Saved in:
Bibliographic Details
Main Authors: Kwon, Joonwoo, Wang, Heehwan, Lee, Jinwoo, Kim, Sooyoung, Yoo, Shinjae, Lin, Yuewei, Cha, Jiook
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.05296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913988695031808
author Kwon, Joonwoo
Wang, Heehwan
Lee, Jinwoo
Kim, Sooyoung
Yoo, Shinjae
Lin, Yuewei
Cha, Jiook
author_facet Kwon, Joonwoo
Wang, Heehwan
Lee, Jinwoo
Kim, Sooyoung
Yoo, Shinjae
Lin, Yuewei
Cha, Jiook
contents In this paper, we introduce RevisitAffectiveMemory, a novel task designed to reconstruct autobiographical memories through audio-visual generation guided by affect extracted from electroencephalogram (EEG) signals. To support this pioneering task, we present the EEG-AffectiveMemory dataset, which encompasses textual descriptions, visuals, music, and EEG recordings collected during memory recall from nine participants. Furthermore, we propose RYM (Revisit Your Memory), a three-stage framework for generating synchronized audio-visual contents while maintaining dynamic personal memory affect trajectories. Experimental results demonstrate our method successfully decodes individual affect dynamics trajectories from neural signals during memory recall (F1=0.9). Also, our approach faithfully reconstructs affect-contextualized audio-visual memory across all subjects, both qualitatively and quantitatively, with participants reporting strong affective concordance between their recalled memories and the generated content. Especially, contents generated from subject-reported affect dynamics showed higher correlation with participants' reported affect dynamics trajectories (r=0.265, p<.05) and received stronger user preference (preference=56%) compared to those generated from randomly reordered affect dynamics. Our approaches advance affect decoding research and its practical applications in personalized media creation via neural-based affect comprehension. Codes and the dataset are available at https://github.com/ioahKwon/Revisiting-Your-Memory.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05296
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation
Kwon, Joonwoo
Wang, Heehwan
Lee, Jinwoo
Kim, Sooyoung
Yoo, Shinjae
Lin, Yuewei
Cha, Jiook
Artificial Intelligence
Human-Computer Interaction
Sound
Audio and Speech Processing
In this paper, we introduce RevisitAffectiveMemory, a novel task designed to reconstruct autobiographical memories through audio-visual generation guided by affect extracted from electroencephalogram (EEG) signals. To support this pioneering task, we present the EEG-AffectiveMemory dataset, which encompasses textual descriptions, visuals, music, and EEG recordings collected during memory recall from nine participants. Furthermore, we propose RYM (Revisit Your Memory), a three-stage framework for generating synchronized audio-visual contents while maintaining dynamic personal memory affect trajectories. Experimental results demonstrate our method successfully decodes individual affect dynamics trajectories from neural signals during memory recall (F1=0.9). Also, our approach faithfully reconstructs affect-contextualized audio-visual memory across all subjects, both qualitatively and quantitatively, with participants reporting strong affective concordance between their recalled memories and the generated content. Especially, contents generated from subject-reported affect dynamics showed higher correlation with participants' reported affect dynamics trajectories (r=0.265, p<.05) and received stronger user preference (preference=56%) compared to those generated from randomly reordered affect dynamics. Our approaches advance affect decoding research and its practical applications in personalized media creation via neural-based affect comprehension. Codes and the dataset are available at https://github.com/ioahKwon/Revisiting-Your-Memory.
title Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation
topic Artificial Intelligence
Human-Computer Interaction
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2412.05296