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

Saurabh Suman, Nilay Naharas, Badri Narayan Subudhi, Vinit Jakhetiya

AAAI 2023 pp. 16340-16341

doi:10.1609/AAAI.V37I13.27030 /aaai/2023/suman2023aaai-two/

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.

PDF AAAI Semantic Scholar

Cite

Text

Suman et al. "Two-Streams: Dark and Light Networks with Graph Convolution for Action Recognition from Dark Videos (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27030

Markdown

[Suman et al. "Two-Streams: Dark and Light Networks with Graph Convolution for Action Recognition from Dark Videos (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/suman2023aaai-two/) doi:10.1609/AAAI.V37I13.27030

BibTeX

@inproceedings{suman2023aaai-two,
  title     = {{Two-Streams: Dark and Light Networks with Graph Convolution for Action Recognition from Dark Videos (Student Abstract)}},
  author    = {Suman, Saurabh and Naharas, Nilay and Subudhi, Badri Narayan and Jakhetiya, Vinit},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16340-16341},
  doi       = {10.1609/AAAI.V37I13.27030},
  url       = {https://mlanthology.org/aaai/2023/suman2023aaai-two/}
}