# TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021

arXiv: https://arxiv.org/abs/2107.13259 · HTML: https://mlsanity.com/paper/2107.13259/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)

## Built on by (most cited first, 6 of 6)

- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [Interaction Region Visual Transformer for Egocentric Action Anticipation](https://mlsanity.com/paper/2211.14154/) (2022)
- [Predicting the Next Action by Modeling the Abstract Goal](https://mlsanity.com/paper/2209.05044/) (2022)
- [Human Action Anticipation: A Survey](https://mlsanity.com/paper/2410.14045/) (2024)
- [Intention Action Anticipation Model with Guide-Feedback Loop Mechanism](https://mlsanity.com/paper/2403.12450/) (2024)
- [Learning to Anticipate Future with Dynamic Context Removal](https://mlsanity.com/paper/2204.02587/) (2022)

## Abstract (arXiv)

In this report, the technical details of our submission to the EPIC-Kitchens Action Anticipation Challenge 2021 are given. We developed a hierarchical attention model for action anticipation, which leverages Transformer-based attention mechanism to aggregate features across temporal dimension, modalities, symbiotic branches respectively. In terms of Mean Top-5 Recall of action, our submission with team name ICL-SJTU achieved 13.39% for overall testing set, 10.05% for unseen subsets and 11.88% for tailed subsets. Additionally, it is noteworthy that our submission ranked 1st in terms of verb class in all three (sub)sets.