# NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022

arXiv: https://arxiv.org/abs/2206.10869 · HTML: https://mlsanity.com/paper/2206.10869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 22 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients](https://mlsanity.com/paper/2010.07468/) (2020)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)
- [Convolutional Tensor-Train LSTM for Spatio-temporal Learning](https://mlsanity.com/paper/2002.09131/) (2020)
- [Long-term Forecasting using Higher Order Tensor RNNs](https://mlsanity.com/paper/1711.00073/) (2017)
- [Unified Recurrence Modeling for Video Action Anticipation](https://mlsanity.com/paper/2206.01009/) (2022)
- [Higher Order Recurrent Space-Time Transformer for Video Action Prediction](https://mlsanity.com/paper/2104.08665/) (2021)

## Built on by (most cited first, 2 of 2)

- [TIM: A Time Interval Machine for Audio-Visual Action Recognition](https://mlsanity.com/paper/2404.05559/) (2024)
- [G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding](https://mlsanity.com/paper/2608.20157/) (2026)

## Abstract (arXiv)

In this report, we describe the technical details of our submission for the EPIC-Kitchen-100 action anticipation challenge. Our modelings, the higher-order recurrent space-time transformer and the message-passing neural network with edge learning, are both recurrent-based architectures which observe only 2.5 seconds inference context to form the action anticipation prediction. By averaging the prediction scores from a set of models compiled with our proposed training pipeline, we achieved strong performance on the test set, which is 19.61% overall mean top-5 recall, recorded as second place on the public leaderboard.