OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 101. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-04-01 to 2024-04-01.)

Article	Citations
Squeeze-and-Excitation Networks	3141
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	2006
Deep High-Resolution Representation Learning for Visual Recognition	1571
Res2Net: A New Multi-Scale Backbone Architecture	1399
Image Segmentation Using Deep Learning: A Survey	1077
Deep Learning for 3D Point Clouds: A Survey	826
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	799
A Survey on Vision Transformer	756
Deep Learning for Image Super-Resolution: A Survey	753
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding	698
Deep Learning for Person Re-Identification: A Survey and Outlook	689
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	664
Event-Based Vision: A Survey	663
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	622
U2Fusion: A Unified Unsupervised Image Fusion Network	580
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm	498
Residual Dense Network for Image Restoration	441
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	437
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	418
Meta-Learning in Neural Networks: A Survey	397
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs	379
A continual learning survey: Defying forgetting in classification tasks	378
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	373
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	342
Recent Advances in Open Set Recognition: A Survey	338

Normalizing Flows: An Introduction and Review of Current Methods	337
Plug-and-Play Image Restoration With Deep Denoiser Prior	290
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI	285
A Style-Based Generator Architecture for Generative Adversarial Networks	272
Deep Multi-View Enhancement Hashing for Image Retrieval	270
Salient Object Detection in the Deep Learning Era: An In-Depth Survey	266
A Review of Domain Adaptation without Target Labels	266
The ApolloScape Open Dataset for Autonomous Driving and Its Application	256
Imbalance Problems in Object Detection: A Review	255
Image Super-Resolution Via Iterative Refinement	254
Convolutional Networks with Dense Connectivity	236
Multi-Task Learning for Dense Prediction Tasks: A Survey	232
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks	228
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	216
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	207
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	207
Detection and Tracking Meet Drones Challenge	204
YOLACT++ Better Real-Time Instance Segmentation	197
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	191
Contextual Transformer Networks for Visual Recognition	190
Deep Audio-Visual Speech Recognition	188
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	183
High Speed and High Dynamic Range Video with an Event Camera	181
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	179
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	176
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	173
Dynamic Neural Networks: A Survey	170
Revisiting Video Saliency Prediction in the Deep Learning Era	165
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	161
Concealed Object Detection	161
CCNet: Criss-Cross Attention for Semantic Segmentation	160
Low-Light Image and Video Enhancement Using Deep Learning: A Survey	159
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos	156
Maximum Density Divergence for Domain Adaptation	154
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks	152
Domain Generalization: A Survey	149
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation	146
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges	143
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training	141
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding	141
A Comprehensive Analysis of Deep Regression	139
Learning Depth with Convolutional Spatial Propagation Network	139
Inferring Salient Objects from Human Fixations	134
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction	133
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition	132
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	130
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	128
Diffusion Models in Vision: A Survey	128
Confidence Propagation through CNNs for Guided Sparse Depth Regression	128
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification	124

Unsupervised Tracklet Person Re-Identification	124
Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking	124
Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks	123
Single Image Deraining: From Model-Based to Data-Driven and Beyond	122
Coherence Constrained Graph LSTM for Group Activity Recognition	121
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models	120
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video	119
Robust Low-Rank Tensor Recovery with Rectification and Alignment	119
Human Action Recognition From Various Data Modalities: A Review	118
Neural Image Compression for Gigapixel Histopathology Image Analysis	116
ArcFace: Additive Angular Margin Loss for Deep Face Recognition	115
Densely Residual Laplacian Super-Resolution	115
GAN Inversion: A Survey	115
Hiding Images within Images	114
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing	112
Direction-Aware Spatial Context Features for Shadow Detection and Removal	111
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation	110
Weakly Supervised Object Localization and Detection: A Survey	106
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning	104
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images	104
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval	104
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion	104
A Survey on Curriculum Learning	103
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	103
Skeleton-Based Online Action Prediction Using Scale Selection Network	103
Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding	102