IEEE Transactions on Pattern Analysis and Machine Intelligence

(The median citation count of IEEE Transactions on Pattern Analysis and Machine Intelligence is 3. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 500 papers]. The publications cover those that have been published in the past four years, i.e., from 2019-08-01 to 2023-08-01.)
Squeeze-and-Excitation Networks2348
Focal Loss for Dense Object Detection2259
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields1515
Mask R-CNN1334
Res2Net: A New Multi-Scale Backbone Architecture940
Deep High-Resolution Representation Learning for Visual Recognition902
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning851
Image Segmentation Using Deep Learning: A Survey731
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey522
Deep Learning for 3D Point Clouds: A Survey521
Deep Learning for Image Super-Resolution: A Survey514
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly486
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding454
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks429
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild414
Cascade R-CNN: High Quality Object Detection and Instance Segmentation409
Event-Based Vision: A Survey398
Deep Learning for Person Re-Identification: A Survey and Outlook383
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm382
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks361
U2Fusion: A Unified Unsupervised Image Fusion Network329
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification316
Temporal Segment Networks for Action Recognition in Videos315
Generalized Latent Multi-View Subspace Clustering314
Residual Dense Network for Image Restoration303
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing290
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition267
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection263
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs260
Transferable Representation Learning with Deep Adaptation Networks251
A Survey on Vision Transformer249
Denoising Prior Driven Deep Neural Network for Image Restoration246
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition245
Richer Convolutional Features for Edge Detection231
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI220
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network215
Meta-Learning in Neural Networks: A Survey210
Recent Advances in Open Set Recognition: A Survey206
Normalizing Flows: An Introduction and Review of Current Methods205
A continual learning survey: Defying forgetting in classification tasks201
Deep Multi-View Enhancement Hashing for Image Retrieval198
Deep Collaborative Embedding for Social Image Understanding189
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning188
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks187
Advances in Variational Inference185
A Review of Domain Adaptation without Target Labels184
Detecting Coherent Groups in Crowd Scenes by Multiview Clustering181
The ApolloScape Open Dataset for Autonomous Driving and Its Application179
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection177
Convolutional Networks with Dense Connectivity169
Imbalance Problems in Object Detection: A Review165
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era160
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer159
Moments in Time Dataset: One Million Videos for Event Understanding158
Salient Object Detection in the Deep Learning Era: An In-Depth Survey155
Rank Minimization for Snapshot Compressive Imaging155
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes151
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization151
Late Fusion Incomplete Multi-View Clustering140
A Style-Based Generator Architecture for Generative Adversarial Networks138
Multi-Task Learning for Dense Prediction Tasks: A Survey137
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals136
Deep Imbalanced Learning for Face Recognition and Attribute Prediction136
YOLACT++ Better Real-Time Instance Segmentation136
Revisiting Video Saliency Prediction in the Deep Learning Era134
Plug-and-Play Image Restoration With Deep Denoiser Prior133
Image Quality Assessment: Unifying Structure and Texture Similarity126
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement121
A Comprehensive Analysis of Deep Regression118
Robust Visual Tracking via Hierarchical Convolutional Features114
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos114
Deep Audio-Visual Speech Recognition113
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding112
ThiNet: Pruning CNN Filters for a Thinner Net112
Robust Low-Rank Tensor Recovery with Rectification and Alignment111
Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach108
Interpreting Deep Visual Representations via Network Dissection108
Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images108
FCOS: A Simple and Strong Anchor-free Object Detector107
Learning Depth with Convolutional Spatial Propagation Network105
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks105
High Speed and High Dynamic Range Video with an Event Camera104
