# Technical Report for Ego4D Long Term Action Anticipation Challenge 2023

arXiv: https://arxiv.org/abs/2307.01467 · HTML: https://mlsanity.com/paper/2307.01467/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Builds on (most cited first, 4 of 4)

- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Video + CLIP Baseline for Ego4D Long-term Action Anticipation](https://mlsanity.com/paper/2207.00579/) (2022)

## Built on by (most cited first, 7 of 7)

- [AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?](https://mlsanity.com/paper/2307.16368/) (2023)
- [Vamos: Versatile Action Models for Video Understanding](https://mlsanity.com/paper/2311.13627/) (2023)
- [Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision](https://mlsanity.com/paper/2506.03605/) (2025)
- [Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation](https://mlsanity.com/paper/2508.01742/) (2025)
- [Vision and Intention Boost Large Language Model in Long-Term Action Anticipation](https://mlsanity.com/paper/2505.01713/) (2025)
- [Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models](https://mlsanity.com/paper/2508.00374/) (2025)
- [Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges](https://mlsanity.com/paper/2609.31665/) (2026)

## Abstract (arXiv)

In this report, we describe the technical details of our approach for the Ego4D Long-Term Action Anticipation Challenge 2023. The aim of this task is to predict a sequence of future actions that will take place at an arbitrary time or later, given an input video. To accomplish this task, we introduce three improvements to the baseline model, which consists of an encoder that generates clip-level features from the video, an aggregator that integrates multiple clip-level features, and a decoder that outputs Z future actions. 1) Model ensemble of SlowFast and SlowFast-CLIP; 2) Label smoothing to relax order constraints for future actions; 3) Constraining the prediction of the action class (verb, noun) based on word co-occurrence. Our method outperformed the baseline performance and recorded as second place solution on the public leaderboard.