Please use this identifier to cite or link to this item:
https://doi.org/10.1109/FG.2019.8756577
Title: | A multimodal LSTM for predicting listener empathic responses over time | Authors: | Tan, ZX Goel, A Nguyen, TS Ong, DC |
Keywords: | cs.CL cs.CL |
Issue Date: | 1-May-2019 | Publisher: | IEEE | Citation: | Tan, ZX, Goel, A, Nguyen, TS, Ong, DC (2019-05-01). A multimodal LSTM for predicting listener empathic responses over time. 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019). ScholarBank@NUS Repository. https://doi.org/10.1109/FG.2019.8756577 | Abstract: | © 2019 IEEE. People naturally understand the emotions of-and often also empathize with-those around them. In this paper, we predict the emotional valence of an empathic listener over time as they listen to a speaker narrating a life story. We use the dataset provided by the OMG-Empathy Prediction Challenge, a workshop held in conjunction with IEEE FG 2019. We present a multimodal LSTM model with feature-level fusion and local attention that predicts empathic responses from audio, text, and visual features. Our best-performing model, which used only the audio and text features, achieved a concordance correlation coefficient (CCC) of. 29 and. 32 on the Validation set for the Generalized and Personalized track respectively, and achieved a CCC of .14 and .14 on the held-out Test set. We discuss the difficulties faced and the lessons learnt tackling this challenge. | Source Title: | 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019) | URI: | https://scholarbank.nus.edu.sg/handle/10635/171917 | ISBN: | 9781728100890 | DOI: | 10.1109/FG.2019.8756577 |
Appears in Collections: | Staff Publications Elements |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
1812.04891v2.pdf | 314.26 kB | Adobe PDF | OPEN | Post-print | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.