A Highly Efficient Marine Mammals Classifier Based on a Cross-Covariance Attended Compact Feed-Forward Sequential Memory Network (Student Abstract)

AAAI 2023 pp. 16268-16269

doi:10.1609/AAAI.V37I13.26994 /aaai/2023/liu2023aaai-highly/

Abstract

Military active sonar and marine transportation are detrimental to the livelihood of marine mammals and the ecosystem. Early detection and classification of marine mammals using machine learning can help humans to mitigate the harm to marine mammals. This paper proposes a cross-covariance attended compact Feed-Forward Sequential Memory Network (CC-FSMN). The proposed framework shows improved efficiency over multiple convolutional neural network (CNN) backbones. It also maintains a relatively decent performance.

PDF AAAI Semantic Scholar

Cite

Text

Liu and Cheng. "A Highly Efficient Marine Mammals Classifier Based on a Cross-Covariance Attended Compact Feed-Forward Sequential Memory Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26994

Markdown

[Liu and Cheng. "A Highly Efficient Marine Mammals Classifier Based on a Cross-Covariance Attended Compact Feed-Forward Sequential Memory Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/liu2023aaai-highly/) doi:10.1609/AAAI.V37I13.26994

BibTeX

@inproceedings{liu2023aaai-highly,
  title     = {{A Highly Efficient Marine Mammals Classifier Based on a Cross-Covariance Attended Compact Feed-Forward Sequential Memory Network (Student Abstract)}},
  author    = {Liu, Xiangrui and Cheng, Julian},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16268-16269},
  doi       = {10.1609/AAAI.V37I13.26994},
  url       = {https://mlanthology.org/aaai/2023/liu2023aaai-highly/}
}