Video Question Answering with Iterative Video-Text Co-Tokenization
This work addresses the problem of efficient and accurate video understanding for AI applications, representing a strong incremental improvement with specific gains.
The paper tackles video question answering by proposing a multi-stream video encoder with iterative video-text co-tokenization, achieving state-of-the-art results on datasets like MSRVTT-QA and reducing computational cost from 150-360 GFLOPs to 67 GFLOPs.
Video question answering is a challenging task that requires understanding jointly the language input, the visual information in individual video frames, as well as the temporal information about the events occurring in the video. In this paper, we propose a novel multi-stream video encoder for video question answering that uses multiple video inputs and a new video-text iterative co-tokenization approach to answer a variety of questions related to videos. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA, outperforming the previous state-of-the-art by large margins. Simultaneously, our model reduces the required GFLOPs from 150-360 to only 67, producing a highly efficient video question answering model.