Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918054407962624 |
|---|---|
| author | Chu, Qiaohui Zhang, Haoyu Feng, Yisen Liu, Meng Guan, Weili Wang, Yaowei Nie, Liqiang |
| author_facet | Chu, Qiaohui Zhang, Haoyu Feng, Yisen Liu, Meng Guan, Weili Wang, Yaowei Nie, Liqiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02550 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025 Chu, Qiaohui Zhang, Haoyu Feng, Yisen Liu, Meng Guan, Weili Wang, Yaowei Nie, Liqiang Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025 |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.02550 |