{"total":14,"rows":[{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2505.01237","title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","created":"2025-05-02","cited_by_count":16,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2411.02236","title":"3D Audio-Visual Segmentation","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2604.11579","title":"Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2412.01488","title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2506.13897","title":"DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2606.27307","title":"See & Sniff: Learning Visuo-Olfactory Representations","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2507.22008","title":"VeS: Teaching Pixels to Listen Without Supervision","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.21761","title":"Learning from Silence and Noise for Visual Sound Source Localization","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.02313","title":"Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2604.08147","title":"Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2607.24786","title":"Unlocking Spatial Grounding in Large Audio-Visual Retrieval models","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}