CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915762183077888 |
|---|---|
| author | Han, Gyuwon Jang, Young Kyun Eom, Chanho |
| author_facet | Han, Gyuwon Jang, Young Kyun Eom, Chanho |
| contents | Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a textual query specifying visual modifications. However, existing benchmarks consider only visual changes, ignoring videos that differ in audio despite visual similarity. To address this limitation, we introduce Composed retrieval for Video with its Audio CoVA, a new retrieval task that accounts for both visual and auditory variations. To support this, we construct AV-Comp, a benchmark consisting of video pairs with cross-modal changes and corresponding textual queries that describe the differences. We also propose AVT Compositional Fusion (AVT), which integrates video, audio, and text features by selectively aligning the query to the most relevant modality. AVT outperforms traditional unimodal fusion and serves as a strong baseline for CoVA. Examples from the proposed dataset, including both visual and auditory information, are available at https://perceptualai-lab.github.io/CoVA/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22508 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content Han, Gyuwon Jang, Young Kyun Eom, Chanho Computer Vision and Pattern Recognition Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a textual query specifying visual modifications. However, existing benchmarks consider only visual changes, ignoring videos that differ in audio despite visual similarity. To address this limitation, we introduce Composed retrieval for Video with its Audio CoVA, a new retrieval task that accounts for both visual and auditory variations. To support this, we construct AV-Comp, a benchmark consisting of video pairs with cross-modal changes and corresponding textual queries that describe the differences. We also propose AVT Compositional Fusion (AVT), which integrates video, audio, and text features by selectively aligning the query to the most relevant modality. AVT outperforms traditional unimodal fusion and serves as a strong baseline for CoVA. Examples from the proposed dataset, including both visual and auditory information, are available at https://perceptualai-lab.github.io/CoVA/. |
| title | CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.22508 |