Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Check 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 IADM to BL | BL on RGBT-CC · RGBT-CC test | GAME(0): 18.70 -> 15.61 | Helped |
| Add IADM to BL | BL on RGBT-CC · RGBT-CC test | RMSE: 32.67 -> 28.18 | Helped |
| Add IADM to CSRNet | CSRNet on ShanghaiTechRGBD · ShanghaiTechRGBD | GAME(0): 4.92 -> 4.38 | Helped |
| Use RGB and thermal inputs rather than RGB alone | CSRNet on RGBT-CC · RGBT-CC test | RMSE: 69.59 -> 30.91 | Helped |
| Use RGB and thermal inputs rather than thermal alone | CSRNet on RGBT-CC · RGBT-CC test | RMSE: 37.38 -> 30.91 | Helped |
| Add gating to filter cross-modal information (ablation) | IADM on RGBT-CC · RGBT-CC test | RMSE: 33.61 -> 30.91 | Helped |
| Add a modality-shared feature branch (ablation) | IADM on RGBT-CC · RGBT-CC test | RMSE: 33.73 -> 30.91 | Helped |
| Add Information Distribution Transfer (ablation) | IADM on RGBT-CC · RGBT-CC test | RMSE: 32.91 -> 30.91 | Helped |
| Increase pyramid pooling from one to three levels (ablation) | IADM on RGBT-CC · RGBT-CC test | RMSE: 33.01 -> 30.91 | Helped |
| Increase pyramid pooling from three to four levels (ablation) | IADM on RGBT-CC · RGBT-CC test | RMSE: 30.91 -> 31.48 | Hurt |
| Use RGB-thermal input rather than RGB alone | CSRNet under bright illumination · RGBT-CC bright test | RMSE: 45.40 -> 32.57 | Helped |
| Use RGB-thermal input rather than RGB alone | CSRNet under darkness · RGBT-CC dark test | RMSE: 87.81 -> 29.11 | Helped |
Closest papers by meaning
- Free Lunch Enhancements for Multi-modal Crowd Counting (CVPR 2025 · similarity 0.90)
- CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model (CVPR 2023 · similarity 0.88)
- Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (CVPR 2019 · similarity 0.87)
- Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (CVPR 2018 · similarity 0.87)
- Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR 2018 · similarity 0.87)
- Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (AAAI 2024 · similarity 0.85)
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.