VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer
Abstract
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/examples/MMPT.- Anthology ID:
- 2021.emnlp-main.544
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6787–6800
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.544
- DOI:
- 10.18653/v1/2021.emnlp-main.544
- Cite (ACL):
- Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, and Christoph Feichtenhofer. 2021. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6787–6800, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding (Xu et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.544.pdf
- Code
- pytorch/fairseq + additional community code
- Data
- COIN, CrossTask, DiDeMo, HowTo100M, MSR-VTT, YouCook2