@inproceedings{77d2cef7cf234d7dabe8102c8cabb280,
title = "A ConvNet Structure Learning Spatiotemporal Features for Gesture Recognition",
abstract = "Gesture recognition makes Human-computer interaction more intuitive and natural, while recognizing complex dynamic gestures challenging. Building a powerful and efficient recognition model is very critical. In this paper, we propose a new network structure for dynamic gesture recognition: S3D + ConvLSTM + Mobilenet. Common RGB video frames are fed into this network, and then processed in three model sections sequentially. Our proposed methodology was rigorously evaluated using two prominent large-scale gesture recognition datasets, namely the Jester and IsoGD datasets. Experimental results demonstrated that our approach achieved performance that are comparable to cutting-edge methods, which significantly reduces the training and prediction calculation overhead by nearly 70\%.",
keywords = "S3D, dynamic gesture recognition, feature extraction, network structure",
author = "Guishuang Fan and Shidong Jin and Fei Wang and Dan Yan",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023 ; Conference date: 19-05-2023 Through 21-05-2023",
year = "2023",
doi = "10.1109/CIPCV58883.2023.00017",
language = "英语",
series = "Proceedings - 2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "40--46",
booktitle = "Proceedings - 2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023",
address = "美国",
}