In this report, we present a novel three-stage framework developed for the Ego4D Long-Term Action Anticipation (LTA) task. Inspired by recent advances in foundation models, our method consists of three stages: feature extraction, action recognition, and long-term action anticipation. First, visual features are extracted using a high-performance visual encoder. The features are then fed into a Transformer to predict verbs and nouns, with a verb-noun co-occurrence matrix incorporated to enhance recognition accuracy. Finally, the predicted verb-noun pairs are formatted as textual prompts and input into a fine-tuned large language model (LLM) to anticipate future action sequences. Our framework achieves first place in this challenge at CVPR 2025, establishing a new state-of-the-art in long-term action prediction. Our code will be released at https://github.com/CorrineQiu/Ego4D-LTA-Challenge-2025.
@article{arxiv.2506.02550,
title = {Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025},
author = {Qiaohui Chu and Haoyu Zhang and Yisen Feng and Meng Liu and Weili Guan and Yaowei Wang and Liqiang Nie},
journal= {arXiv preprint arXiv:2506.02550},
year = {2025}
}
Comments
The champion solution for the Ego4D Long-Term Action Anticipation Challenge at the CVPR EgoVis Workshop 2025