OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 91. 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 2019-09-01 to 2023-09-01.)

Article	Citations
Squeeze-and-Excitation Networks	2466
Focal Loss for Dense Object Detection	2369
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	1578
Mask R-CNN	1394
Deep High-Resolution Representation Learning for Visual Recognition	1012
Res2Net: A New Multi-Scale Backbone Architecture	1004
Image Segmentation Using Deep Learning: A Survey	761
Deep Learning for 3D Point Clouds: A Survey	564
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	556
Deep Learning for Image Super-Resolution: A Survey	549
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly	526
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding	492
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	454
Event-Based Vision: A Survey	450
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	446
Deep Learning for Person Re-Identification: A Survey and Outlook	428
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm	403
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks	381
U2Fusion: A Unified Unsupervised Image Fusion Network	372
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification	344
Temporal Segment Networks for Action Recognition in Videos	334
Residual Dense Network for Image Restoration	332
Generalized Latent Multi-View Subspace Clustering	324
A Survey on Vision Transformer	304
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing	304

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	285
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs	279
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	276
Transferable Representation Learning with Deep Adaptation Networks	263
Denoising Prior Driven Deep Neural Network for Image Restoration	260
Meta-Learning in Neural Networks: A Survey	232
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI	226
Recent Advances in Open Set Recognition: A Survey	224
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network	222
Normalizing Flows: An Introduction and Review of Current Methods	221
A continual learning survey: Defying forgetting in classification tasks	221
Deep Multi-View Enhancement Hashing for Image Retrieval	207
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	203
Deep Collaborative Embedding for Social Image Understanding	199
A Review of Domain Adaptation without Target Labels	198
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks	195
The ApolloScape Open Dataset for Autonomous Driving and Its Application	192
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	189
Detecting Coherent Groups in Crowd Scenes by Multiview Clustering	184
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection	183
Imbalance Problems in Object Detection: A Review	181
Convolutional Networks with Dense Connectivity	174
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	170
Rank Minimization for Snapshot Compressive Imaging	169
Salient Object Detection in the Deep Learning Era: An In-Depth Survey	168
Moments in Time Dataset: One Million Videos for Event Understanding	165
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	160
Multi-Task Learning for Dense Prediction Tasks: A Survey	153
A Style-Based Generator Architecture for Generative Adversarial Networks	152
Plug-and-Play Image Restoration With Deep Denoiser Prior	151
Late Fusion Incomplete Multi-View Clustering	146
YOLACT++ Better Real-Time Instance Segmentation	144
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	144
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	141
Image Quality Assessment: Unifying Structure and Texture Similarity	138
Revisiting Video Saliency Prediction in the Deep Learning Era	135
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	132
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos	124
A Comprehensive Analysis of Deep Regression	122
High Speed and High Dynamic Range Video with an Event Camera	118
Deep Audio-Visual Speech Recognition	117
ThiNet: Pruning CNN Filters for a Thinner Net	117
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding	117
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	117
Robust Visual Tracking via Hierarchical Convolutional Features	116
FCOS: A Simple and Strong Anchor-free Object Detector	116
Interpreting Deep Visual Representations via Network Dissection	114
Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images	113
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	113
Robust Low-Rank Tensor Recovery with Rectification and Alignment	113

Learning Depth with Convolutional Spatial Propagation Network	112
CCNet: Criss-Cross Attention for Semantic Segmentation	109
Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach	109
Confidence Propagation through CNNs for Guided Sparse Depth Regression	107
Maximum Density Divergence for Domain Adaptation	106
Single Image Dehazing Using Haze-Lines	105
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	105
On the Effectiveness of Least Squares Generative Adversarial Networks	104
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering	103
Unsupervised Tracklet Person Re-Identification	102
Inferring Salient Objects from Human Fixations	97
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	97
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	93
Skeleton-Based Online Action Prediction Using Scale Selection Network	93
Coherence Constrained Graph LSTM for Group Activity Recognition	92
Label Consistent Matrix Factorization Hashing for Large-Scale Cross-Modal Similarity Search	91