{"total":31,"rows":[{"id":"2207.01138","title":"ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges","created":"2022-07-03","cited_by_count":110,"area":null},{"id":"2303.01498","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges","created":"2023-03-02","cited_by_count":110,"area":null},{"id":"2402.19344","title":"The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition","created":"2024-02-29","cited_by_count":78,"area":null},{"id":"2407.03835","title":"7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition","created":"2024-07-04","cited_by_count":53,"area":null},{"id":"2406.10581","title":"CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach","created":"2024-06-15","cited_by_count":38,"area":null},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"area":null},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2403.13659","title":"Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition","created":"2024-03-20","cited_by_count":15,"area":null},{"id":"2403.10488","title":"Joint Multimodal Transformer for Emotion Recognition in the Wild","created":"2024-03-15","cited_by_count":14,"area":null},{"id":"2603.15818","title":"Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2412.09402","title":"MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2503.12623","title":"MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2304.07958","title":"Recursive Joint Attention for Audio-Visual Fusion in Regression based Emotion Recognition","created":"2023-04-17","cited_by_count":6,"area":null},{"id":"2402.03658","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2310.17212","title":"Affective Video Content Analysis: Decade Review and New Perspectives","created":"2023-10-26","cited_by_count":5,"area":null},{"id":"2406.06163","title":"Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2309.16569","title":"Audio-Visual Speaker Verification via Joint Cross-Attention","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2508.12522","title":"MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2408.14441","title":"Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification","created":"2024-08-26","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":"2209.10170","title":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2405.12853","title":"Inconsistency-Aware Cross-Attention for Audio-Visual Fusion in Dimensional Emotion Recognition","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2603.11468","title":"Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2607.22729","title":"Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2404.12251","title":"Dynamic Modality and View Selection for Multimodal Emotion Recognition with Missing Modalities","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2410.08321","title":"Music Genre Classification using Large Language Models","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.13607","title":"VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2503.12261","title":"United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2609.09801","title":"Morphological Decoupling-Based Skeletal Classification for Clinical Assessment of Malocclusion","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.13687","title":"X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}