We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn fundamental vision-language concepts, and then adapted to video data in an intermediate video-text pre-training stage to learn video-specific skills such as spatio-temporal reasoning. As a result, our VideoOFA model achieves new state-of-the-art performance on four Video Captioning benchmarks, beating prior art by an average of 9.7 points in CIDEr score. It also outperforms existing models on two open-ended Video Question Answering datasets, showcasing its generalization capability as a universal video-to-text model.
@article{arxiv.2305.03204,
title = {VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation},
author = {Xilun Chen and Lili Yu and Wenhan Xiong and Barlas Oğuz and Yashar Mehdad and Wen-tau Yih},
journal= {arXiv preprint arXiv:2305.03204},
year = {2023}
}