Attention-Based 3D-CNNs for Large-Vocabulary Sign Language Recognition

• Published in: IEEE transactions on circuits and systems for video technology Vol. 29; no. 9; pp. 2822 - 2832
• Main Authors: Huang, Jie, Zhou, Wengang, Li, Houqiang, Li, Weiping
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3D convolutional neural networks; Algorithms; Artificial neural networks; Assistive technology; attention mechanism; Convolution; Datasets; deep learning; Feature extraction; Gesture recognition; Hidden Markov models; Multimedia; Neural networks; Recognition; Sign language; Sign language recognition; Three-dimensional displays

Sign language recognition (SLR) is an important and challenging research topic in the multimedia field. Conventional techniques for SLR rely on hand-crafted features, which achieve limited success. In this paper, we present attention-based 3D-convolutional neural networks (3D-CNNs) for SLR. The fram...