Research map / Vision-language and multimodal / Cross-modal learning
Human-Centric Multi-Exposure Fusion: Benchmark and Bi-level Cognition Distillation Framework
Jingjie Shang, Tengyu Ma, Heng Zhang, Jinyuan Liu, Risheng Liu, Yuan Wang, Xiaochen Bo
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 EEG cross-attention Teacher (no distillation) to image-only baseline (ablation) | image-only Student · SICE | PSNR: 17.900 -> 18.980 | Improved |
| add cognition distillation to EEG-guided Teacher (ablation) | EEG-guided Teacher · SICE | PSNR: 18.980 -> 23.764 | Improved |
| use bi-level optimization instead of two-stage training (ablation) | Ours · SICE | PSNR: 20.531 -> 23.764 | Improved |
| use bi-level optimization instead of joint training (ablation) | Ours · SICE | PSNR: 22.108 -> 23.764 | Improved |
| add EEG guidance in encoder (ablation) | Ours · SICE | PSNR: 23.155 -> 23.764 | Improved |
| add EEG guidance in decoder (ablation) | Ours · SICE | PSNR: 23.420 -> 23.764 | Improved |
| use cross-attention instead of concatenation to fuse cognitive priors (ablation) | Ours · SICE | PSNR: 22.887 -> 23.764 | Improved |
| Ours vs HSDS-MEF (second best) on SICE | HSDS-MEF · SICE | PSNR: 20.568 -> 23.764 | Improved |
| Ours vs HSDS-MEF on MEF-LUT MSE | HSDS-MEF · MEF-LUT (cross-dataset) | MSE: 0.0074 -> 0.0076 | Mixed |
| Ours vs HSDS-MEF on MEFB | HSDS-MEF · MEFB (no reference) | BRISQUE: 20.112 -> 19.492 | Improved |
Closest papers by meaning
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.85)
- Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion (AAAI 2024 · similarity 0.85)
- CognitionCapturer: Decoding Visual Stimuli from Human EEG Signal with Multimodal Information (AAAI 2025 · similarity 0.85)
- What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment (NeurIPS 2026 · similarity 0.85)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.85)
- Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment (NeurIPS 2026 · similarity 0.84)
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.
