{"total":21,"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":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2304.06275","title":"Noisy Correspondence Learning with Meta Similarity Correction","created":"2023-04-13","cited_by_count":26,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"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":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2206.13390","title":"A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!","created":"2022-06-20","cited_by_count":9,"area":null},{"id":"2208.14114","title":"Robust Sound-Guided Image Manipulation","created":"2022-08-30","cited_by_count":7,"area":null},{"id":"2110.13412","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2511.08263","title":"ImagebindDC: Compressing Multi-modal Data with Imagebind-based Condensation","created":"2025-11-11","cited_by_count":4,"area":null},{"id":"2210.00434","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2306.10684","title":"Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2309.07606","title":"Zero-shot Audio Topic Reranking using Large Language Models","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2207.09732","title":"Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval","created":"2022-07-20","cited_by_count":1,"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":"2409.11729","title":"DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information","created":"2024-09-18","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":"2210.08389","title":"Semantic Video Moments Retrieval at Scale: A New Task and a Baseline","created":"2022-10-15","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}],"next_cursor":null}