Video-Based Sentiment Analysis with hvnLBP-TOP Feature and Bi-LSTM

AAAI 2019 pp. 9963-9964

doi:10.1609/AAAI.V33I01.33019963 /aaai/2019/li2019aaai-video/

Abstract

In this paper, we propose a new feature extraction method called hvnLBP-TOP for video-based sentiment analysis. Furthermore, we use principal component analysis (PCA) and bidirectional long short term memory (bi-LSTM) for dimensionality reduction and classification. We achieved an average recognition accuracy of 71.1% on the MOUD dataset and 63.9% on the CMU-MOSI dataset.

PDF AAAI Semantic Scholar

Cite

Text

Li and Xu. "Video-Based Sentiment Analysis with hvnLBP-TOP Feature and Bi-LSTM." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019963

Markdown

[Li and Xu. "Video-Based Sentiment Analysis with hvnLBP-TOP Feature and Bi-LSTM." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/li2019aaai-video/) doi:10.1609/AAAI.V33I01.33019963

BibTeX

@inproceedings{li2019aaai-video,
  title     = {{Video-Based Sentiment Analysis with hvnLBP-TOP Feature and Bi-LSTM}},
  author    = {Li, Haoran and Xu, Hua},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9963-9964},
  doi       = {10.1609/AAAI.V33I01.33019963},
  url       = {https://mlanthology.org/aaai/2019/li2019aaai-video/}
}