# VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation Source: [VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:17:36.551Z Authors: Xilun Chen, Lili Yu, Wenhan Xiong, Barlas O\\u{g}uz, Yashar Mehdad, Wen-tau Yih Published: 2023-05-04T23:27:21.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Video Question Answering on MSRVTT-QA (test)](): Video Question Answering; MSRVTT-QA (test); Accuracy: 45.4. ## Original sources and implementation [Original paper]() [PDF]()