IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
Squeeze-and-Excitation Networks	2348
Focal Loss for Dense Object Detection	2259
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	1515
Mask R-CNN	1334
Res2Net: A New Multi-Scale Backbone Architecture	940
Deep High-Resolution Representation Learning for Visual Recognition	902
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning	851
Image Segmentation Using Deep Learning: A Survey	731
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	522
Deep Learning for 3D Point Clouds: A Survey	521
Deep Learning for Image Super-Resolution: A Survey	514
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly	486
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding	454
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks	429
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	414
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	409
Event-Based Vision: A Survey	398
Deep Learning for Person Re-Identification: A Survey and Outlook	383
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm	382
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks	361
U2Fusion: A Unified Unsupervised Image Fusion Network	329
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification	316
Temporal Segment Networks for Action Recognition in Videos	315
Generalized Latent Multi-View Subspace Clustering	314
Residual Dense Network for Image Restoration	303

ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing	290
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	267
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	263
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs	260
Transferable Representation Learning with Deep Adaptation Networks	251
A Survey on Vision Transformer	249
Denoising Prior Driven Deep Neural Network for Image Restoration	246
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition	245
Richer Convolutional Features for Edge Detection	231
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI	220
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network	215
Meta-Learning in Neural Networks: A Survey	210
Recent Advances in Open Set Recognition: A Survey	206
Normalizing Flows: An Introduction and Review of Current Methods	205
A continual learning survey: Defying forgetting in classification tasks	201
Deep Multi-View Enhancement Hashing for Image Retrieval	198
Deep Collaborative Embedding for Social Image Understanding	189
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	188
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks	187
Advances in Variational Inference	185
A Review of Domain Adaptation without Target Labels	184
Detecting Coherent Groups in Crowd Scenes by Multiview Clustering	181
The ApolloScape Open Dataset for Autonomous Driving and Its Application	179
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection	177
Convolutional Networks with Dense Connectivity	169
Imbalance Problems in Object Detection: A Review	165
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	160
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	159
Moments in Time Dataset: One Million Videos for Event Understanding	158
Rank Minimization for Snapshot Compressive Imaging	155
Salient Object Detection in the Deep Learning Era: An In-Depth Survey	155
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes	151
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	151
Late Fusion Incomplete Multi-View Clustering	140
A Style-Based Generator Architecture for Generative Adversarial Networks	138
Multi-Task Learning for Dense Prediction Tasks: A Survey	137
YOLACT++ Better Real-Time Instance Segmentation	136
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	136
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	136
Revisiting Video Saliency Prediction in the Deep Learning Era	134
Plug-and-Play Image Restoration With Deep Denoiser Prior	133
Image Quality Assessment: Unifying Structure and Texture Similarity	126
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	121
A Comprehensive Analysis of Deep Regression	118
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos	114
Robust Visual Tracking via Hierarchical Convolutional Features	114
Deep Audio-Visual Speech Recognition	113
ThiNet: Pruning CNN Filters for a Thinner Net	112
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding	112
Robust Low-Rank Tensor Recovery with Rectification and Alignment	111

Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images	108
Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach	108
Interpreting Deep Visual Representations via Network Dissection	108
FCOS: A Simple and Strong Anchor-free Object Detector	107
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	105
Learning Depth with Convolutional Spatial Propagation Network	105
High Speed and High Dynamic Range Video with an Event Camera	104
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	103
On the Effectiveness of Least Squares Generative Adversarial Networks	102
Confidence Propagation through CNNs for Guided Sparse Depth Regression	102
CCNet: Criss-Cross Attention for Semantic Segmentation	101
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering	101
Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank	100
Unsupervised Tracklet Person Re-Identification	99
Single Image Dehazing Using Haze-Lines	99
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	98
Maximum Density Divergence for Domain Adaptation	97
Inferring Salient Objects from Human Fixations	95
Label Consistent Matrix Factorization Hashing for Large-Scale Cross-Modal Similarity Search	90
Skeleton-Based Online Action Prediction Using Scale Selection Network	89
Coherence Constrained Graph LSTM for Group Activity Recognition	87
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification	86
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video	86
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	85
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset	85
Single Image Deraining: From Model-Based to Data-Driven and Beyond	85
Hiding Images within Images	84
Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding	84
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	81
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation	78
Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking	77
Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks	77
Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer	76
Generalizable Data-Free Objective for Crafting Universal Adversarial Perturbations	76
A Comprehensive Database for Benchmarking Imaging Systems	75
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images	75
Representation Learning by Rotating Your Faces	75
Direction-Aware Spatial Context Features for Shadow Detection and Removal	75
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation	73
Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition	73
Contextual Transformer Networks for Visual Recognition	72
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges	71
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition	71
Neural Image Compression for Gigapixel Histopathology Image Analysis	71
Densely Residual Laplacian Super-Resolution	70
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation	70
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction	70
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes	70
Structured Knowledge Distillation for Dense Prediction	69
3D-Aided Dual-Agent GANs for Unconstrained Face Recognition	68
Dynamic Neural Networks: A Survey	68
Deep Neural Network Compression by In-Parallel Pruning-Quantization	68
Joint Image Filtering with Deep Convolutional Networks	68
Detection and Tracking Meet Drones Challenge	67
Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception	67
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle	67
Concealed Object Detection	67
Saliency Prediction in the Deep Learning Era: Successes and Limitations	66
Feature Boosting Network For 3D Pose Estimation	66
Deep Residual Correction Network for Partial Domain Adaptation	65
Learning to Adapt Invariance in Memory for Person Re-identification	64
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	64
Graph Neural Networks with Convolutional ARMA Filters	63
Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly	63
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction	62
Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation	62
Early Action Prediction by Soft Regression	61
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method	60
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval	59
Weakly Supervised Object Localization and Detection: A Survey	59
Physics-Based Generative Adversarial Models for Image Restoration and Beyond	59
Neural Machine Translation with Deep Attention	59
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing	58
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds	58
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks	58
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild	58
A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization	58
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	57
Learning Generalisable Omni-Scale Representations for Person Re-Identification	56
Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms	56

Infinite Feature Selection: A Graph-based Feature Filtering Approach	56
Low-Light Image and Video Enhancement Using Deep Learning: A Survey	56
Mutually Guided Image Filtering	56
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	55
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training	55
A Review on Deep Learning Techniques for Video Prediction	55
Dense 3D Object Reconstruction from a Single Depth View	55
Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods	55
Augmentation Invariant and Instance Spreading Feature for Softmax Embedding	54
Siamese Network for RGB-D Salient Object Detection and Beyond	54
End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning	54
PhlatCam: Designed Phase-Mask Based Thin Lensless Camera	54
A Fast Adaptive k-means with No Bounds	53
Incremental Learning Through Deep Adaptation	53
Multiset Feature Learning for Highly Imbalanced Data Classification	53
Object Detection in Videos by High Quality Object Linking	53
Nonlinear Regression via Deep Negative Correlation Learning	52
A Bayesian Formulation of Coherent Point Drift	52
Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers	52
Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging	52
Tensor Low-Rank Representation for Data Recovery and Clustering	51
A Novel Approach to Large-Scale Dynamically Weighted Directed Network Representation	51
SensitiveNets: Learning Agnostic Representations with Application to Face Images	51
A Survey on Curriculum Learning	50
SPFTN: A Joint Learning Framework for Localizing and Segmenting Objects in Weakly Labeled Videos	50
Multi-Source Causal Feature Selection	50
P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization	49
DeepFake Detection Based on Discrepancies Between Faces and Their Context	49
Non-local Meets Global: An Integrated Paradigm for Hyperspectral Image Restoration	49
Domain Generalization: A Survey	49
Convolutional Neural Network Architecture for Geometric Matching	49
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models	49
Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification	49
Hashing with Mutual Information	48
Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation	48
Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks	48
An End-to-End Learning Framework for Video Compression	48
Dual Encoding for Video Retrieval by Text	47
Person Re-Identification by Contour Sketch Under Moderate Clothing Change	47
Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time	47
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging	47
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing	47
Learning Part-based Convolutional Features for Person Re-Identification	47
Object Detection from Scratch with Deep Supervision	47
Negation of the Quantum Mass Function for Multisource Quantum Information Fusion With its Application to Pattern Classification	47
Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations	47
Context-Aware Visual Policy Network for Fine-Grained Image Captioning	47
A Survey of Single-Scene Video Anomaly Detection	47
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL	46
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition	46
Image Super-Resolution Via Iterative Refinement	46
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?	46
Learning a Fixed-Length Fingerprint Representation	46
Simultaneous Fidelity and Regularization Learning for Image Restoration	45
Cascaded Parsing of Human-Object Interaction Recognition	45
Paying Attention to Video Object Pattern Understanding	45
Hyperspectral Recovery from RGB Images using Gaussian Processes	45
GAN Inversion: A Survey	44
Bayesian Temporal Factorization for Multidimensional Time Series Prediction	44
Deep Convolutional Neural Network for Multi-Modal Image Restoration and Fusion	44
Enhanced Tensor RPCA and its Application	44
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction	44
Neural Architecture Transfer	43
Face-from-Depth for Head Pose Estimation on Depth Images	43
Min-Entropy Latent Model for Weakly Supervised Object Detection	43
CTNet: Context-Based Tandem Network for Semantic Segmentation	43
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition	43
Fast Multi-Instance Multi-Label Learning	42
Real-World Image Denoising with Deep Boosting	42
On the Convergence of Learning-Based Iterative Methods for Nonconvex Inverse Problems	42
On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks	42
Self-Correction for Human Parsing	41
RGB-D SLAM in Dynamic Environments Using Point Correlations	41
Semi-Supervised Multi-View Deep Discriminant Representation Learning	41
A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking	41
Generalized Feedback Loop for Joint Hand-Object Pose Estimation	41
Deep Partial Multi-View Learning	41
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning	41
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Network	41
Segmenting Objects From Relational Visual Data	41
Salient Subsequence Learning for Time Series Clustering	40
Subspace Clustering via Good Neighbors	40
Neural Sensors: Learning Pixel Exposures for HDR Imaging and Video Compressive Sensing With Programmable Sensors	40
Fine-Grained Image Analysis With Deep Learning: A Survey	40
Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy	40
Parallax Attention for Unsupervised Stereo Correspondence Learning	40
Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction	40
Focal Visual-Text Attention for Memex Question Answering	39
Uncertainty Inspired RGB-D Saliency Detection	39
Learning to Match Anchors for Visual Object Detection	39
Towards Robust Discriminative Projections Learning via Non-Greedy -Norm MinMax	38
Deep Hough Transform for Semantic Line Detection	38
Real-Time RGB-D Camera Pose Estimation in Novel Scenes Using a Relocalisation Cascade	38
Long-Term Visual Localization Revisited	38
Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning	37
Absent Multiple Kernel Learning Algorithms	37
Symbiotic Attention for Egocentric Action Recognition With Object-Centric Alignment	37
Intel® RealSense™ SR300 Coded Light Depth Camera	37
What and How: Generalized Lifelong Spectral Clustering via Dual Memory	37
Deep Clustering: On the Link Between Discriminative Models and K-Means	37
