{"total":22,"rows":[{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2508.07959","title":"Large Language Models for Subjective Language Understanding: A Survey","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2601.16449","title":"Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2505.17090","title":"EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2512.06447","title":"Towards Stable Cross-Domain Depression Recognition under Missing Modalities","created":"2025-12-06","cited_by_count":3,"area":null},{"id":"2604.11730","title":"Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2602.00171","title":"Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervals","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.05496","title":"XEmoGPT: An Explainable Multimodal Emotion Recognition Framework with Cue-Level Perception and Reasoning","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2507.21015","title":"Learning Transferable Facial Emotion Representations from Large-Scale Semantically Rich Captions","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.21633","title":"Semantic F1 Scores: Fair Evaluation Under Fuzzy Class Boundaries","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2601.15906","title":"Understanding Affective Adaptation in Multimodal Foundation Models: Emergent Functional Specialization","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2603.10043","title":"AMB-DSGDN: Adaptive Modality-Balanced Dynamic Semantic Graph Differential Network for Multimodal Emotion Recognition","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2605.05640","title":"AffectSeek: Agentic Affective Understanding in Long Videos under Vague User Queries","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.28649","title":"COSI-Lab: Conference Living Lab for Modeling Multi-Perspective Multimodal Social Intention","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.21371","title":"RobotEQ-Video: A Video-Centric Benchmark for Social Proactive Intelligence with World-State Taxonomy","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.32804","title":"Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36563","title":"AffectReveal: Event-Grounded Emotion Recognition Beyond Visual Appearances","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18455","title":"EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}