New Attack Method Preserves Motion Quality in Skeleton Action Recognition

报道来源 [4]

1. Hugging Face Daily Papers TIER_1 English(EN) · 2026-06-11 07:55

   面向骨骼动作识别的质量保持不可感知对抗性攻击

   Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently perceptible with recent advancements in S-HAR s…

2. arXiv cs.CV TIER_1 English(EN) · Ziyi Chang, Kanglei Zhou, Xiaohui Liang, Hubert P. H. Shum · 2026-06-12 04:00

   面向骨骼动作识别的保持质量的不可感知对抗性攻击

   arXiv:2606.13022v1 Announce Type: new Abstract: Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently…

3. arXiv cs.CV TIER_1 English(EN) · Hubert P. H. Shum · 2026-06-11 07:55

   面向骨骼动作识别的保持质量的不可感知对抗性攻击

   Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently perceptible with recent advancements in S-HAR s…

4. arXiv cs.CV TIER_1 English(EN) · Shengkai Sun, Zhiyong Cheng, Zefan Zhang, Jianfeng Dong, Zhihui Li, Meng Wang · 2026-06-11 04:00

   探索自监督骨骼动作识别的自适应掩码重建

   arXiv:2606.11450v1 Announce Type: new Abstract: Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recognition. However, existing state-of-the-art methods mus…