{"total":16,"rows":[{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48,"area":null},{"id":"2412.14719","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","created":"2024-12-19","cited_by_count":22,"area":null},{"id":"2407.05311","title":"MMAD: Multi-label Micro-Action Detection in Videos","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2308.01526","title":"Data Augmentation for Human Behavior Analysis in Multi-Person Conversations","created":"2023-08-03","cited_by_count":15,"area":null},{"id":"2507.08344","title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2507.21977","title":"Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition","created":"2025-07-29","cited_by_count":11,"area":null},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9,"area":null},{"id":"2410.08470","title":"DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2212.03968","title":"Multimodal Vision Transformers with Forced Attention for Behavior Analysis","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2308.08256","title":"MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions","created":"2023-08-16","cited_by_count":3,"area":null},{"id":"2408.04420","title":"Recognizing Emotion Regulation Strategies from Human Behavior with Large Language Models","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2604.09715","title":"MuPPet: Multi-person 2D-to-3D Pose Lifting","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2309.10765","title":"MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2409.20270","title":"Loose Social-Interaction Recognition in Real-world Therapy Scenarios","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2501.03332","title":"CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets","created":"2025-01-06","cited_by_count":0,"area":null}],"next_cursor":null}