VTC: Improving Video-Text Retrieval with User Comments
This work addresses the gap in multi-modal retrieval for applications like recommendation and search by leveraging user comments, though it is incremental as it builds on existing attention mechanisms.
The paper tackles the problem of video-text retrieval by incorporating user comments, which are often ignored due to their irrelevance, and introduces a new dataset and attention-based method that improves multi-modal representation learning, achieving better contextualized representations for image, video, and audio.
Multi-modal retrieval is an important problem for many applications, such as recommendation and search. Current benchmarks and even datasets are often manually constructed and consist of mostly clean samples where all modalities are well-correlated with the content. Thus, current video-text retrieval literature largely focuses on video titles or audio transcripts, while ignoring user comments, since users often tend to discuss topics only vaguely related to the video. Despite the ubiquity of user comments online, there is currently no multi-modal representation learning datasets that includes comments. In this paper, we a) introduce a new dataset of videos, titles and comments; b) present an attention-based mechanism that allows the model to learn from sometimes irrelevant data such as comments; c) show that by using comments, our method is able to learn better, more contextualised, representations for image, video and audio representations. Project page: https://unitaryai.github.io/vtc-paper.