Research map / Video / Video segmentation and tracking
Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction
Haonan Wang, Qixiang Zhang, Lehan Wang, Xuanqi Huang, Xiaomeng Li
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 key object segmentation loss (ablation) | brain model with Lrec · cc2017 video-based (subject 1) | 2-way accuracy: 0.814 -> 0.834 | Improved |
| add key object segmentation loss (ablation) | brain model with Lrec · cc2017 video-based (subject 1) | 50-way accuracy: 0.164 -> 0.225 | Improved |
| add key object segmentation loss (ablation) | brain model with Lrec · cc2017 video-based (subject 1) | CLIP-pcc: 0.894 -> 0.926 | Improved |
| add concept recognition loss (ablation) | Lrec+Lseg · cc2017 video-based (subject 1) | 50-way accuracy: 0.225 -> 0.234 | Improved |
| add concept recognition loss (ablation) | Lrec+Lseg · cc2017 video-based (subject 1) | CLIP-pcc: 0.926 -> 0.911 | Hurt |
| add scene description loss (ablation) | Lrec+Lseg+Lcls · cc2017 video-based (subject 1) | 2-way accuracy: 0.836 -> 0.847 | Improved |
| add scene description loss (ablation) | Lrec+Lseg+Lcls · cc2017 video-based (subject 1) | 50-way accuracy: 0.234 -> 0.213 | Hurt |
| add scene description loss (ablation) | Lrec+Lseg+Lcls · cc2017 video-based (subject 1) | CLIP-pcc: 0.911 -> 0.923 | Improved |
| add progressive learning (ablation) | Lrec+Lseg+Lcls+Ltxt · cc2017 video-based (subject 1) | 2-way accuracy: 0.847 -> 0.856 | Improved |
| add progressive learning (ablation) | Lrec+Lseg+Lcls+Ltxt · cc2017 video-based (subject 1) | CLIP-pcc: 0.923 -> 0.937 | Improved |
| add aggregated video reconstruction (ablation) | Neurons with PL · cc2017 video-based (subject 1) | 50-way accuracy: 0.235 -> 0.254 | Improved |
| add aggregated video reconstruction (ablation) | Neurons with PL · cc2017 video-based (subject 1) | CLIP-pcc: 0.937 -> 0.932 | Hurt |
Later papers that compared with this method
2 later accepted papers report NEURONS as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- CortexVideo: A Semantic-Spatial Dual-Anchor Framework for High-Fidelity fMRI-to-Video Reconstruction (ECCV 2026 · better on 6 of 7 shared results)
- SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance (CVPR 2026 · better on 6 of 6 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuroClips — NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction (NeurIPS 2024) · better on 3 of 3 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
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.90)
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.90)
- Reanimating Images using Neural Representations of Dynamic Stimuli (CVPR 2025 · similarity 0.89)
- NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction (NeurIPS 2024 · similarity 0.89)
- SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments (ICLR 2025 · similarity 0.89)
- Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex (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.
