OOIR: Observatory of International Research

Papers

(The H4-Index of ACM Transactions on Multimedia Computing Communications and Applicatio is 36. 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 2022-01-01 to 2026-01-01.)

Article	Citations
Upsampling Algorithm for V-PCC-Coded 3D Point Clouds	352
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation	186
QuickCSGModeling: Quick CSG Operations Based on Fusing Signed Distance Fields for VR Modeling	184
Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning	143
Hypercube Pooling for Visual Semantic Embedding	136
Tensorial Evolutionary Optimization for Natural Image Matting	122
Backdoor Two-Stream Video Models on Federated Learning	98
Attentional Composition Networks for Long-Tailed Human Action Recognition	97
Facial-expression-aware Emotional Color Transfer Based on Convolutional Neural Network	92
Fine-Grained Text-to-Video Temporal Grounding from Coarse Boundary	90
Unsupervised Discovery and Manipulation of Continuous Disentangled Factors of Variation	76
Discriminative Action Snippet Propagation Network for Weakly Supervised Temporal Action Localization	74
Image-Based Personality Questionnaire Design	71
Quantum Fourier Convolutional Network	70
Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer	67
Self-Adaptive Representation Learning Model for Multi-Modal Sentiment and Sarcasm Joint Analysis	66
Towards Generalizable Deepfake Detection by Primary Region Regularization	61
Semi-supervised Learning for Mars Imagery Classification and Segmentation	60
HTTP Adaptive Streaming: A Review on Current Advances and Future Challenges	59
CVLP-NaVD: Contrastive Visual-language Pre-training Models for Non-annotated Visual Description	55
Rank-in-Rank Loss for Person Re-identification	53
ForgeFinder: Perceptive Multimodal Deepfake Detection via Multi-grained Forgery Localization	53
High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers	48
AED-PADA: Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation	47
BiC-Net: Learning Efficient Spatio-temporal Relation for Text-Video Retrieval	45

Infrared and Visible Image Fusion via Text-Prior Guided Frequency-Domain Decomposition	44
A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep Learning	43
Joint Mixing Data Augmentation for Skeleton-Based Action Recognition	42
Towards Intelligent Attack Detection Using DNA Computing	42
Enhanced Video Super-Resolution Network towards Compressed Data	42
A Comprehensive Survey on Methods for Image Integrity	42
Establishing Trust and Security in Decentralized Metaverse: A Web 3.0 Approach	40
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-reference Metric	40
Psychology-Guided Environment Aware Network for Discovering Social Interaction Groups from Videos	39
Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image	36
JDAN: Joint Detection and Association Network for Real-Time Online Multi-Object Tracking	36