Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.00824 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914524949381120 |
|---|---|
| author | Qin, Yawen Qiu, Ke Zhang, Qin |
| author_facet | Qin, Yawen Qiu, Ke Zhang, Qin |
| contents | Dance serves as both a cultural cornerstone and a medium for personal expression, yet the rapid growth of online dance content has made personalized discovery increasingly difficult. Text-based dance retrieval offers a natural interface for users to search with choreographic intent, but it remains underexplored because dance requires simultaneous reasoning over linguistic semantics, musical rhythm, and full-body motion dynamics. We introduce TD-Data, a large-scale open dataset for text-dance retrieval, containing about 4,000 12-second dance clips, 14.6 hours of motion, 22 genres, and annotations from professional dance experts. On top of this dataset, we propose CustomDancer, a multimodal retrieval framework that aligns text with dance through a CLIP-based text encoder, music and motion encoders, and a music-motion blending module. CustomDancer achieves state-of-the-art performance on TD-Data, reaching 10.23% Recall@1 and improving retrieval quality in both quantitative benchmarks and user preference studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00824 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CustomDancer: Customized Dance Recommendation by Text-Dance Retrieval Qin, Yawen Qiu, Ke Zhang, Qin Multimedia Dance serves as both a cultural cornerstone and a medium for personal expression, yet the rapid growth of online dance content has made personalized discovery increasingly difficult. Text-based dance retrieval offers a natural interface for users to search with choreographic intent, but it remains underexplored because dance requires simultaneous reasoning over linguistic semantics, musical rhythm, and full-body motion dynamics. We introduce TD-Data, a large-scale open dataset for text-dance retrieval, containing about 4,000 12-second dance clips, 14.6 hours of motion, 22 genres, and annotations from professional dance experts. On top of this dataset, we propose CustomDancer, a multimodal retrieval framework that aligns text with dance through a CLIP-based text encoder, music and motion encoders, and a music-motion blending module. CustomDancer achieves state-of-the-art performance on TD-Data, reaching 10.23% Recall@1 and improving retrieval quality in both quantitative benchmarks and user preference studies. |
| title | CustomDancer: Customized Dance Recommendation by Text-Dance Retrieval |
| topic | Multimedia |
| url | https://arxiv.org/abs/2605.00824 |