AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Canonical F-Correlation Projection for Compact Multiview Representation

Yun-Hao Yuan, Jin Li, Yun Li, Jipeng Qiang, Yi Zhu, Xiaobo Shen, Jianping Gou

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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
Use Gaussian-kernel feature-level F-covariation projections instead of the compared two-view methodsCCP · Yale and COIL-20 pairwise view combinationsclassification accuracy (%): 82.9 ± 4.60 vs 80.8 ± 4.10; 80.1 ± 6.57 vs 77.9 ± 5.26; 82.9 ± 3.05 vs 80.1 ± 2.20; 76.9 ± 2.50 vs 72.7 ± 3.81; 75.9 ± 2Improved
Use multiset feature-level F-covariation projections instead of the compared multiview methodsMCCP · Yale and COIL-20classification accuracy: 82.5 vs 82.2; 76.9 vs 75.3Improved
Use Gaussian-kernel feature-level F-covariation projections instead of the compared two-view methodsCCP · WebKB, BBC-Sport, Krvskp, and DNANominalclustering ACC: 0.9800 vs 0.9762; 0.9430 vs 0.8750; 0.6834 vs 0.5917; 0.6871 vs 0.5712Improved
Use Gaussian-kernel feature-level F-covariation projections instead of the compared two-view methodsCCP · WebKB, BBC-Sport, Krvskp, and DNANominalclustering NMI: 0.8290 vs 0.7986; 0.8352 vs 0.8012; 0.1148 vs 0.0616; 0.3022 vs 0.1445Improved
Use multiset feature-level F-covariation projections instead of the compared multiview methodsMCCP · Yale and COIL-20clustering ACC: 0.6727 vs 0.6606; 0.6826 vs 0.6681Improved
Use multiset feature-level F-covariation projections instead of the compared multiview methodsMCCP · Yale and COIL-20clustering NMI: 0.7440 vs 0.7318; 0.8135 vs 0.8082Improved

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