@inproceedings{c5aa6df23e194d98aa20ec0a4058ed85,
title = "Context-Aware Multimodal Emotion Recognition",
abstract = "Making human–computer interaction more organic and personalized for users essentially demands advancement in human emotion recognition. Emotions are perceived by humans considering multiple factors such as facial expressions, voice tonality, and information context. Although significant research has been conducted in the area of unimodal/multimodal emotion recognition in videos using acoustic/visual features, few papers have explored the potential of textual information obtained from the video utterances. Humans experience emotions through their audio-visual and linguistic senses, making it quintessential to take the latter into account. This paper outlines two different algorithms for recognizing multimodal emotional expressions in online videos. In addition to acoustic (speech), visual (facial), and textual (utterances) feature extraction using BERT, we utilize bidirectional LSTMs to capture the context between utterances. To obtain richer sequential information, we also implement a multi-head self-attention mechanism. Our analysis utilizes the benchmarking CMU multimodal opinion sentiment and emotion intensity (CMU-MOSEI) dataset, which is the largest dataset for sentiment analysis and emotion recognition to date. Our experiments result in improved F1 scores in comparison to the baseline models.",
keywords = "BERT, CMU-MOSEI, Context-aware, Emotion, Multi-head attention, Multimodal, Recognition",
author = "Aaishwarya Khalane and Talal Shaikh",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 15th International Conference on Information Technology and Applications 2021, ICITA 2021 ; Conference date: 13-11-2021 Through 14-11-2021",
year = "2022",
month = apr,
day = "21",
doi = "10.1007/978-981-16-7618-5_5",
language = "English",
isbn = "9789811676178",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer",
pages = "51--61",
editor = "Abrar Ullah and Steve Gill and {\'A}lvaro Rocha and Sajid Anwar",
booktitle = "Proceedings of International Conference on Information Technology and Applications. ICITA 2021",
}