# Audio Visual Scene-Aware Dialog Generation with Transformer-based Video Representations

arXiv: https://arxiv.org/abs/2202.09979 · HTML: https://mlsanity.com/paper/2202.09979/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features](https://mlsanity.com/paper/1806.08409/) (2018)
- [BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues](https://mlsanity.com/paper/2010.10095/) (2020)
- [Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog](https://mlsanity.com/paper/2002.00163/) (2020)
- [Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning](https://mlsanity.com/paper/2110.06894/) (2021)
- [From FiLM to Video: Multi-turn Question Answering with Multi-modal Context](https://mlsanity.com/paper/1812.07023/) (2018)

## Built on by (most cited first, 4 of 4)

- [End-to-End Multimodal Representation Learning for Video Dialog](https://mlsanity.com/paper/2210.14512/) (2022)
- [MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation](https://mlsanity.com/paper/2311.12820/) (2023)
- [M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation](https://mlsanity.com/paper/2402.11875/) (2024)
- [Grounding is All You Need? Dual Temporal Grounding for Video Dialog](https://mlsanity.com/paper/2410.05767/) (2024)

## Abstract (arXiv)

There have been many attempts to build multimodal dialog systems that can respond to a question about given audio-visual information, and the representative task for such systems is the Audio Visual Scene-Aware Dialog (AVSD). Most conventional AVSD models adopt the Convolutional Neural Network (CNN)-based video feature extractor to understand visual information. While a CNN tends to obtain both temporally and spatially local information, global information is also crucial for boosting video understanding because AVSD requires long-term temporal visual dependency and whole visual information. In this study, we apply the Transformer-based video feature that can capture both temporally and spatially global representations more efficiently than the CNN-based feature. Our AVSD model with its Transformer-based feature attains higher objective performance scores for answer generation. In addition, our model achieves a subjective score close to that of human answers in DSTC10. We observed that the Transformer-based visual feature is beneficial for the AVSD task because our model tends to correctly answer the questions that need a temporally and spatially broad range of visual information.