OOIR: Observatory of International Research

Papers

(The H4-Index of ACM Transactions on Multimedia Computing Communications and Applicatio is 39. 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 2022-06-01 to 2026-06-01.)

Article	Citations
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation	438
Hypercube Pooling for Visual Semantic Embedding	161
Backdoor Two-Stream Video Models on Federated Learning	158
Self-Adaptive Representation Learning Model for Multi-Modal Sentiment and Sarcasm Joint Analysis	117
Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image	104
ForgeFinder: Perceptive Multimodal Deepfake Detection via Multi-grained Forgery Localization	85
Discriminative Action Snippet Propagation Network for Weakly Supervised Temporal Action Localization	84
Fine-Grained Text-to-Video Temporal Grounding from Coarse Boundary	84
Unsupervised Discovery and Manipulation of Continuous Disentangled Factors of Variation	82
Semi-supervised Learning for Mars Imagery Classification and Segmentation	78
AED-PADA: Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation	67
HTTP Adaptive Streaming: A Review on Current Advances and Future Challenges	63
Enhanced Video Super-Resolution Network towards Compressed Data	62
Psychology-Guided Environment Aware Network for Discovering Social Interaction Groups from Videos	61
Towards Intelligent Attack Detection Using DNA Computing	59
Establishing Trust and Security in Decentralized Metaverse: A Web 3.0 Approach	57
CVLP-NaVD: Contrastive Visual-language Pre-training Models for Non-annotated Visual Description	55
SEADUNet: A Multilingual Ancient Document Image Binarization using EMCAM Attention Mechanism and SCP	53
QuickCSGModeling: Quick CSG Operations Based on Fusing Signed Distance Fields for VR Modeling	52
Upsampling Algorithm for V-PCC-Coded 3D Point Clouds	52
A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep Learning	51
Tensorial Evolutionary Optimization for Natural Image Matting	49
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-reference Metric	48
Exploring Talking Head Models with Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation	47
Infrared and Visible Image Fusion via Text-Prior Guided Frequency-Domain Decomposition	47

JDAN: Joint Detection and Association Network for Real-Time Online Multi-Object Tracking	46
Quantum Fourier Convolutional Network	46
High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers	46
Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning	45
Towards Generalizable Deepfake Detection by Primary Region Regularization	45
BiC-Net: Learning Efficient Spatio-temporal Relation for Text-Video Retrieval	44
Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer	44
Rank-in-Rank Loss for Person Re-identification	43
Attentional Composition Networks for Long-Tailed Human Action Recognition	42
A Comprehensive Survey on Methods for Image Integrity	42
Joint Mixing Data Augmentation for Skeleton-Based Action Recognition	42
New Metrics and Dataset for Biological Development Video Generation	42
Immersive Multimedia Service Caching in Edge Cloud with Renewable Energy	41
SNIPPET: A Framework for Subjective Evaluation of Visual Explanations Applied to DeepFake Detection	41