论文标题
使用时间卷积网络的手语分段
Sign language segmentation with temporal convolutional networks
论文作者
论文摘要
这项工作的目的是确定连续手语视频中标志之间的时间边界的位置。我们的方法采用3D卷积神经网络表示，并具有迭代的时间细分细分细分，以解决符号边界线索之间的歧义。我们证明了我们的方法对BSLCORPU，Phoenix14和BSL-1K数据集的有效性，对先前的艺术状态显示出很大的改善，并且能够推广到新的签名者，语言和域。
The objective of this work is to determine the location of temporal boundaries between signs in continuous sign language videos. Our approach employs 3D convolutional neural network representations with iterative temporal segment refinement to resolve ambiguities between sign boundary cues. We demonstrate the effectiveness of our approach on the BSLCORPUS, PHOENIX14 and BSL-1K datasets, showing considerable improvement over the prior state of the art and the ability to generalise to new signers, languages and domains.
