A novel and effective representation is presented that captures action-related information in the pipeline of HAR without any extra annotation overhead beyond the existing skeleton extraction and achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art skeleton-only approaches.
The results indicate that skeleton-rendered pose images provide a practical accuracy-efficiency trade-off for structured physical training action recognition.
Shuo Wang, Hao Lu, Ye Zhuang et al.· Discover Applied Sciences· 0 citations
A Body Part-Based Dual-Task Spatio-Temporal Graph Convolutional Network (BPDT-STGCN) is proposed, which partitioned the human skeleton into three anatomical parts, the head, hand, and leg, which are individually fed into Spatio-Temporal Graph Convolutional Networks (ST-GCN) for feature extraction.
Bo Su, Ke-Fei Shi· International Journal of Mac...· 0 citations
A compact and deployable Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) framework that combines a 2D convolutional backbone (AlexNet) for frame-level descriptors with an LSTM head for sequence modeling is proposed, indicating a robust, real-time-capable solution for video understanding in both offline a...
H. Khan, Altaf Hussain· ICCK Transactions on Advance...· 0 citations
HPCLR is a hierarchical part-aware contrastive learning framework for skeleton-based action recognition that leverages the consistency among joint, motion, and bone modalities to select more reliable positive samples, thereby contributing to more stable and informative multi-stream skeleton representations.
Hong-Wei Chen, Min Wei, Yuanyuan Zhu et al.· Journal of Supercomputing· 0 citations
This paper constructs RTP-Dataset (Rail Transit Passenger Dataset), a dataset specifically designed for detecting anomalous behavior in rail transit scenarios, and proposes a Scene Semantic Enhancement Multimodal Network (SSEM-Net), a network that integrates three modalities: text, skeleton, and RGB.
Human 3D pose estimation is an important problem in computer vision, having applications in a wide variety of fields, such as healthcare, sports science, human-computer interaction, entertainment and retail. However, when solely using 2D sequences of human joints as input data, this becomes an ill-posed problem, caused...
Andrei Mihalea, Mihai Nan, I. Mocanu· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
