MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Xuan-Hao, Liu, Yan-Kai, Zhou, Tianyi, Lu, Bao-Liang, Zheng, Wei-Long
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915625537896448
author Liu, Xuan-Hao
Liu, Yan-Kai
Zhou, Tianyi
Lu, Bao-Liang
Zheng, Wei-Long
author_facet Liu, Xuan-Hao
Liu, Yan-Kai
Zhou, Tianyi
Lu, Bao-Liang
Zheng, Wei-Long
contents Reconstructing video from brain signals is an important brain decoding task. Existing brain decoding frameworks are primarily built on a subject-dependent paradigm, which requires large amounts of brain data for each subject. However, the expensive cost of collecting brain-video data causes severe data scarcity. Although some cross-subject methods being introduced, they often overfocus with subject-invariant information while neglecting subject-specific information, resulting in slow fine-tune-based adaptation strategy. To achieve fast and data-efficient new subject adaptation, we propose MindCross, a novel cross-subject framework. MindCross's N specific encoders and one shared encoder are designed to extract subject-specific and subject-invariant information, respectively. Additionally, a Top-K collaboration module is adopted to enhance new subject decoding with the knowledge learned from previous subjects' encoders. Extensive experiments on fMRI/EEG-to-video benchmarks demonstrate MindCross's efficacy and efficiency of cross-subject decoding and new subject adaptation using only one model.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14196
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals
Liu, Xuan-Hao
Liu, Yan-Kai
Zhou, Tianyi
Lu, Bao-Liang
Zheng, Wei-Long
Multimedia
Computer Vision and Pattern Recognition
Human-Computer Interaction
Reconstructing video from brain signals is an important brain decoding task. Existing brain decoding frameworks are primarily built on a subject-dependent paradigm, which requires large amounts of brain data for each subject. However, the expensive cost of collecting brain-video data causes severe data scarcity. Although some cross-subject methods being introduced, they often overfocus with subject-invariant information while neglecting subject-specific information, resulting in slow fine-tune-based adaptation strategy. To achieve fast and data-efficient new subject adaptation, we propose MindCross, a novel cross-subject framework. MindCross's N specific encoders and one shared encoder are designed to extract subject-specific and subject-invariant information, respectively. Additionally, a Top-K collaboration module is adopted to enhance new subject decoding with the knowledge learned from previous subjects' encoders. Extensive experiments on fMRI/EEG-to-video benchmarks demonstrate MindCross's efficacy and efficiency of cross-subject decoding and new subject adaptation using only one model.
title MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals
topic Multimedia
Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2511.14196