This report presents the CuriosAI team's submission to the EgoExo4D Proficiency Estimation Challenge at CVPR 2025. We propose two methods for multi-view skill assessment: (1) a multi-task learning framework using Sapiens-2B that jointly predicts proficiency and scenario labels (43.6 % accuracy), and (2) a two-stage pipeline combining zero-shot scenario recognition with view-specific VideoMAE classifiers (47.8 % accuracy). The superior performance of the two-stage approach demonstrates the effectiveness of scenario-conditioned modeling for proficiency estimation.
@article{arxiv.2507.08022,
title = {CuriosAI Submission to the EgoExo4D Proficiency Estimation Challenge 2025},
author = {Hayato Tanoue and Hiroki Nishihara and Yuma Suzuki and Takayuki Hori and Hiroki Takushima and Aiswariya Manojkumar and Yuki Shibata and Mitsuru Takeda and Fumika Beppu and Zhao Hengwei and Yuto Kanda and Daichi Yamaga},
journal= {arXiv preprint arXiv:2507.08022},
year = {2025}
}
Comments
The 2nd place solution for the EgoExo4D Proficiency Estimation Challenge at the CVPR EgoVis Workshop 2025