Open Set Domain Adaptation for Image and Action Recognition	37
Momentum-Net: Fast and Convergent Iterative Neural Network for Inverse Problems	37
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	37
Pose-Guided Representation Learning for Person Re-Identification	36
ArcFace: Additive Angular Margin Loss for Deep Face Recognition	36
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation	36
SibNet: Sibling Convolutional Encoder for Video Captioning	36
Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships	36
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation	35
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition	35
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation	35
Large Graph Clustering With Simultaneous Spectral Embedding and Discretization	35
Analysis of the Hands in Egocentric Vision: A Survey	35
High-Fidelity Monocular Face Reconstruction Based on an Unsupervised Model-Based Face Autoencoder	35
Distributed Variational Representation Learning	35
CoRRN: Cooperative Reflection Removal Network	34
Semi-Supervised Domain Adaptation by Covariance Matching	34
Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks	34
Line Graph Neural Networks for Link Prediction	34
Visual Tracking via Dynamic Graph Learning	34
The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines	34
Unsupervised Domain Adaptation for Depth Prediction from Images	34
Packing Convolutional Neural Networks in the Frequency Domain	34
Label Independent Memory for Semi-Supervised Few-shot Video Classification	33
Visibility Graphs for Image Processing	33
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC	33
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation	33
RefineFace: Refinement Neural Network for High Performance Face Detection	33
ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning	33
Efficient and Effective Regularized Incomplete Multi-view Clustering	33
Convolutional Prototype Network for Open Set Recognition	33
Learning Compact Features for Human Activity Recognition Via Probabilistic First-Take-All	33
UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction Using Commercial RGBD Cameras	33
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D	33
Deep Self-Evolution Clustering	32
Neural Granger Causality	32
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation	32
Surface-Aware Blind Image Deblurring	32
Learning End-to-End Lossy Image Compression: A Benchmark	32
Deep Variational and Structural Hashing	32
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size	32
Recognizing Material Properties from Images	32
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition	32
Towards a Complete 3D Morphable Model of the Human Head	32
Bias in Cross-Entropy-Based Training of Deep Survival Networks	32

Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences	32
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers	32
Age from Faces in the Deep Learning Revolution	32
Pattern of Local Gravitational Force (PLGF): A Novel Local Image Descriptor	31
Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation	31
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology	31
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition	31
Chart Mining: A Survey of Methods for Automated Chart Analysis	31
Robust Bi-stochastic Graph Regularized Matrix Factorization for Data Clustering	31
End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform	31
SurfelMeshing: Online Surfel-Based Mesh Reconstruction	31
Deep Object Tracking with Shrinkage Loss	31
Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery	31
Adversarial Reciprocal Points Learning for Open Set Recognition	31
Explainability in Graph Neural Networks: A Taxonomic Survey	31
A Differential Approach for Gaze Estimation	30
Learning to Compose and Reason with Language Tree Structures for Visual Grounding	30
Kernel-Based Density Map Generation for Dense Object Counting	30
Joint Camera Spectral Response Selection and Hyperspectral Image Recovery	30
A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras	30
Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications	30
Robust Multi-View Clustering With Incomplete Information	30
On Learning Disentangled Representations for Gait Recognition	30
Deep Back-ProjectiNetworks for Single Image Super-Resolution	30
Scattering Networks for Hybrid Representation Learning	30
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer	29
Training Faster by Separating Modes of Variation in Batch-Normalized Models	29
GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set	29
The Emerging Trends of Multi-Label Learning	29
Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features	29
Zero and Few Shot Learning With Semantic Feature Synthesis and Competitive Learning	29
Learning Deep Binary Descriptor with Multi-Quantization	29
Learning with Privileged Information via Adversarial Discriminative Modality Distillation	29
BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection	29
DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features	29
A Simple and Fast Algorithm for L1-Norm Kernel PCA	29
DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions	28
Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification	28
