Research map / Vision-language and multimodal / Cross-modal learning
ACM: Adaptive Cross-Modal Graph Convolutional Neural Networks for RGB-D Scene Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 graph modeling to RGB features (ablation) | RGB AlexNet · SUN RGB-D | accuracy (%): 42.7% -> 45.7% | Helped |
| add graph modeling to RGB features (ablation) | RGB AlexNet · NYUD v2 | accuracy (%): 53.2% -> 55.4% | Helped |
| add RGB and depth feature concatenation instead of RGB only (ablation) | RGB AlexNet · SUN RGB-D | accuracy (%): 42.7% -> 48.2% | Helped |
| add cross-modal graph on top of RGB-D concatenation (ablation) | RGB-D(HHA) AlexNet · SUN RGB-D | accuracy (%): 48.2% -> 55.1% | Helped |
| add cross-modal graph on top of RGB-D concatenation (ablation) | RGB-D(HHA) AlexNet · NYUD v2 | accuracy (%): 61.1% -> 67.2% | Helped |
| increase graph nodes K from 9 to 16 (ablation) | ACM · NYUD v2 | accuracy (%): 66.1% -> 67.2% | Helped |
| increase graph nodes K from 16 to 25 (ablation) | ACM · NYUD v2 | accuracy (%): 67.2% -> 67.4% | No clear effect |
Closest papers by meaning
- Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Multi-Modal Object Re-identification via Sparse Mixture-of-Experts (ICML 2025 · similarity 0.85)
- CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning (CVPR 2024 · similarity 0.84)
- CrossOver: 3D Scene Cross-Modal Alignment (CVPR 2025 · similarity 0.84)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.83)
- End-to-End RGB-D Image Compression via Exploiting Channel-Modality Redundancy (AAAI 2024 · similarity 0.83)
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.