{"total":15,"rows":[{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29,"area":null},{"id":"2210.09138","title":"An Open-source Benchmark of Deep Learning Models for Audio-visual Apparent and Self-reported Personality Recognition","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2306.01656","title":"Backchannel Detection and Agreement Estimation from Video with Transformer Networks","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2110.13570","title":"Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition","created":"2021-10-26","cited_by_count":5,"area":null},{"id":"2112.01177","title":"MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention","created":"2021-12-02","cited_by_count":5,"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":"2306.02548","title":"Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2304.12204","title":"Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2305.12369","title":"HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2606.30543","title":"TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech","created":"2026-06-29","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":"2506.13971","title":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2508.00205","title":"Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}