AI Paper Atlas

Research map / Video / Video segmentation and tracking

Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment

Chong Li, Xuelin Qian, Yun Wang, Jingyang Huo, Xiangyang Xue, Yanwei Fu, Jianfeng Feng

ECCV 2024 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GLFA global-local functional alignment to fMRI-PTE-V (ablation)fMRI-PTE-V · Benchmark dataset, task 1,2->3 (spatial correlation r(s1,s3))fMRI spatial correlation: .358 -> .517Improved
add GLFA to fMRI-PTE-V (ablation)fMRI-PTE-V · Benchmark dataset, task 1,2->3 (ISC subject 3)ISC: .496 -> .597Improved
add GLFA to fMRI-PTE-V (ablation)fMRI-PTE-V · Own dataset, ISC subject 1ISC: .012 -> .036Improved
add GLFA to fMRI-PTE-V (ablation)fMRI-PTE-V · Benchmark dataset, task 1,2->3 (video 50-way)video-based 50-way accuracy: 0.182 -> 0.193Improved
add GLFA to fMRI-PTE-V (ablation)fMRI-PTE-V · Benchmark dataset, task 1,3->2 (video 2-way)video-based 2-way accuracy: 0.844 -> 0.838Hurt
add GLFA to fMRI-PTE-V (ablation)fMRI-PTE-V · Benchmark dataset, task 2,3->1 (SSIM)SSIM: 0.151 -> 0.181Improved
fMRI-PTE-V instead of MinD-Video for within-subject decodingfMRI decoder · Benchmark dataset within-subjectvideo/frame accuracy: 50-way video subject 1: 0.202 -> 0.214; frame 50-way subject 3: 0.193 -> 0.173Mixed
use fMRI-PTE-V pipeline with GLFA instead of LEA ridge regression baselinecross-subject decoding · Own dataset, task 2,3->1SSIM: 0.167 -> 0.199Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy