OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Multimedia is 59. 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 2021-04-01 to 2025-04-01.)

Article	Citations
Compact Latent Primitive Space Learning for Compositional Zero-Shot Learning	483
Cluster Assumption-Guided Timestamp-Supervised Temporal Action Segmentation	270
Uncertainty-Guided Diffusion Model for Camouflaged Object Detection	261
Ensemble Prototype Networks for Unsupervised Cross-modal Hashing with Cross-Task Consistency	198
CLIP-GAN: Stacking CLIPs and GAN for Efficient and Controllable Text-to-Image Synthesis	190
Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations	188
WV-LUT: Wide Vision Lookup Tables for Real-Time Low-Light Image Enhancement	162
Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection	157
Text2Avatar: Articulated 3D Avatar Creation with Text Instructions	148
PRA-Det: Anchor-Free Oriented Object Detection With Polar Radius Representation	143
Video Instance Segmentation Without Using Mask and Identity Supervision	128
Learning From Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation	127
High-Quality Reconstruction of Depth Maps From Graph-Based Non-Uniform Sampling	124
PointMCD: Boosting Deep Point Cloud Encoders via Multi-View Cross-Modal Distillation for 3D Shape Recognition	113
CrossNet: Cross-Scene Background Subtraction Network via 3D Optical Flow	108
Multiple Adaptation Network for Multi-source and Multi-target Domain Adaptation	106
An Efficient Ungrouped Mask Method With two Learnable Parameters for 3D Object Detection	104
AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation	99
Adaptive Multi-Scale Language Reinforcement for Multimodal Named Entity Recognition	98
DSAF: Dual Space Alignment Framework for Visible-Infrared Person Re-Identification	96
Deep Mutual Distillation for Unsupervised Domain Adaptation Person Re-Identification	96
Progressive Knowledge Distillation From Different Levels of Teachers for Online Action Detection	93
Rethinking Depth Guided Reflection Removal	93
Beyond Subspace Isolation: Many-to-Many Transformer for Light Field Image Super-Resolution	93
A Multi-Granularity Relation Graph Aggregation Framework with Multimodal Clues for Social Relation Reasoning	93

Masked Attribute Description Embedding for Cloth-Changing Person Re-Identification	92
Discriminative Anchor Learning for Efficient Multi-View Clustering	89
Generalizable Prompt Learning via Gradient Constrained Sharpness-Aware Minimization	88
Leveraging Enriched Skeleton Representation With Multi-Relational Metrics for Few-Shot Action Recognition	87
Improving Vision Anomaly Detection With the Guidance of Language Modality	86
GFTLS-SLT: Gloss-Free Transformer Based Lexical and Semantic Awareness Framework for Multimodal Sign Language Translation	85
MIGN: Multiscale Image Generation Network for Remote Sensing Image Semantic Segmentation	82
Robust Multimodal Sentiment Analysis via Tag Encoding of Uncertain Missing Modalities	81
UCM-Net: A U-Net-Like Tampered-Region-Related Framework for Copy-Move Forgery Detection	77
Lightweight Video-Based Respiration Rate Detection Algorithm: An Application Case on Intensive Care	77
Combining Retargeting Quality and Depth Perception Measures for Quality Evaluation of Retargeted Stereopairs	76
Semi-Supervised Domain Adaptation for Major Depressive Disorder Detection	75
RSUIA: Dynamic No-Reference Underwater Image Assessment via Reinforcement Sequences	74
ETC: Temporal Boundary Expand Then Clarify for Weakly Supervised Video Grounding With Multimodal Large Language Model	73
One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing	72
Heterogeneous Domain Adaptation via Correlative and Discriminative Feature Learning	72
Deep Semantic-consistent Penalizing Hashing for Cross-modal Retrieval	71
Asymptotics-Aware Multi-View Subspace Clustering	70
Snippet-inter Difference Attention Network for Weakly-supervised Temporal Action Localization	70
Learning Shape-Color Diffusion Priors for Text-Guided 3D Object Generation	65
Multi-view Clustering via Multi-stage Fusion	65
Rectangling for Stitched Image via Pixel-wise Deformation Learning	65
Hand Gesture Recognition from an Open-Set Perspective	65
BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised Learning	64
DCPTalk: Speech-Driven 3D Face Animation With Personalized Facial Dynamic Coupling Properties	64
Dual Semantic Reconstruction Network for Weakly Supervised Temporal Sentence Grounding	62
List of Reviewers	62
From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios	62
IEEE Transactions on Multimedia Publication Information	61
BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge	61
Dual-Domain Aligned Deep Hierarchical Matrix Factorization Method for Micro-Video Multi-Label Classification	60
Provably Secure Robust Image Steganography	60
SGG-Nets: Generic Rotation-Invariant Plugin Networks for Point Cloud Analysis	59
Learning the Global Descriptor for 3-D Object Recognition Based on Multiple Views Decomposition	59
Progressive Local Filter Pruning for Image Retrieval Acceleration	59