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency103
On the Effectiveness of Least Squares Generative Adversarial Networks102
Confidence Propagation through CNNs for Guided Sparse Depth Regression102
CCNet: Criss-Cross Attention for Semantic Segmentation101
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering101
Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank100
Unsupervised Tracklet Person Re-Identification99
Single Image Dehazing Using Haze-Lines99
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes98
Maximum Density Divergence for Domain Adaptation97
Inferring Salient Objects from Human Fixations95
Label Consistent Matrix Factorization Hashing for Large-Scale Cross-Modal Similarity Search90
Skeleton-Based Online Action Prediction Using Scale Selection Network89
Coherence Constrained Graph LSTM for Group Activity Recognition87
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video86
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification86
Single Image Deraining: From Model-Based to Data-Driven and Beyond85
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs85
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset85
Hiding Images within Images84
Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding84
Prior Guided Feature Enrichment Network for Few-Shot Segmentation81
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation78
Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks77
Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking77
Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer76
Generalizable Data-Free Objective for Crafting Universal Adversarial Perturbations76
A Comprehensive Database for Benchmarking Imaging Systems75
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images75
Representation Learning by Rotating Your Faces75
Direction-Aware Spatial Context Features for Shadow Detection and Removal75
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation73
Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition73
Contextual Transformer Networks for Visual Recognition72
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges71
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition71
Neural Image Compression for Gigapixel Histopathology Image Analysis71
Densely Residual Laplacian Super-Resolution70
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation70
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction70
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes70
Structured Knowledge Distillation for Dense Prediction69
3D-Aided Dual-Agent GANs for Unconstrained Face Recognition68
Dynamic Neural Networks: A Survey68
Deep Neural Network Compression by In-Parallel Pruning-Quantization68
Joint Image Filtering with Deep Convolutional Networks68
Concealed Object Detection67
Detection and Tracking Meet Drones Challenge67
Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception67
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle67
Feature Boosting Network For 3D Pose Estimation66
Saliency Prediction in the Deep Learning Era: Successes and Limitations66
Deep Residual Correction Network for Partial Domain Adaptation65
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method64
Learning to Adapt Invariance in Memory for Person Re-identification64
Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly63
Graph Neural Networks with Convolutional ARMA Filters63
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction62
Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation62
Early Action Prediction by Soft Regression61
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method60
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval59
Weakly Supervised Object Localization and Detection: A Survey59
Physics-Based Generative Adversarial Models for Image Restoration and Beyond59
Neural Machine Translation with Deep Attention59
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing58
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds58
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks58
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild58
A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization58
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation57
Learning Generalisable Omni-Scale Representations for Person Re-Identification56
Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms56
Infinite Feature Selection: A Graph-based Feature Filtering Approach56
Low-Light Image and Video Enhancement Using Deep Learning: A Survey56
Mutually Guided Image Filtering56
Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods55
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion55
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training55
A Review on Deep Learning Techniques for Video Prediction55
Dense 3D Object Reconstruction from a Single Depth View55
PhlatCam: Designed Phase-Mask Based Thin Lensless Camera54
Augmentation Invariant and Instance Spreading Feature for Softmax Embedding54
Siamese Network for RGB-D Salient Object Detection and Beyond54
End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning54
Multiset Feature Learning for Highly Imbalanced Data Classification53
