Home > Research > Publications & Outputs > One-Shot Action Recognition via Multi-Scale Spa...

Links

Text available via DOI:

View graph of relations

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching. / Yang, Siyuan; Liu, Jun; Lu, Shijian et al.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 46, No. 7, 31.07.2024, p. 5149-5156.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Yang, S, Liu, J, Lu, S, Hwa, EM & Kot, AC 2024, 'One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 7, pp. 5149-5156. https://doi.org/10.1109/TPAMI.2024.3363831

APA

Yang, S., Liu, J., Lu, S., Hwa, E. M., & Kot, A. C. (2024). One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 5149-5156. https://doi.org/10.1109/TPAMI.2024.3363831

Vancouver

Yang S, Liu J, Lu S, Hwa EM, Kot AC. One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024 Jul 31;46(7):5149-5156. Epub 2024 Feb 8. doi: 10.1109/TPAMI.2024.3363831

Author

Yang, Siyuan ; Liu, Jun ; Lu, Shijian et al. / One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024 ; Vol. 46, No. 7. pp. 5149-5156.

Bibtex

@article{4dbf4240dbf94545baad5bd9d0feeb21,
title = "One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching",
abstract = "One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins.",
author = "Siyuan Yang and Jun Liu and Shijian Lu and Hwa, {Er Meng} and Kot, {Alex C.}",
year = "2024",
month = jul,
day = "31",
doi = "10.1109/TPAMI.2024.3363831",
language = "English",
volume = "46",
pages = "5149--5156",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "7",

}

RIS

TY - JOUR

T1 - One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

AU - Yang, Siyuan

AU - Liu, Jun

AU - Lu, Shijian

AU - Hwa, Er Meng

AU - Kot, Alex C.

PY - 2024/7/31

Y1 - 2024/7/31

N2 - One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins.

AB - One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins.

U2 - 10.1109/TPAMI.2024.3363831

DO - 10.1109/TPAMI.2024.3363831

M3 - Journal article

VL - 46

SP - 5149

EP - 5156

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 7

ER -