# SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021

arXiv: https://arxiv.org/abs/2110.02902 · HTML: https://mlsanity.com/paper/2110.02902/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 4 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 3 of 3)

- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Space-time Mixing Attention for Video Transformer](https://mlsanity.com/paper/2106.05968/) (2021)
- [Gate-Shift Networks for Video Action Recognition](https://mlsanity.com/paper/1912.00381/) (2019)

## Built on by (most cited first, 3 of 3)

- [TIM: A Time Interval Machine for Audio-Visual Action Recognition](https://mlsanity.com/paper/2404.05559/) (2024)
- [LEAP: LLM-Generation of Egocentric Action Programs](https://mlsanity.com/paper/2312.00055/) (2023)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)

## Abstract (arXiv)

This report presents the technical details of our submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021. To participate in the challenge we deployed spatio-temporal feature extraction and aggregation models we have developed recently: GSF and XViT. GSF is an efficient spatio-temporal feature extracting module that can be plugged into 2D CNNs for video action recognition. XViT is a convolution free video feature extractor based on transformer architecture. We design an ensemble of GSF and XViT model families with different backbones and pretraining to generate the prediction scores. Our submission, visible on the public leaderboard, achieved a top-1 action recognition accuracy of 44.82%, using only RGB.