OOIR: Observatory of International Research

Papers

(The H4-Index of ACM Transactions on Multimedia Computing Communications and Applicatio is 40. 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
Hypercube Pooling for Visual Semantic Embedding	554
Self-Adaptive Representation Learning Model for Multi-Modal Sentiment and Sarcasm Joint Analysis	175
Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image	173
ForgeFinder: Perceptive Multimodal Deepfake Detection via Multi-grained Forgery Localization	127
Discriminative Action Snippet Propagation Network for Weakly Supervised Temporal Action Localization	113
Fine-Grained Text-to-Video Temporal Grounding from Coarse Boundary	91
Unsupervised Discovery and Manipulation of Continuous Disentangled Factors of Variation	87
AED-PADA: Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation	86
Semi-supervised Learning for Mars Imagery Classification and Segmentation	86
Enhanced Video Super-Resolution Network towards Compressed Data	77
Towards Intelligent Attack Detection Using DNA Computing	70
Psychology-Guided Environment Aware Network for Discovering Social Interaction Groups from Videos	70
Establishing Trust and Security in Decentralized Metaverse: A Web 3.0 Approach	69
CVLP-NaVD: Contrastive Visual-language Pre-training Models for Non-annotated Visual Description	64
Upsampling Algorithm for V-PCC-Coded 3D Point Clouds	61
A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep Learning	59
QuickCSGModeling: Quick CSG Operations Based on Fusing Signed Distance Fields for VR Modeling	59
Tensorial Evolutionary Optimization for Natural Image Matting	57
Exploring Talking Head Models with Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation	56
High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers	55
JDAN: Joint Detection and Association Network for Real-Time Online Multi-Object Tracking	55
Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning	52
Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer	52
A Comprehensive Survey on Methods for Image Integrity	51
Attentional Composition Networks for Long-Tailed Human Action Recognition	51

Backdoor Two-Stream Video Models on Federated Learning	49
Towards Generalizable Deepfake Detection by Primary Region Regularization	48
Disentangled Multimodal Tuning and Interaction for Human Perception Understanding	48
LAM-MD: A Large Action Model Integrated Multi-Agent Reinforcement Learning Framework for NOMA Networks	48
BiC-Net: Learning Efficient Spatio-temporal Relation for Text-Video Retrieval	47
Infrared and Visible Image Fusion via Text-Prior Guided Frequency-Domain Decomposition	47
SEADUNet: A Multilingual Ancient Document Image Binarization using EMCAM Attention Mechanism and SCP	47
Quantum Fourier Convolutional Network	47
Joint Mixing Data Augmentation for Skeleton-Based Action Recognition	44
Seeing in the Dark with Ambient Guidance	44
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation	44
HTTP Adaptive Streaming: A Review on Current Advances and Future Challenges	43
A novel image hashing with visual and structural feature maps for content authentication	43
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-reference Metric	42
New Metrics and Dataset for Biological Development Video Generation	41
Expanding-Window Zigzag Decodable Fountain Codes for Scalable Multimedia Transmission	40
Visual-linguistic-stylistic Triple Reward for Cross-lingual Image Captioning	40