Object Detection in Videos by High Quality Object Linking53
A Fast Adaptive k-means with No Bounds53
Incremental Learning Through Deep Adaptation53
Nonlinear Regression via Deep Negative Correlation Learning52
A Bayesian Formulation of Coherent Point Drift52
Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers52
Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging52
Tensor Low-Rank Representation for Data Recovery and Clustering51
A Novel Approach to Large-Scale Dynamically Weighted Directed Network Representation51
SensitiveNets: Learning Agnostic Representations with Application to Face Images51
A Survey on Curriculum Learning50
SPFTN: A Joint Learning Framework for Localizing and Segmenting Objects in Weakly Labeled Videos50
Multi-Source Causal Feature Selection50
Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification49
P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization49
DeepFake Detection Based on Discrepancies Between Faces and Their Context49
Non-local Meets Global: An Integrated Paradigm for Hyperspectral Image Restoration49
Domain Generalization: A Survey49
Convolutional Neural Network Architecture for Geometric Matching49
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models49
An End-to-End Learning Framework for Video Compression48
Hashing with Mutual Information48
Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation48
Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks48
Context-Aware Visual Policy Network for Fine-Grained Image Captioning47
A Survey of Single-Scene Video Anomaly Detection47
Dual Encoding for Video Retrieval by Text47
Person Re-Identification by Contour Sketch Under Moderate Clothing Change47
Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time47
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging47
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing47
Learning Part-based Convolutional Features for Person Re-Identification47
Object Detection from Scratch with Deep Supervision47
Negation of the Quantum Mass Function for Multisource Quantum Information Fusion With its Application to Pattern Classification47
Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations47
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL46
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition46
Image Super-Resolution Via Iterative Refinement46
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?46
Learning a Fixed-Length Fingerprint Representation46
Simultaneous Fidelity and Regularization Learning for Image Restoration45
Cascaded Parsing of Human-Object Interaction Recognition45
Paying Attention to Video Object Pattern Understanding45
Hyperspectral Recovery from RGB Images using Gaussian Processes45
GAN Inversion: A Survey44
Bayesian Temporal Factorization for Multidimensional Time Series Prediction44
Deep Convolutional Neural Network for Multi-Modal Image Restoration and Fusion44
Enhanced Tensor RPCA and its Application44
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction44
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition43
Neural Architecture Transfer43
Face-from-Depth for Head Pose Estimation on Depth Images43
Min-Entropy Latent Model for Weakly Supervised Object Detection43
CTNet: Context-Based Tandem Network for Semantic Segmentation43
On the Convergence of Learning-Based Iterative Methods for Nonconvex Inverse Problems42
On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks42
Fast Multi-Instance Multi-Label Learning42
Real-World Image Denoising with Deep Boosting42
Segmenting Objects From Relational Visual Data41
Self-Correction for Human Parsing41
RGB-D SLAM in Dynamic Environments Using Point Correlations41
Semi-Supervised Multi-View Deep Discriminant Representation Learning41
A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking41
Generalized Feedback Loop for Joint Hand-Object Pose Estimation41
Deep Partial Multi-View Learning41
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning41
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Network41
Salient Subsequence Learning for Time Series Clustering40
Subspace Clustering via Good Neighbors40
Neural Sensors: Learning Pixel Exposures for HDR Imaging and Video Compressive Sensing With Programmable Sensors40
Fine-Grained Image Analysis With Deep Learning: A Survey40
Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy40
Parallax Attention for Unsupervised Stereo Correspondence Learning40
Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction40
Focal Visual-Text Attention for Memex Question Answering39
Uncertainty Inspired RGB-D Saliency Detection39
Learning to Match Anchors for Visual Object Detection39
Towards Robust Discriminative Projections Learning via Non-Greedy -Norm MinMax38
Deep Hough Transform for Semantic Line Detection38
Real-Time RGB-D Camera Pose Estimation in Novel Scenes Using a Relocalisation Cascade38
Long-Term Visual Localization Revisited38
Open Set Domain Adaptation for Image and Action Recognition37
Momentum-Net: Fast and Convergent Iterative Neural Network for Inverse Problems37
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition37
Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning37
