Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiahang, Lin, Lilang, Liu, Jiaying
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913434355892224
author Zhang, Jiahang
Lin, Lilang
Liu, Jiaying
author_facet Zhang, Jiahang
Lin, Lilang
Liu, Jiaying
contents In real-world scenarios, human actions often fall into a long-tailed distribution. It makes the existing skeleton-based action recognition works, which are mostly designed based on balanced datasets, suffer from a sharp performance degradation. Recently, many efforts have been madeto image/video long-tailed learning. However, directly applying them to skeleton data can be sub-optimal due to the lack of consideration of the crucial spatial-temporal motion patterns, especially for some modality-specific methodologies such as data augmentation. To this end, considering the crucial role of the body parts in the spatially concentrated human actions, we attend to the mixing augmentations and propose a novel method, Shap-Mix, which improves long-tailed learning by mining representative motion patterns for tail categories. Specifically, we first develop an effective spatial-temporal mixing strategy for the skeleton to boost representation quality. Then, the employed saliency guidance method is presented, consisting of the saliency estimation based on Shapley value and a tail-aware mixing policy. It preserves the salient motion parts of minority classes in mixed data, explicitly establishing the relationships between crucial body structure cues and high-level semantics. Extensive experiments on three large-scale skeleton datasets show our remarkable performance improvement under both long-tailed and balanced settings. Our project is publicly available at: https://jhang2020.github.io/Projects/Shap-Mix/Shap-Mix.html.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12312
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
Zhang, Jiahang
Lin, Lilang
Liu, Jiaying
Computer Vision and Pattern Recognition
In real-world scenarios, human actions often fall into a long-tailed distribution. It makes the existing skeleton-based action recognition works, which are mostly designed based on balanced datasets, suffer from a sharp performance degradation. Recently, many efforts have been madeto image/video long-tailed learning. However, directly applying them to skeleton data can be sub-optimal due to the lack of consideration of the crucial spatial-temporal motion patterns, especially for some modality-specific methodologies such as data augmentation. To this end, considering the crucial role of the body parts in the spatially concentrated human actions, we attend to the mixing augmentations and propose a novel method, Shap-Mix, which improves long-tailed learning by mining representative motion patterns for tail categories. Specifically, we first develop an effective spatial-temporal mixing strategy for the skeleton to boost representation quality. Then, the employed saliency guidance method is presented, consisting of the saliency estimation based on Shapley value and a tail-aware mixing policy. It preserves the salient motion parts of minority classes in mixed data, explicitly establishing the relationships between crucial body structure cues and high-level semantics. Extensive experiments on three large-scale skeleton datasets show our remarkable performance improvement under both long-tailed and balanced settings. Our project is publicly available at: https://jhang2020.github.io/Projects/Shap-Mix/Shap-Mix.html.
title Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.12312