{"total":15,"rows":[{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2211.03434","title":"Complete Cross-triplet Loss in Label Space for Audio-visual Cross-modal Retrieval","created":"2022-11-07","cited_by_count":6,"area":null},{"id":"2503.08147","title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2310.13451","title":"Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2404.13789","title":"Anchor-aware Deep Metric Learning for Audio-visual Retrieval","created":"2024-04-21","cited_by_count":4,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2306.07187","title":"Video-to-Music Recommendation using Temporal Alignment of Segments","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2407.19415","title":"Start from Video-Music Retrieval: An Inter-Intra Modal Loss for Cross Modal Retrieval","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2601.11995","title":"Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2303.12379","title":"VMCML: Video and Music Matching via Cross-Modality Lifting","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2604.04229","title":"Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning","created":"2026-04-05","cited_by_count":0,"area":null}],"next_cursor":null}