DCA: Diversified Co-Attention towards Informative Live Video Commenting
This work addresses the problem of generating informative real-time comments for live video viewers, representing an incremental improvement in a domain-specific task.
The paper tackles the challenge of leveraging diverse video and text information for Automatic Live Video Commenting (ALVC) by proposing a Diversified Co-Attention (DCA) model, which outperforms existing methods and achieves new state-of-the-art results.
We focus on the task of Automatic Live Video Commenting (ALVC), which aims to generate real-time video comments with both video frames and other viewers' comments as inputs. A major challenge in this task is how to properly leverage the rich and diverse information carried by video and text. In this paper, we aim to collect diversified information from video and text for informative comment generation. To achieve this, we propose a Diversified Co-Attention (DCA) model for this task. Our model builds bidirectional interactions between video frames and surrounding comments from multiple perspectives via metric learning, to collect a diversified and informative context for comment generation. We also propose an effective parameter orthogonalization technique to avoid excessive overlap of information learned from different perspectives. Results show that our approach outperforms existing methods in the ALVC task, achieving new state-of-the-art results.