Research map / Vision-language and multimodal / Human and embodied modeling
Beyond Brain Decoding: Visual-Semantic Reconstructions to Mental Creation Extension Based on fMRI
Haodong Jing, Dongyao Jiang, Yongqiang Ma, Haibo Hua, Bo Huang, Nanning Zheng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add BEA module to frozen DREAM | DREAM · NSD | PixCorr: .274 -> .299 | Improved |
| add BEA module to frozen OneLLM | OneLLM · NSD captioning | CIDEr: 22.99 -> 30.78 | Improved |
| train cross-subject instead of Subject-1 only | NeuroCreat · NSD | SSIM: .411 -> .448 | Improved |
| train cross-subject instead of Subject-1 only | NeuroCreat · NSD captioning | CIDEr: 65.12 -> 69.93 | Improved |
| add text prompt P^T (ablation) | NeuroCreat · NSD | CLIP: 82.50% -> 97.80% | Improved |
| add fMRI prompt P^F (ablation) | NeuroCreat · NSD | PixCorr: .293 -> .339 | Improved |
| add creation prompt P^C (ablation) | NeuroCreat · NSD | PixCorr: .327 -> .339 | Improved |
| add structural loss L_Stru (ablation) | NeuroCreat · NSD | SSIM: .276 -> .448 | Improved |
| add prior loss L_prior (ablation) | NeuroCreat · NSD | SSIM: .253 -> .448 | Improved |
| add cross-subject loss L_Cross (ablation) | NeuroCreat · NSD | SSIM: .407 -> .448 | Improved |
| use HVC instead of FFA for creation (ablation) | NeuroCreat · NSD creation video | FVD: 57.81 -> 50.11 | Improved |
| use HVC instead of LVC for creation (ablation) | NeuroCreat · NSD creation video | FVD: 55.18 -> 50.11 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- UMBRAE — UMBRAE: Unified Multimodal Brain Decoding (ECCV 2024) · better on 4 of 4 shared results
- BLIP-2 — BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (ICML 2022) · better on 0 of 1 shared result
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
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding (NeurIPS 2025 · similarity 0.90)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.90)
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.88)
- NSD-Imagery: A Benchmark Dataset for Extending fMRI Vision Decoding Methods to Mental Imagery (CVPR 2025 · similarity 0.88)
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.88)
- $i$MIND: Insightful Multi-subject Invariant Neural Decoding (NeurIPS 2025 · similarity 0.88)
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.