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling	28
Height-from-Polarisation with Unknown Lighting or Albedo	28
A Self-Supervised Gait Encoding Approach With Locality-Awareness for 3D Skeleton Based Person Re-Identification	28
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration	28
Guided Attention Inference Network	28
Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation	28
Deep Model Intellectual Property Protection via Deep Watermarking	28
A Comprehensive Survey of Scene Graphs: Generation and Application	28
Salient Object Detection via Integrity Learning	28
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion	28
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	28
Re-thinking Co-Salient Object Detection	28
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video	27
Human Action Recognition From Various Data Modalities: A Review	27
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition	27
Adversarial Attacks on Time Series	27
Optimizing Latent Distributions for Non-Adversarial Generative Networks	27
Generative Zero-Shot Learning via Low-Rank Embedded Semantic Dictionary	27
Disentangling Light Fields for Super-Resolution and Disparity Estimation	27
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	27
DAC-SDC Low Power Object Detection Challenge for UAV Applications	27
Cooperative Training of Descriptor and Generator Networks	27
Semi-Supervised Adversarial Monocular Depth Estimation	27
VOLO: Vision Outlooker for Visual Recognition	27
End2End Occluded Face Recognition by Masking Corrupted Features	26
Deep Non-Negative Matrix Factorization Architecture Based on Underlying Basis Images Learning	26
Second-Order Pooling for Graph Neural Networks	26
On Detection, Data Association and Segmentation for Multi-Target Tracking	26
SANet: A Slice-Aware Network for Pulmonary Nodule Detection	26
TransCenter: Transformers With Dense Representations for Multiple-Object Tracking	26
Towards Efficient U-Nets: A Coupled and Quantized Approach	26
Reinforced, Incremental and Cross-Lingual Event Detection From Social Messages	26
Hierarchical Gaussian Descriptors with Application to Person Re-Identification	26
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey	26
Multi-Task Head Pose Estimation in-the-Wild	26
Towards A Weakly Supervised Framework for 3D Point Cloud Object Detection and Annotation	26
A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding	26
Graph Neural Networks in Network Neuroscience	26
Adversarial Action Prediction Networks	26
Deep Differentiable Random Forests for Age Estimation	26
Deep Learning-based Multi-focus Image Fusion: A Survey and A Comparative Study	25
Efficient Training for Positive Unlabeled Learning	25
Bayesian Low-Tubal-Rank Robust Tensor Factorization with Multi-Rank Determination	25
Distance Surface for Event-Based Optical Flow	25
Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features	25
Deep Photometric Stereo for Non-Lambertian Surfaces	25
Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification	25
Active Surveillance via Group Sparse Bayesian Learning	25
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning	25
Universal Weighting Metric Learning for Cross-Modal Retrieval	25
Cross-Generation Kinship Verification with Sparse Discriminative Metric	25
Group Maximum Differentiation Competition: Model Comparison with Few Samples	25
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos	25
Meta-Teacher For Face Anti-Spoofing	25
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet	25
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement	25
Fast and Robust Iterative Closest Point	24
Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach	24
Switchable Normalization for Learning-to-Normalize Deep Representation	24
Persistence Paths and Signature Features in Topological Data Analysis	24
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor	24
From Handcrafted to Deep Features for Pedestrian Detection: A Survey	24
Learning More Universal Representations for Transfer-Learning	24
Deep Supervision with Intermediate Concepts	24
High Frame Rate Video Reconstruction based on an Event Camera	24
DeepGCNs: Making GCNs Go as Deep as CNNs	24
Pixel2Mesh: 3D Mesh Model Generation via Image Guided Deformation	24
Outlier Detection for Robust Multi-Dimensional Scaling	24
Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning	24
Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection	24
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation	24
On the Importance of Visual Context for Data Augmentation in Scene Understanding	24
Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation	23
Learning Continuous Face Age Progression: A Pyramid of GANs	23
Higher-Order Explanations of Graph Neural Networks via Relevant Walks	23
Approximate Sparse Multinomial Logistic Regression for Classification	23
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation	23
Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets	23
Non-Local Graph Neural Networks	23
An Efficient Solution to Non-Minimal Case Essential Matrix Estimation	23
PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text	23
