First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910615099932672 |
|---|---|
| author | Peng, Yingzhe Yuan, Yixiao Ao, Zitian Zhou, Huapeng Wang, Kangqi Zhu, Qipeng Yang, Xu |
| author_facet | Peng, Yingzhe Yuan, Yixiao Ao, Zitian Zhou, Huapeng Wang, Kangqi Zhu, Qipeng Yang, Xu |
| contents | In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13538 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge Peng, Yingzhe Yuan, Yixiao Ao, Zitian Zhou, Huapeng Wang, Kangqi Zhu, Qipeng Yang, Xu Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard. |
| title | First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.13538 |