Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversation. This task arises as a crucial pursuit to gain insights into human's interaction dynamics and behavior patterns within a conversation. In this research, we introduce a dilated convolutional Transformer for modeling and estimating human engagement in the MULTIMEDIATE 2023 competition. Our proposed system surpasses the baseline models, exhibiting a noteworthy 7\% improvement on test set and 4\% on validation set. Moreover, we employ different modality fusion mechanism and show that for this type of data, a simple concatenated method with self-attention fusion gains the best performance.
@article{arxiv.2308.01966,
title = {DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation},
author = {Vu Ngoc Tu and Van Thong Huynh and Hyung-Jeong Yang and M. Zaigham Zaheer and Shah Nawaz and Karthik Nandakumar and Soo-Hyung Kim},
journal= {arXiv preprint arXiv:2308.01966},
year = {2023}
}