OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Multimedia is 63. 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 2021-06-01 to 2025-06-01.)

Article	Citations
AMS-Net: Adaptive Multi-Scale Network for Image Compressive Sensing	545
Self-Mining the Confident Prototypes for Source-Free Unsupervised Domain Adaptation in Image Segmentation	305
Focusing on Subtle Differences: A Feature Disentanglement Model for Series Photo Selection	282
Semantic-Aware Triplet Loss for Image Classification	213
Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations	206
Optimal Transport-Based Patch Matching for Image Style Transfer	198
Adaptive Weight Generator for Multi-Task Image Recognition by Task Grouping Prompt	183
Semi-Supervised Domain Adaptation via Joint Transductive and Inductive Subspace Learning	177
Improving Pre-Trained Model-Based Speech Emotion Recognition From a Low-Level Speech Feature Perspective	158
Perceptual Image Hashing Using Feature Fusion of Orthogonal Moments	149
Rethinking Video Sentence Grounding From a Tracking Perspective With Memory Network and Masked Attention	149
Disaggregation Distillation for Person Search	139
Multi-Level Transitional Contrast Learning for Personalized Image Aesthetics Assessment	133
Guided Image-to-Image Translation by Discriminator-Generator Communication	123
Online Low-Light Sand-Dust Video Enhancement Using Adaptive Dynamic Brightness Correction and a Rolling Guidance Filter	121
One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing	118
SGG-Nets: Generic Rotation-Invariant Plugin Networks for Point Cloud Analysis	109
Feature First: Advancing Image-Text Retrieval Through Improved Visual Features	105
Improving Vision Anomaly Detection With the Guidance of Language Modality	105
Ensemble Prototype Networks for Unsupervised Cross-modal Hashing with Cross-Task Consistency	103
BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised Learning	103
Asymptotics-Aware Multi-View Subspace Clustering	102
MGKsite: Multi-Modal Knowledge-Driven Site Selection via Intra and Inter-Modal Graph Fusion	101
Neighborhood Contrastive Transformer for Change Captioning	101
Disentangled Graph Variational Auto-Encoder for Multimodal Recommendation With Interpretability	99

Few-Shot Generative Model Adaptation via Style-Guided Prompt	99
SCSP: An Unsupervised Image-to-Image Translation Network Based on Semantic Cooperative Shape Perception	98
MHRN: A Multimodal Hierarchical Reasoning Network for Topic Detection	98
Towards Fast and Robust Real Image Denoising With Attentive Neural Network and PID Controller	97
Skeleton-Based Action Recognition With Select-Assemble-Normalize Graph Convolutional Networks	95
Pixel Bleach Network for Detecting Face Forgery Under Compression	94
Semi-Supervised Contrastive Learning With Similarity Co-Calibration	90
Bias-Correction Feature Learner for Semi-Supervised Instance Segmentation	88
Dynamic Contrastive Distillation for Image-Text Retrieval	87
Rethinking Affine Transform for Efficient Image Enhancement: A Color Space Perspective	83
Siamese Alignment Network for Weakly Supervised Video Moment Retrieval	83
Vulnerability of Feature Extractors in 2D Image-Based 3D Object Retrieval	81
Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames	81
Dual-task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding	80
Exploring Kernel Transformations for Implicit Neural Representations	79
Deep Semantic-consistent Penalizing Hashing for Cross-modal Retrieval	78
Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition	76
Unsupervised Learning-Based Framework for Deepfake Video Detection	74
SkyML: A MLaaS Federation Design for Multicloud-Based Multimedia Analytics	74
Annealing Genetic GAN for Imbalanced Web Data Learning	73
Quality Assessment for DIBR-Synthesized Views Based on Wavelet Transform and Gradient Magnitude Similarity	73
Adaptive HEVC Video Steganography With High Performance Based on Attention-Net and PU Partition Modes	73
Progressive Local Filter Pruning for Image Retrieval Acceleration	73
Bidirectional Translation Between UHD-HDR and HD-SDR Videos	72
FoodSAM: Any Food Segmentation	70
Hierarchical Equalization Loss for Long-Tailed Instance Segmentation	69
A Total Variation With Joint Norms For Infrared and Visible Image Fusion	69
ICE: Interactive 3D Game Character Facial Editing via Dialogue	68
A Comprehensive Study on Deep Learning-Based Methods for Sign Language Recognition	68
Structured Attention Network for Referring Image Segmentation	68
Semi-Supervised Domain Adaptation for Major Depressive Disorder Detection	67
Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization	67
Interpretable Graph Convolutional Network for Multi-View Semi-Supervised Learning	66
Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes	65
PhotoHelper: Portrait Photographing Guidance Via Deep Feature Retrieval and Fusion	65
DREAMT: Diversity Enlarged Mutual Teaching for Unsupervised Domain Adaptive Person Re-Identification	64
Cps-STS: Bridging the Gap Between Content and Position for Coarse-Point-Supervised Scene Text Spotter	64
Unsupervised Image and Text Fusion for Travel Information Enhancement	63
EPM-Net: Efficient Feature Extraction, Point-Pair Feature Matching for Robust 6-D Pose Estimation	63