{"total":13,"rows":[{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170,"area":null},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97,"area":null},{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"area":null},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33,"area":null},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2210.07055","title":"Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors","created":"2022-10-13","cited_by_count":26,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2104.10116","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2310.05304","title":"GestSync: Determining who is speaking without a talking head","created":"2023-10-08","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":"2609.07893","title":"Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal Data","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}