{"total":15,"rows":[{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"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":"2311.16471","title":"A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis","created":"2023-11-28","cited_by_count":12,"area":null},{"id":"2410.13267","title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2407.20445","title":"Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2312.09207","title":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2409.11498","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2411.02551","title":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2510.15543","title":"MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2309.01340","title":"MDSC: Towards Evaluating the Style Consistency Between Music and Dance","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2601.13931","title":"Towards Effective Negation Modeling in Joint Audio-Text Models for Music","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2501.01094","title":"MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2602.12301","title":"Beyond Musical Descriptors: Extracting Preference-Bearing Intent in Music Queries","created":"2026-02-11","cited_by_count":0,"area":null}],"next_cursor":null}