Depthwise Separable Temporal Convolutional Network for Action Segmentation
Fine-grained temporal action segmentation in long, untrimmed RGB videos is a key topic in visual human- machine interaction. Recent temporal convolution based approaches either use encoder-decoder(ED) architecture or dilations with doubling factor in consecutive convolution layers to segment actions in videos. However ED networks operate on low temporal resolution and the dilations in suc- cessive layers cause gridding artifacts problem. We propose depthwise separable temporal convolution network (DS- TCN) that operates on full temporal resolution and with re- duced gridding effects. The basic component of DS-TCN is residual depthwise dilated block (RDDB). We explore the trade-off between large kernels and small dilation rates us- ing RDDB. We show that our DS-TCN is capable of captur- ing long-term dependencies as well as local temporal cues efficiently. Our evaluation on three benchmark datasets, GTEA, 50Salads, and Breakfast demonstrates that DS-TCN outperforms the existing ED-TCN and dilation based TCN baselines even with comparatively fewer parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
Action SegmentationDecoderTemporal Action SegmentationSimilar Papers 제목 키워드 기반
Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation
Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning mod…
Speech DereverberationDepthwise-STFT based separable Convolutional Neural Networks
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer i…
image-classificationImage ClassificationPositionXception: Deep Learning with Depthwise Separable Convolutions
We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution f…
ClassificationDeep Learningimage-classificationImage Classification+1Xception: Deep Learning With Depthwise Separable Convolutions
We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution f…
Deep Learningimage-classificationImage ClassificationSeparable Convolutional LSTMs for Faster Video Segmentation
Semantic Segmentation is an important module for autonomous robots such as self-driving cars. The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is con…
GPUImage SegmentationSegmentationSelf-Driving Cars+3