Instance-aware Fine-grained Micro-action Recognition

摘要

Micro-action involves low-amplitude movement of human body, which brings challenges to common action recognition. This paper focuses on the extremely small region of human body as well as the severe long-tail distribution in micro-action recognition. An intuitive yet effective instance-aware data preprocessing is designed to enlarge the movement of human body and alleviate the multi-scale variant by a pretrianed human detector. Long-tail distribution brings severe data imbalance difficult to solve directly. To simplify this problem, we propose a novel coarse-grained focal loss to focus on the misclassification at coarse-grained level by introducing adaptive weights. Two-level supervision, the fine-grained and coarse-grained annotations, benefits to improve model performance further. Finally, our method achieved 3rd place and 2nd place in MAC 2024 Track 1 and Track 2 respectively, which demonstrates the effectiveness and generalization of our proposed method. Our code is available in https://github.com/ilovepose/instance-aware-fine-grained-micro-action-recognition.