A Spatial-Temporal Normalized Contrastive Embedding for Robust Motion Similarity Retrieval
Seung-su Lee1, Young-Been Noh1, HwaYoung Jeong2, Kwang-il Hwang1,*
1 Department of Embedded Systems Engineering, Incheon National University, Incheon, Republic of Korea
2 Humanitas College, Kyung Hee University, Seoul, Republic of Korea
* Corresponding Author: Kwang-il Hwang. Email: 
Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.081251
Received 26 February 2026; Accepted 22 May 2026; Published online 06 July 2026
Abstract
Robust motion similarity retrieval from monocular 2D pose sequences is challenged by body-scale variation, viewpoint inconsistency, translation drift, and temporal misalignment. Existing contrastive skeleton learning methods primarily address action recognition and rarely integrate explicit geometric canonicalization for retrieval-oriented metric learning. This paper proposes a spatial-temporal normalized contrastive embedding framework that unifies structured nuisance suppression with scalable similarity representation learning. A four-stage normalization pipeline—torso-scale normalization, pelvis-centered alignment, posture-axis alignment, and phase-synchronized temporal resampling—removes geometric and temporal distortions prior to embedding. The normalized sequences are encoded using an acausal dilated temporal convolutional network trained with a hybrid contrastive objective combining NT-Xent and semi-hard triplet loss, enabling both global separation and fine-grained stylistic discrimination. A prototype-based representation further supports interpretable amateur-to-professional style mapping. Experiments on a golf swing benchmark achieve a Top-1 accuracy of 91.3%, outperforming BiLSTM and Dynamic Time Warping baselines. The framework establishes an invariant and interpretable paradigm for motion similarity retrieval applicable to broader human movement analysis tasks.
Keywords
Motion similarity retrieval; spatial-temporal normalization; contrastive representation learning; temporal convolutional networks (TCN); prototype-based embedding
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
