OOIR: Observatory of International Research

Papers

(The H4-Index of ACM Transactions on Multimedia Computing Communications and Applicatio is 38. 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 2022-05-01 to 2026-05-01.)

Article	Citations
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation	398
Hypercube Pooling for Visual Semantic Embedding	159
Backdoor Two-Stream Video Models on Federated Learning	155
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	102
ForgeFinder: Perceptive Multimodal Deepfake Detection via Multi-grained Forgery Localization	84
Fine-Grained Text-to-Video Temporal Grounding from Coarse Boundary	80
Discriminative Action Snippet Propagation Network for Weakly Supervised Temporal Action Localization	80
Unsupervised Discovery and Manipulation of Continuous Disentangled Factors of Variation	79
Quantum Fourier Convolutional Network	75
Attentional Composition Networks for Long-Tailed Human Action Recognition	65
Semi-supervised Learning for Mars Imagery Classification and Segmentation	61
HTTP Adaptive Streaming: A Review on Current Advances and Future Challenges	59
AED-PADA: Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation	59
Enhanced Video Super-Resolution Network towards Compressed Data	59
Psychology-Guided Environment Aware Network for Discovering Social Interaction Groups from Videos	56
Towards Intelligent Attack Detection Using DNA Computing	54
Establishing Trust and Security in Decentralized Metaverse: A Web 3.0 Approach	53
CVLP-NaVD: Contrastive Visual-language Pre-training Models for Non-annotated Visual Description	51
SEADUNet: A Multilingual Ancient Document Image Binarization using EMCAM Attention Mechanism and SCP	49
Upsampling Algorithm for V-PCC-Coded 3D Point Clouds	46
QuickCSGModeling: Quick CSG Operations Based on Fusing Signed Distance Fields for VR Modeling	46
A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep Learning	45
High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers	45
JDAN: Joint Detection and Association Network for Real-Time Online Multi-Object Tracking	45

BiC-Net: Learning Efficient Spatio-temporal Relation for Text-Video Retrieval	44
Towards Generalizable Deepfake Detection by Primary Region Regularization	44
Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer	44
Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning	44
Exploring Talking Head Models with Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation	43
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-reference Metric	43
Rank-in-Rank Loss for Person Re-identification	43
Tensorial Evolutionary Optimization for Natural Image Matting	42
Infrared and Visible Image Fusion via Text-Prior Guided Frequency-Domain Decomposition	42
A Comprehensive Survey on Methods for Image Integrity	42
Joint Mixing Data Augmentation for Skeleton-Based Action Recognition	41
New Metrics and Dataset for Biological Development Video Generation	40
SNIPPET: A Framework for Subjective Evaluation of Visual Explanations Applied to DeepFake Detection	39
Immersive Multimedia Service Caching in Edge Cloud with Renewable Energy	38
(Compress and Restore) ^N : A Robust Defense Against Adversarial Attacks on Image Classification	38