CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering
- 5 December 2024
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (5) , 2581-2598
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (Grant No. 62173045, 62273054)
- Fundamental Research Funds for the Central Universities (Grant No. 2020XD-A04-3)
- Natural Science Foundation of Hainan Province (Grant No. 622RC675)
This publication has 36 references indexed in Scilit:
- Extract Free Dense Labels from CLIP2022
- Learning to Prompt for Vision-Language ModelsInternational Journal of Computer Vision, 2022
- Self-supervised Learning of Audio-Visual Objects from Video2020
- Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing2020
- Describing Unseen Videos via Multi-modal Cooperative Dialog Agents2020
- Multi-modal Transformer for Video Retrieval2020
- Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering2019
- Audio-Visual Event Localization in Unconstrained Videos2018
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015