Saved in:
Bibliographic Details
Main Authors: Fodor, Ádám, Saboundji, Rachid R., Lőrincz, András
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.03846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913343195840512
author Fodor, Ádám
Saboundji, Rachid R.
Lőrincz, András
author_facet Fodor, Ádám
Saboundji, Rachid R.
Lőrincz, András
contents Automatic personality trait assessment is essential for high-quality human-machine interactions. Systems capable of human behavior analysis could be used for self-driving cars, medical research, and surveillance, among many others. We present a multimodal deep neural network with a Siamese extension for apparent personality trait prediction trained on short video recordings and exploiting modality invariant embeddings. Acoustic, visual, and textual information are utilized to reach high-performance solutions in this task. Due to the highly centralized target distribution of the analyzed dataset, the changes in the third digit are relevant. Our proposed method addresses the challenge of under-represented extreme values, achieves 0.0033 MAE average improvement, and shows a clear advantage over the baseline multimodal DNN without the introduced module.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03846
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Apparent Personality Trait Analysis with Cross-Modal Embeddings
Fodor, Ádám
Saboundji, Rachid R.
Lőrincz, András
Computer Vision and Pattern Recognition
Human-Computer Interaction
Automatic personality trait assessment is essential for high-quality human-machine interactions. Systems capable of human behavior analysis could be used for self-driving cars, medical research, and surveillance, among many others. We present a multimodal deep neural network with a Siamese extension for apparent personality trait prediction trained on short video recordings and exploiting modality invariant embeddings. Acoustic, visual, and textual information are utilized to reach high-performance solutions in this task. Due to the highly centralized target distribution of the analyzed dataset, the changes in the third digit are relevant. Our proposed method addresses the challenge of under-represented extreme values, achieves 0.0033 MAE average improvement, and shows a clear advantage over the baseline multimodal DNN without the introduced module.
title Enhancing Apparent Personality Trait Analysis with Cross-Modal Embeddings
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2405.03846