Research map / Vision-language and multimodal / Cross-modal learning
Prism: Harmonizing Missing Modalities via Implicit Structural Alignment on Lightweight Pulse RWKV for Multimodal Crack Segmentation
Hui Liu, Chen Jia, Fan Shi, Xu Cheng, Mianzhao Wang, Jiangpeng Zheng, Shengyong Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Prism, a lightweight Pulse RWKV-based multimodal crack segmentation model that stays robust to missing modalities via implicit structural alignment.
Problem
Multimodal crack segmentation for industrial facilities suffers when one modality is missing, degrading pixel-level accuracy, while also requiring low computation and efficient cross-modal topology perception.
Approach
Harmonizes missing-modality effects through implicit structural alignment built on a lightweight Pulse RWKV backbone, aiming to adaptively perceive cross-modal topology without high computational cost.
Experimental setup
Builds on: RWKV
Closest papers by meaning
- SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation (ICML 2026 · similarity 0.88)
- CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning (CVPR 2026 · similarity 0.86)
- MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention (CVPR 2026 · similarity 0.85)
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models (NeurIPS 2026 · similarity 0.84)
- SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures (CVPR 2025 · similarity 0.84)
- Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation (CVPR 2025 · similarity 0.82)
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.
