AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection

Lu Zhang, Xiangyu Zhu, Xiangyu Chen, Xu Yang, Zhen Lei, Zhiyong Liu

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 306 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Region Feature Alignment (RFA) module (ablation)AR-CNN · KAIST shift robustness (S45)std of MR^T over shifts: 9.77 -> 1.24Improved
add Region Feature Alignment (RFA) module (ablation)AR-CNN · KAIST shift robustness (origin)MR^T: 12.94 -> 10.90Improved
add RoI jitter strategy on top of RFA (ablation)AR-CNN · KAIST shift robustness (origin)MR^T: 10.90 -> 9.87Improved
add RoI jitter strategy on top of RFA (ablation)AR-CNN · KAIST shift robustness (S45 std)std of MR^T over shifts: 2.59 -> 1.71Improved
add confidence-aware fusion on top of RFA and RoI jitter (ablation)AR-CNN · KAIST shift robustness (origin)MR^T: 9.87 -> 8.26Improved
add confidence-aware fusion on top of RFA and RoI jitter (ablation)AR-CNN · KAIST shift robustness (S45 std)std of MR^T over shifts: 1.71 -> 1.24Improved
add RFA, RoI jitter and confidence-aware fusion (full AR-CNN) versus MSDS-RCNNAR-CNN · KAIST-Paired all-dayMR^T: 12.51 -> 8.26Improved
add AR-CNN versus MSDS-RCNN on color annotationAR-CNN · KAIST-Paired all-dayMR^C: 11.28 -> 9.86Improved
add AR-CNN versus best prior method on CVC-14 nightAR-CNN · CVC-14 nightMR: 30.8 -> 18.1Improved
shift color image by (-6,6) pixels at test timeBaseline detector · KAIST reasonableMR: 15.18 -> 25.10Hurt
shift color image by (1,-1) pixels at test timeBaseline detector · KAIST reasonableMR: 15.18 -> 14.68Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy