AI Paper Atlas

Research map / Video / Video segmentation and tracking

CortexVideo: A Semantic-Spatial Dual-Anchor Framework for High-Fidelity fMRI-to-Video Reconstruction

Xiaoquan Shen, Jiaxuan Chen, Jiajun Li, Gang Pan

ECCV 2026 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 0 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 ventral stream enhancement (semantic guidance) (ablation)CortexVideo · Subject 2 ablation2-way accuracy: 0.868 -> 0.879Improved
add ventral stream enhancement (semantic guidance) (ablation)CortexVideo · Subject 2 ablation50-way accuracy: 0.266 -> 0.282Improved
add ventral stream enhancement (semantic guidance) (ablation)CortexVideo · Subject 2 ablationBLEU-1: 0.222 -> 0.247Improved
add dorsal stream enhancement (spatial regularization) (ablation)CortexVideo · Subject 2 ablation2-way accuracy: 0.870 -> 0.879Improved
add dorsal stream enhancement (spatial regularization) (ablation)CortexVideo · Subject 2 ablationDice: 0.472 -> 0.481Improved
add dorsal stream enhancement (spatial regularization) (ablation)CortexVideo · Subject 2 ablation50-way accuracy: 0.269 -> 0.282Improved
add both streams to NEURONS baseline (ablation)CortexVideo · Subject 2 ablation50-way accuracy: 0.252 -> 0.282Improved
use CortexVideo instead of NEURONSCortexVideo · cc2017CIDEr: 0.174 -> 0.240Improved
use CortexVideo instead of NEURONSCortexVideo · cc2017IoU: 0.353 -> 0.362Improved
use CortexVideo instead of NEURONSCortexVideo · fMRI-to-video (video-level)CLIP-pcc: 0.934 -> 0.926Hurt
use CortexVideo instead of NEURONSCortexVideo · fMRI-to-video (video-level)2-way accuracy: 0.863 -> 0.874Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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