OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Multimedia is 83. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Improving Vision Anomaly Detection With the Guidance of Language Modality	1006
Focusing on Subtle Differences: A Feature Disentanglement Model for Series Photo Selection	547
Rethinking Video Sentence Grounding From a Tracking Perspective With Memory Network and Masked Attention	398
Rethinking Affine Transform for Efficient Image Enhancement: A Color Space Perspective	366
FoodSAM: Any Food Segmentation	261
Online Low-Light Sand-Dust Video Enhancement Using Adaptive Dynamic Brightness Correction and a Rolling Guidance Filter	228
Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization	207
SGG-Nets: Generic Rotation-Invariant Plugin Networks for Point Cloud Analysis	204
ViDR-GNN: Vision Implicit Discriminative Reorganization Graph Neural Networks	202
Dual-Task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding	196
Few-Shot Generative Model Adaptation via Style-Guided Prompt	195
Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations	191
Towards Substation Semantic Segmentation: A benchmark dataset and a cross-attention embedded hierarchical network	184
HRVFusion: Video-based Long-Term Heart Rate Variability Measurement with Conditional Diffusion Models	168
Revisiting the Adversarial Transferability: Towards a Perspective of Semantic Preservation	162
Exploring Kernel Transformations for Implicit Neural Representations	160
Posture-Movement-Frequency-Enhanced Graph Convolutional Network for Gait Emotion Recognition	158
LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation	156
Mask-Aware Kernel Learning for Action Recognition	156
Bias-Correction Feature Learner for Semi-Supervised Instance Segmentation	155
Mix-Based Training Strategies for Learning Implicit Neural Representations	154
Bidirectional Translation Between UHD-HDR and HD-SDR Videos	153
Optimal Transport-Based Patch Matching for Image Style Transfer	151
Neighborhood Contrastive Transformer for Change Captioning	151
Robust Multi-Stage Tracking via Multi-Scale and Multi-Level Representation Learning	144

Watch Where You Move: Region-Aware Dynamic Aggregation and Excitation for Gait Recognition	142
PropMambaSR: Lightweight Image Super-Resolution with Propagation State Space Model	139
Adaptive Weight Generator for Multi-Task Image Recognition by Task Grouping Prompt	138
Semantic-Aware Triplet Loss for Image Classification	136
Semantic Dual-Adversarial Network for Blended-Target Domain Adaptation	136
AMS-Net: Adaptive Multi-Scale Network for Image Compressive Sensing	135
DWSF-Net: A Dynamic Wavelet-based Spatial-frequency Fusion Network for Multispectral Object Detection	135
Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization	134
Disaggregation Distillation for Person Search	132
Rényi Entropy Induced Efficient and Balanced One-Step Multi-View Clustering	132
Vision-Controllable Language Model for Image-Guided Story Ending Generation	128
Multi-Level Transitional Contrast Learning for Personalized Image Aesthetics Assessment	125
Semi-Supervised Contrastive Learning With Similarity Co-Calibration	123
Distributed Deep Point Cloud Feature Compression for Vehicle-to-Vehicle Cooperative Perception	120
Guided Image-to-Image Translation by Discriminator-Generator Communication	119
Weakly-Supervised 3D Visual Grounding Based on Visual Language Alignment	119
One-Shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing	118
MHRN: A Multimodal Hierarchical Reasoning Network for Topic Detection	115
SCSP: An Unsupervised Image-to-Image Translation Network Based on Semantic Cooperative Shape Perception	115
BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised Learning	114
Unsupervised Learning-Based Framework for Deepfake Video Detection	114
Long Video Understanding With Learnable Retrieval in Video-Language Models	113
Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames	112
Transferable Backdoor Attack on Any CLIP Model With Any Target Class by Pre-Trained Hack Network	111
Quality Assessment for DIBR-Synthesized Views Based on Wavelet Transform and Gradient Magnitude Similarity	111
Asymptotics-Aware Multi-View Subspace Clustering	110
Structured Graph Reasoning for Traffic Anomaly Detection	108
Self-Guided Discriminative Locality Preserving Projections	107
Vulnerability of Feature Extractors in 2D Image-Based 3D Object Retrieval	105
Dynamic Mosaics: Saliency-Guided Adaptive Masking for Occluded Person Re-Identification	104
MGKsite: Multi-Modal Knowledge-Driven Site Selection via Intra and Inter-Modal Graph Fusion	104
Beyond Simple Extraction: Unleashing the Potential of Encoder Interaction in Few-Shot Segmentation	103
Interpretable Graph Convolutional Network for Multi-View Semi-Supervised Learning	102
GLCT: A Novel Global-Local Constraint for Unpaired Image-to-Image Translation	100
TFBF: Temporal-Frequency Bidirectional Fusion for Action Quality Assessment	100
Outliers Adaptation Exploration and Centroids Matching Label Refinement for Unsupervised Person Re-Identification	100
Cross-modal Semantic Relevance is An Efficient Gatekeeper for Audio-Visual Video Parsing	98
SkyML: A MLaaS Federation Design for Multicloud-Based Multimedia Analytics	98
ICE: Interactive 3D Game Character Facial Editing via Dialogue	97
Ensemble Prototype Networks for Unsupervised Cross-Modal Hashing With Cross-Task Consistency	96
Siamese Alignment Network for Weakly Supervised Video Moment Retrieval	96
MVPC-CLIP: Multi-Granularity Visual Prompt Co-Operative for Aerial Video Recognition	96
Anomaly-Led Prompting Learning Caption Generating Model and Benchmark	96
Distilling Multi-View Diffusion Models Into 3D Generators	94
Skeleton-Based Action Recognition With Select-Assemble-Normalize Graph Convolutional Networks	94
Adversarial 3D-to-Real Watermarking: Revealing Invisible Messages Hidden in Complexly Distorted Surfaces	93
BASNet: Boundary Assisted Network for Image Splicing Forgery Detection	91
Scale Up Composed Image Retrieval Learning via Modification Text Generation	91
Pixel Bleach Network for Detecting Face Forgery Under Compression	90
Self-Mining the Confident Prototypes for Source-Free Unsupervised Domain Adaptation in Image Segmentation	90

3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement	88
$\rm {M}^{2}\rm {C-EvDet}$: Multi-Domain Multi-Order Cross-Modal Knowledge Distillation for Event-based Object Detection	88
Progressive Local Filter Pruning for Image Retrieval Acceleration	87
XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework	86
Disentangled Graph Variational Auto-Encoder for Multimodal Recommendation With Interpretability	85
Semi-Supervised Domain Adaptation for Major Depressive Disorder Detection	84
Feature First: Advancing Image-Text Retrieval Through Improved Visual Features	83
Dynamic Contrastive Distillation for Image-Text Retrieval	83