AVCaps: An Audio-Visual Dataset With Modality-Specific Captions
This paper introduces AVCaps, an audio-visual dataset that contains separate textual captions for the audio, visual, and audio-visual contents of video clips. The dataset contains 2061 video clips constituting a total of 28.8 hours. We provide up to 5 captions for the audio, visual, and audio-visual...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Signal Processing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11029114/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
