Corroded Pipeline–
The exact quantification of corrosive will be influenced by the intrinsic defect in the screen and the position of the center of halation.
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 2026-10-14. 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.