Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Yuchen, Wang, Wei, Liu, Yifei, Dong, Linfeng, Wu, Hao, Zhang, Mingxin, Zhong, Zhihang, Sun, Xiao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.06522
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912265868935168
author Yang, Yuchen
Wang, Wei
Liu, Yifei
Dong, Linfeng
Wu, Hao
Zhang, Mingxin
Zhong, Zhihang
Sun, Xiao
author_facet Yang, Yuchen
Wang, Wei
Liu, Yifei
Dong, Linfeng
Wu, Hao
Zhang, Mingxin
Zhong, Zhihang
Sun, Xiao
contents Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the evaluation of state-of-the-art algorithms. To address these limitations, we introduce SGA-INTERACT, the first 3D skeleton-based benchmark for group activity understanding. It features complex activities inspired by basketball tactics, emphasizing rich spatial interactions and long-term dependencies. SGA-INTERACT introduces Temporal Group Activity Localization (TGAL) task, extending group activity understanding to untrimmed sequences, filling the gap left by GAR as a standalone task. In addition to the benchmark, we propose One2Many, a novel framework that employs a pretrained 3D skeleton backbone for unified individual feature extraction. This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks. We conduct extensive evaluations on SGA-INTERACT using two skeleton-based methods, three RGB-based methods, and a proposed baseline within the One2Many framework. The general low performance of baselines highlights the benchmark's challenges, motivating advancements in group activity understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06522
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
Yang, Yuchen
Wang, Wei
Liu, Yifei
Dong, Linfeng
Wu, Hao
Zhang, Mingxin
Zhong, Zhihang
Sun, Xiao
Computer Vision and Pattern Recognition
Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the evaluation of state-of-the-art algorithms. To address these limitations, we introduce SGA-INTERACT, the first 3D skeleton-based benchmark for group activity understanding. It features complex activities inspired by basketball tactics, emphasizing rich spatial interactions and long-term dependencies. SGA-INTERACT introduces Temporal Group Activity Localization (TGAL) task, extending group activity understanding to untrimmed sequences, filling the gap left by GAR as a standalone task. In addition to the benchmark, we propose One2Many, a novel framework that employs a pretrained 3D skeleton backbone for unified individual feature extraction. This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks. We conduct extensive evaluations on SGA-INTERACT using two skeleton-based methods, three RGB-based methods, and a proposed baseline within the One2Many framework. The general low performance of baselines highlights the benchmark's challenges, motivating advancements in group activity understanding.
title SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06522