Absent Multiple Kernel Learning Algorithms37
Symbiotic Attention for Egocentric Action Recognition With Object-Centric Alignment37
Intel® RealSense™ SR300 Coded Light Depth Camera37
What and How: Generalized Lifelong Spectral Clustering via Dual Memory37
Deep Clustering: On the Link Between Discriminative Models and K-Means37
Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships36
Pose-Guided Representation Learning for Person Re-Identification36
ArcFace: Additive Angular Margin Loss for Deep Face Recognition36
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation36
SibNet: Sibling Convolutional Encoder for Video Captioning36
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation35
Large Graph Clustering With Simultaneous Spectral Embedding and Discretization35
High-Fidelity Monocular Face Reconstruction Based on an Unsupervised Model-Based Face Autoencoder35
Distributed Variational Representation Learning35
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation35
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition35
Analysis of the Hands in Egocentric Vision: A Survey35
Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks34
Line Graph Neural Networks for Link Prediction34
Visual Tracking via Dynamic Graph Learning34
The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines34
Unsupervised Domain Adaptation for Depth Prediction from Images34
Packing Convolutional Neural Networks in the Frequency Domain34
CoRRN: Cooperative Reflection Removal Network34
Semi-Supervised Domain Adaptation by Covariance Matching34
RefineFace: Refinement Neural Network for High Performance Face Detection33
ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning33
Efficient and Effective Regularized Incomplete Multi-view Clustering33
Convolutional Prototype Network for Open Set Recognition33
Learning Compact Features for Human Activity Recognition Via Probabilistic First-Take-All33
UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction Using Commercial RGBD Cameras33
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D33
Label Independent Memory for Semi-Supervised Few-shot Video Classification33
Visibility Graphs for Image Processing33
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC33
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation33
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size32
Recognizing Material Properties from Images32
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition32
Towards a Complete 3D Morphable Model of the Human Head32
Bias in Cross-Entropy-Based Training of Deep Survival Networks32
Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences32
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers32
Age from Faces in the Deep Learning Revolution32
Deep Self-Evolution Clustering32
Neural Granger Causality32
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation32
Surface-Aware Blind Image Deblurring32
Learning End-to-End Lossy Image Compression: A Benchmark32
Deep Variational and Structural Hashing32
Chart Mining: A Survey of Methods for Automated Chart Analysis31
Robust Bi-stochastic Graph Regularized Matrix Factorization for Data Clustering31
End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform31
SurfelMeshing: Online Surfel-Based Mesh Reconstruction31
Deep Object Tracking with Shrinkage Loss31
Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery31
Adversarial Reciprocal Points Learning for Open Set Recognition31
Explainability in Graph Neural Networks: A Taxonomic Survey31
Pattern of Local Gravitational Force (PLGF): A Novel Local Image Descriptor31
Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation31
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology31
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition31
Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications30
Robust Multi-View Clustering With Incomplete Information30
On Learning Disentangled Representations for Gait Recognition30
Deep Back-ProjectiNetworks for Single Image Super-Resolution30
Scattering Networks for Hybrid Representation Learning30
A Differential Approach for Gaze Estimation30
Learning to Compose and Reason with Language Tree Structures for Visual Grounding30
Kernel-Based Density Map Generation for Dense Object Counting30
Joint Camera Spectral Response Selection and Hyperspectral Image Recovery30
A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras30
The Emerging Trends of Multi-Label Learning29
Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features29
Zero and Few Shot Learning With Semantic Feature Synthesis and Competitive Learning29
Learning Deep Binary Descriptor with Multi-Quantization29
Learning with Privileged Information via Adversarial Discriminative Modality Distillation29
BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection29
DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features29
A Simple and Fast Algorithm for L1-Norm Kernel PCA29
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer29
Training Faster by Separating Modes of Variation in Batch-Normalized Models29
GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set29
