Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training

H Yan, Y Liu, Y Wei, Z Li, G Li… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
Skeleton sequence representation learning has shown great advantages for action
recognition due to its promising ability to model human joints and topology. However, the …

Skeleton-based action recognition with multi-stream adaptive graph convolutional networks

L Shi, Y Zhang, J Cheng, H Lu - IEEE Transactions on Image …, 2020‏ - ieeexplore.ieee.org
Graph convolutional networks (GCNs), which generalize CNNs to more generic non-
Euclidean structures, have achieved remarkable performance for skeleton-based action …

Decoupled spatial-temporal attention network for skeleton-based action-gesture recognition

L Shi, Y Zhang, J Cheng, H Lu - Proceedings of the Asian …, 2020‏ - openaccess.thecvf.com
Dynamic skeletal data, represented as the 2D/3D coordinates of human joints, has been
widely studied for human action recognition due to its high-level semantic information and …

Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition

J Wang, C Xu, Z Yang, J Zhang… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
Defect pattern recognition (DPR) of wafer maps is critical for determining the root cause of
production defects, which can provide insights for the yield improvement in wafer foundries …

Global spatio-temporal synergistic topology learning for skeleton-based action recognition

M Dai, Z Sun, T Wang, J Feng, K Jia - Pattern Recognition, 2023‏ - Elsevier
Compared to RGB video-based action recognition, skeleton-based action recognition
algorithm has attracted much more attention due to being more lightweight, better …

AdaSGN: Adapting joint number and model size for efficient skeleton-based action recognition

L Shi, Y Zhang, J Cheng, H Lu - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Existing methods for skeleton-based action recognition mainly focus on improving the
recognition accuracy, whereas the efficiency of the model is rarely considered. Recently …

Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition

H Tian, Y Zhang, H Wu, X Ma, Y Li - Neurocomputing, 2024‏ - Elsevier
Skeleton-based action recognition has attracted increasing interest in recent years. With the
flexibility of modeling long-range dependency of joints, the self-attention module has served …

Iip-transformer: Intra-inter-part transformer for skeleton-based action recognition

Q Wang, S Shi, J He, J Peng, T Liu… - 2023 IEEE International …, 2023‏ - ieeexplore.ieee.org
Recently, body part as an intuitive movement unit has received increasing attention in
skeleton-based action. However, the part-level embedding is hard to be fully exploited …

[HTML][HTML] Dynamic hand gesture recognition for smart lifecare routines via K-Ary tree hashing classifier

H Ansar, A Ksibi, A Jalal, M Shorfuzzaman… - Applied Sciences, 2022‏ - mdpi.com
Featured Application The proposed system is an image processing module that monitors,
tracks, and recognizes hand gestures and has been evaluated over publicly available …

TMMF: Temporal multi-modal fusion for single-stage continuous gesture recognition

H Gammulle, S Denman, S Sridharan… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Gesture recognition is a much studied research area which has myriad real-world
applications including robotics and human-machine interaction. Current gesture recognition …