# DCA: Diversified Co-Attention towards Informative Live Video Commenting

arXiv: https://arxiv.org/abs/1911.02739 · HTML: https://mlsanity.com/paper/1911.02739/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models](https://mlsanity.com/paper/2311.17404/) (2023)
- [TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding](https://mlsanity.com/paper/2310.19060/) (2023)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Learning Relation Alignment for Calibrated Cross-modal Retrieval](https://mlsanity.com/paper/2105.13868/) (2021)
- [Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting](https://mlsanity.com/paper/2404.12782/) (2024)
- [A Unified Encoder-Decoder Framework with Entity Memory](https://mlsanity.com/paper/2210.03273/) (2022)
- [Knowledge Enhanced Model for Live Video Comment Generation](https://mlsanity.com/paper/2304.14657/) (2023)
- [Semantic Frame Aggregation-based Transformer for Live Video Comment Generation](https://mlsanity.com/paper/2510.26978/) (2025)

## Abstract (arXiv)

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.