Two-Streams: Dark and Light Networks with Graph Convolution for Action Recognition from Dark Videos (Student Abstract)

In this article, we propose a two-stream action recognition technique for recognizing human actions from dark videos. The proposed action recognition network consists of an image enhancement network with Self-Calibrated Illumination (SCI) module, followed by a two-stream action recognition network. We have used R(2+1)D as a feature extractor for both streams with shared weights. Graph Convolutional Network (GCN), a temporal graph encoder is utilized to enhance the obtained features which are then further fed to a classification head to recognize the actions in a video. The experimental results are presented on the recent benchmark ``ARID" dark-video database.

Authors

• Saurabh Suman Indian Institute of Technology Jammu
• Nilay Naharas Indian Institute of Technology Jammu
• Badri Narayan Subudhi Indian Institute of Technology Jammu
• Vinit Jakhetiya Indian Institute of Technology Jammu

Keywords

• Computer Vision
• Convolutional Neural Network
• Dark Environment
• Graph Convolutional Network
• Image Enhancement
• Self-Calibrated Illumination
• Two-Stream Network
• Video Action Recognition