Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation
This addresses the challenge of video topic segmentation for long, complex videos like livestreams, but it is incremental as it builds on existing multi-modal and domain adaptation techniques.
The paper tackled the problem of segmenting long videos with subtle semantic changes by introducing a multi-modal video topic segmenter using transcripts and frames with cross-modal attention and dual-contrastive domain adaptation. The result showed that the solution significantly surpassed baseline methods in accuracy and transferability on both short and long video corpora.
Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably insufficient. On the other hand, prior solutions for similar tasks like video scene/shot segmentation cater to short videos with clear visual shifts but falter for long videos with subtle changes, such as livestreams. In this paper, we introduce a multi-modal video topic segmenter that utilizes both video transcripts and frames, bolstered by a cross-modal attention mechanism. Furthermore, we propose a dual-contrastive learning framework adhering to the unsupervised domain adaptation paradigm, enhancing our model's adaptability to longer, more semantically complex videos. Experiments on short and long video corpora demonstrate that our proposed solution, significantly surpasses baseline methods in terms of both accuracy and transferability, in both intra- and cross-domain settings.