OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 103. 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 2020-05-01 to 2024-05-01.)

Article	Citations
Squeeze-and-Excitation Networks	3253
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	2061
Deep High-Resolution Representation Learning for Visual Recognition	1671
Res2Net: A New Multi-Scale Backbone Architecture	1455
Image Segmentation Using Deep Learning: A Survey	1118
Deep Learning for 3D Point Clouds: A Survey	878
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	830
A Survey on Vision Transformer	821
Deep Learning for Image Super-Resolution: A Survey	788
Deep Learning for Person Re-Identification: A Survey and Outlook	734
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding	719
Event-Based Vision: A Survey	701
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	691
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	654
U2Fusion: A Unified Unsupervised Image Fusion Network	628
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	478
Residual Dense Network for Image Restoration	451
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	440
Meta-Learning in Neural Networks: A Survey	420
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	404
A continual learning survey: Defying forgetting in classification tasks	396
Normalizing Flows: An Introduction and Review of Current Methods	357
Recent Advances in Open Set Recognition: A Survey	352
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	349
Plug-and-Play Image Restoration With Deep Denoiser Prior	311

Image Super-Resolution Via Iterative Refinement	290
A Style-Based Generator Architecture for Generative Adversarial Networks	282
Salient Object Detection in the Deep Learning Era: An In-Depth Survey	275
Deep Multi-View Enhancement Hashing for Image Retrieval	274
A Review of Domain Adaptation without Target Labels	274
The ApolloScape Open Dataset for Autonomous Driving and Its Application	264
Imbalance Problems in Object Detection: A Review	257
Convolutional Networks with Dense Connectivity	246
Multi-Task Learning for Dense Prediction Tasks: A Survey	245
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks	236
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	228
Detection and Tracking Meet Drones Challenge	220
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	220
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	213
YOLACT++ Better Real-Time Instance Segmentation	208
Contextual Transformer Networks for Visual Recognition	204
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	202
Deep Audio-Visual Speech Recognition	200
High Speed and High Dynamic Range Video with an Event Camera	193
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	191
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	185
Dynamic Neural Networks: A Survey	185
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	181
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	178
Low-Light Image and Video Enhancement Using Deep Learning: A Survey	176
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	175
Concealed Object Detection	174
CCNet: Criss-Cross Attention for Semantic Segmentation	172
Domain Generalization: A Survey	171
Revisiting Video Saliency Prediction in the Deep Learning Era	169
Maximum Density Divergence for Domain Adaptation	165
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos	161
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation	157
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks	157
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training	157
Diffusion Models in Vision: A Survey	156
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges	149
A Comprehensive Analysis of Deep Regression	143
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	143
Learning Depth with Convolutional Spatial Propagation Network	143
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding	143
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction	139
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition	138
Human Action Recognition From Various Data Modalities: A Review	135
Inferring Salient Objects from Human Fixations	134
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models	134
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	133
Unsupervised Tracklet Person Re-Identification	130
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification	130
Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks	130

Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking	128
Confidence Propagation through CNNs for Guided Sparse Depth Regression	128
Single Image Deraining: From Model-Based to Data-Driven and Beyond	127
Coherence Constrained Graph LSTM for Group Activity Recognition	126
ArcFace: Additive Angular Margin Loss for Deep Face Recognition	126
GAN Inversion: A Survey	125
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video	124
Robust Low-Rank Tensor Recovery with Rectification and Alignment	122
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing	122
Densely Residual Laplacian Super-Resolution	121
Hiding Images within Images	120
Neural Image Compression for Gigapixel Histopathology Image Analysis	118
Weakly Supervised Object Localization and Detection: A Survey	116
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning	116
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion	113
Direction-Aware Spatial Context Features for Shadow Detection and Removal	111
A Survey on Curriculum Learning	110
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation	110
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	110
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval	109
Self-Correction for Human Parsing	109
Negation of the Quantum Mass Function for Multisource Quantum Information Fusion With its Application to Pattern Classification	108
Graph U-Nets	107
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images	107
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?	105
Fine-Grained Image Analysis With Deep Learning: A Survey	104
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	104
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification	103
Graph Neural Networks with Convolutional ARMA Filters	103
Skeleton-Based Online Action Prediction Using Scale Selection Network	103
Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods	103