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration28
Guided Attention Inference Network28
Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation28
Deep Model Intellectual Property Protection via Deep Watermarking28
A Comprehensive Survey of Scene Graphs: Generation and Application28
Salient Object Detection via Integrity Learning28
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion28
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network28
Re-thinking Co-Salient Object Detection28
DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions28
Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification28
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling28
Height-from-Polarisation with Unknown Lighting or Albedo28
A Self-Supervised Gait Encoding Approach With Locality-Awareness for 3D Skeleton Based Person Re-Identification28
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution27
Optimizing Latent Distributions for Non-Adversarial Generative Networks27
Generative Zero-Shot Learning via Low-Rank Embedded Semantic Dictionary27
Disentangling Light Fields for Super-Resolution and Disparity Estimation27
DAC-SDC Low Power Object Detection Challenge for UAV Applications27
Cooperative Training of Descriptor and Generator Networks27
Semi-Supervised Adversarial Monocular Depth Estimation27
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition27
VOLO: Vision Outlooker for Visual Recognition27
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video27
Human Action Recognition From Various Data Modalities: A Review27
Adversarial Attacks on Time Series27
End2End Occluded Face Recognition by Masking Corrupted Features26
Deep Non-Negative Matrix Factorization Architecture Based on Underlying Basis Images Learning26
Second-Order Pooling for Graph Neural Networks26
On Detection, Data Association and Segmentation for Multi-Target Tracking26
SANet: A Slice-Aware Network for Pulmonary Nodule Detection26
TransCenter: Transformers With Dense Representations for Multiple-Object Tracking26
Towards Efficient U-Nets: A Coupled and Quantized Approach26
Reinforced, Incremental and Cross-Lingual Event Detection From Social Messages26
Hierarchical Gaussian Descriptors with Application to Person Re-Identification26
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey26
Multi-Task Head Pose Estimation in-the-Wild26
Towards A Weakly Supervised Framework for 3D Point Cloud Object Detection and Annotation26
A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding26
Graph Neural Networks in Network Neuroscience26
Adversarial Action Prediction Networks26
Deep Differentiable Random Forests for Age Estimation26
Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features25
Deep Photometric Stereo for Non-Lambertian Surfaces25
Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification25
Active Surveillance via Group Sparse Bayesian Learning25
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning25
Universal Weighting Metric Learning for Cross-Modal Retrieval25
Cross-Generation Kinship Verification with Sparse Discriminative Metric25
Group Maximum Differentiation Competition: Model Comparison with Few Samples25
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos25
Meta-Teacher For Face Anti-Spoofing25
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet25
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement25
Deep Learning-based Multi-focus Image Fusion: A Survey and A Comparative Study25
Efficient Training for Positive Unlabeled Learning25
Bayesian Low-Tubal-Rank Robust Tensor Factorization with Multi-Rank Determination25
Distance Surface for Event-Based Optical Flow25
Fast and Robust Iterative Closest Point24
Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach24
Switchable Normalization for Learning-to-Normalize Deep Representation24
Persistence Paths and Signature Features in Topological Data Analysis24
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor24
From Handcrafted to Deep Features for Pedestrian Detection: A Survey24
Learning More Universal Representations for Transfer-Learning24
Deep Supervision with Intermediate Concepts24
High Frame Rate Video Reconstruction based on an Event Camera24
DeepGCNs: Making GCNs Go as Deep as CNNs24
Pixel2Mesh: 3D Mesh Model Generation via Image Guided Deformation24
Outlier Detection for Robust Multi-Dimensional Scaling24
Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning24
Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection24
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation24
On the Importance of Visual Context for Data Augmentation in Scene Understanding24
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation23
Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets23
Non-Local Graph Neural Networks23
An Efficient Solution to Non-Minimal Case Essential Matrix Estimation23
PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text23
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video23
Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks23
Co-Embedding of Nodes and Edges With Graph Neural Networks23
Runtime Network Routing for Efficient Image Classification23
