DCA: Diversified Co-Attention towards Informative Live Video Commenting

TL;DR

This paper introduces DCA, a model that leverages diversified co-attention mechanisms to improve real-time automatic live video commenting by effectively integrating video frames and viewer comments.

Contribution

The paper proposes a novel Diversified Co-Attention model with an orthogonalization technique for better information integration in live video commenting.

Findings

Outperforms existing methods in ALVC task

Achieves state-of-the-art results

Effectively captures diverse video and comment information

Abstract

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.