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video	23
Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks	23
Co-Embedding of Nodes and Edges With Graph Neural Networks	23
Runtime Network Routing for Efficient Image Classification	23
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization	23
RaspiReader: Open Source Fingerprint Reader	23
Self-Distillation: Towards Efficient and Compact Neural Networks	22
Automatic Detection of Pain from Facial Expressions: A Survey	22
Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation	22
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	22
Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation	22
iDeLog: Iterative Dual Spatial and Kinematic Extraction of Sigma-Lognormal Parameters	22
Learning Complexity-Aware Cascades for Pedestrian Detection	22
Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation	22
Reconstructive Sequence-Graph Network for Video Summarization	22
Deep Coarse-to-Fine Dense Light Field Reconstruction With Flexible Sampling and Geometry-Aware Fusion	22
Index Networks	22
Real-Time Nonparametric Anomaly Detection in High-Dimensional Settings	22
Instance-Invariant Domain Adaptive Object Detection via Progressive Disentanglement	22
Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning	22
Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views	21
Optimal Transport in Reproducing Kernel Hilbert Spaces: Theory and Applications	21
Partial Multi-Label Learning via Credible Label Elicitation	21
Active Camera Relocalization from a Single Reference Image without Hand-Eye Calibration	21
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition	21
Learning Optimal Wavefront Shaping for Multi-Channel Imaging	21
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	21
Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation	21
Learning Raw Image Reconstruction-Aware Deep Image Compressors	21
Hypergraph Learning: Methods and Practices	21
Semi-Supervised Clustering With Constraints of Different Types From Multiple Information Sources	21
Norm-Preservation: Why Residual Networks Can Become Extremely Deep?	21
Deep Gait Recognition: A Survey	21
From Show to Tell: A Survey on Deep Learning-Based Image Captioning	21
Ordered or Orderless: A Revisit for Video Based Person Re-Identification	21
InLoc: Indoor Visual Localization with Dense Matching and View Synthesis	21
Interpretable Visual Question Answering by Reasoning on Dependency Trees	21
3D Hand Pose Estimation Using Synthetic Data and Weakly Labeled RGB Images	21
Contactless Biometric Identification Using 3D Finger Knuckle Patterns	21
Multi-View Representation Learning With Deep Gaussian Processes	21
Topology-Aware Graph Pooling Networks	21
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation	21
Personalized Saliency and Its Prediction	21
Robust RGB-D Face Recognition Using Attribute-Aware Loss	21
Learning Content-Weighted Deep Image Compression	20
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching	20
In the Eye of the Beholder: Gaze and Actions in First Person Video	20
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization	20
AP-Loss for Accurate One-Stage Object Detection	20
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook	20
Coded Hyperspectral Image Reconstruction using Deep External and Internal Learning	20
Meta-Transfer Learning Through Hard Tasks	20
Distilled Siamese Networks for Visual Tracking	20
Can We See More? Joint Frontalization and Hallucination of Unaligned Tiny Faces	20
Loss Decomposition and Centroid Estimation for Positive and Unlabeled Learning	20
Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition	20
Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets	20
Regularizing Deep Networks with Semantic Data Augmentation	20
Support Vector Machine Classifier via Soft-Margin Loss	20
Part-Object Relational Visual Saliency	20
Towards Age-Invariant Face Recognition	20
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection	20
A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution	20
Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice	20
Unmixing Convolutional Features for Crisp Edge Detection	20
Adversarial Metric Attack and Defense for Person Re-Identification	20
Recurrent Temporal Aggregation Framework for Deep Video Inpainting	20
A Disocclusion Inpainting Framework for Depth-Based View Synthesis	20
Semantic Object Accuracy for Generative Text-to-Image Synthesis	20
Re-weighting and 1-Point RANSAC-Based P P Solution to Handle Outliers	20
Max-Margin Majority Voting for Learning from Crowds	20
Two-Stream Region Convolutional 3D Network for Temporal Activity Detection	20
Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations	20
Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction	19
Adaptation Strategies for Automated Machine Learning on Evolving Data	19
Image and Sentence Matching via Semantic Concepts and Order Learning	19
Tensor Representations for Action Recognition	19
Learning 3D Human Shape and Pose from Dense Body Parts	19
Non-Exhaustive, Overlapping Clustering	19
Building and Interpreting Deep Similarity Models	19
AutoML for Multi-Label Classification: Overview and Empirical Evaluation	19