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization23
RaspiReader: Open Source Fingerprint Reader23
Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation23
Learning Continuous Face Age Progression: A Pyramid of GANs23
Higher-Order Explanations of Graph Neural Networks via Relevant Walks23
Approximate Sparse Multinomial Logistic Regression for Classification23
Self-Distillation: Towards Efficient and Compact Neural Networks22
Automatic Detection of Pain from Facial Expressions: A Survey22
Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation22
Unsupervised Domain Adaptation via Discriminative Manifold Propagation22
Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation22
iDeLog: Iterative Dual Spatial and Kinematic Extraction of Sigma-Lognormal Parameters22
Learning Complexity-Aware Cascades for Pedestrian Detection22
Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation22
Reconstructive Sequence-Graph Network for Video Summarization22
Deep Coarse-to-Fine Dense Light Field Reconstruction With Flexible Sampling and Geometry-Aware Fusion22
Index Networks22
Real-Time Nonparametric Anomaly Detection in High-Dimensional Settings22
Instance-Invariant Domain Adaptive Object Detection via Progressive Disentanglement22
Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning22
Learning Raw Image Reconstruction-Aware Deep Image Compressors21
Hypergraph Learning: Methods and Practices21
Learning Optimal Wavefront Shaping for Multi-Channel Imaging21
Semi-Supervised Clustering With Constraints of Different Types From Multiple Information Sources21
Norm-Preservation: Why Residual Networks Can Become Extremely Deep?21
Deep Gait Recognition: A Survey21
From Show to Tell: A Survey on Deep Learning-Based Image Captioning21
Ordered or Orderless: A Revisit for Video Based Person Re-Identification21
InLoc: Indoor Visual Localization with Dense Matching and View Synthesis21
Interpretable Visual Question Answering by Reasoning on Dependency Trees21
3D Hand Pose Estimation Using Synthetic Data and Weakly Labeled RGB Images21
Contactless Biometric Identification Using 3D Finger Knuckle Patterns21
Multi-View Representation Learning With Deep Gaussian Processes21
Topology-Aware Graph Pooling Networks21
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation21
Personalized Saliency and Its Prediction21
Robust RGB-D Face Recognition Using Attribute-Aware Loss21
Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views21
Optimal Transport in Reproducing Kernel Hilbert Spaces: Theory and Applications21
Partial Multi-Label Learning via Credible Label Elicitation21
Active Camera Relocalization from a Single Reference Image without Hand-Eye Calibration21
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition21
AutoNovel: Automatically Discovering and Learning Novel Visual Categories21
Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation21
Can We See More? Joint Frontalization and Hallucination of Unaligned Tiny Faces20
Loss Decomposition and Centroid Estimation for Positive and Unlabeled Learning20
Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition20
Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets20
Regularizing Deep Networks with Semantic Data Augmentation20
Support Vector Machine Classifier via Soft-Margin Loss20
Part-Object Relational Visual Saliency20
Towards Age-Invariant Face Recognition20
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection20
A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution20
Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice20
Unmixing Convolutional Features for Crisp Edge Detection20
Adversarial Metric Attack and Defense for Person Re-Identification20
Recurrent Temporal Aggregation Framework for Deep Video Inpainting20
A Disocclusion Inpainting Framework for Depth-Based View Synthesis20
Semantic Object Accuracy for Generative Text-to-Image Synthesis20
Re-weighting and 1-Point RANSAC-Based P P Solution to Handle Outliers20
Max-Margin Majority Voting for Learning from Crowds20
Two-Stream Region Convolutional 3D Network for Temporal Activity Detection20
Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations20
Learning Content-Weighted Deep Image Compression20
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching20
In the Eye of the Beholder: Gaze and Actions in First Person Video20
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization20
AP-Loss for Accurate One-Stage Object Detection20
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook20
Coded Hyperspectral Image Reconstruction using Deep External and Internal Learning20
Meta-Transfer Learning Through Hard Tasks20
Distilled Siamese Networks for Visual Tracking20
Tensor Representations for Action Recognition19
Learning 3D Human Shape and Pose from Dense Body Parts19
Non-Exhaustive, Overlapping Clustering19
Building and Interpreting Deep Similarity Models19
AutoML for Multi-Label Classification: Overview and Empirical Evaluation19
Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction19
Adaptation Strategies for Automated Machine Learning on Evolving Data19
Image and Sentence Matching via Semantic Concepts and Order Learning19