2019
AAAI
AAAI 2019
Video-Based Sentiment Analysis with hvnLBP-TOP Feature and bi-LSTM
Abstract
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.
🚀
Conference Pioneer
- AAAI 2019
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Computer Vision and Interdisciplinary and Natural Language Processing
🐣
Hot Topic Early Bird
- facial expression recognition
Topics
Machine Learning > Core Methods > Classification
Machine Learning > Application Areas > Data Augmentation
Deep Learning > Architectures > Neural Networks
Computer Vision > Processing > Video Understanding
Interdisciplinary > Social > Affective Computing
Natural Language Processing > Applications > Sentiment Analysis
Deep Learning > Architectures > Recurrent Neural Networks