{"total":23,"rows":[{"id":"2412.10749","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","created":"2024-12-14","cited_by_count":13,"area":null},{"id":"2412.11248","title":"Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing","created":"2024-12-15","cited_by_count":13,"area":null},{"id":"2412.12628","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","created":"2024-12-17","cited_by_count":12,"area":null},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2511.17890","title":"Decoupled Audio-Visual Dataset Distillation","created":"2025-11-22","cited_by_count":7,"area":null},{"id":"2508.04566","title":"CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization","created":"2025-08-06","cited_by_count":6,"area":null},{"id":"2509.17537","title":"SimToken: A Simple Baseline for Referring Audio-Visual Segmentation","created":"2025-09-22","cited_by_count":6,"area":null},{"id":"2512.24731","title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","created":"2025-12-31","cited_by_count":6,"area":null},{"id":"2505.23155","title":"PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2512.00115","title":"MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2601.08876","title":"The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.03892","title":"Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2507.09945","title":"ESG-Net: Event-Aware Semantic Guided Network for Dense Audio-Visual Event Localization","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.09525","title":"Learning Spatial Decay for Vision Transformers","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2603.14750","title":"Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.07033","title":"Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2511.16225","title":"Real-Time Inference for Distributed Multimodal Systems under Communication Delay Uncertainty","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.08309","title":"CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.08723","title":"EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11572","title":"TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.03264","title":"Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07923","title":"SCoPE: Training-Free Audio-Visual Event Perception via Sparse Cross-Modal Prior Exchange","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.22337","title":"Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}