AI Paper Atlas

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

Person Re-Identification by Camera Correlation Aware Feature Augmentation

Ying-Cong Chen, Xiatian Zhu, Wei‐Shi Zheng, Jianhuang Lai

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 340 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 CVD regularization to CRAFT (ablation)CRAFT (kernelized, MFA) · VIPeRrank-1 (%): 46.3 -> 50.3Improved
add CVD regularization to CRAFT (ablation)CRAFT (kernelized, MFA) · CUHK01rank-1 (%): 73.8 -> 74.5Improved
add CVD regularization to CRAFT (ablation)CRAFT (kernelized, MFA) · CUHK03rank-1 (%): 83.9 -> 84.3Improved
add CVD regularization to CRAFT (ablation)CRAFT (kernelized, MFA) · Market-1501rank-1 (%): 66.6 -> 68.7Improved
add CVD regularization to CRAFT (ablation)CRAFT (kernelized, MFA) · QMUL GRIDrank-1 (%): 15.8 -> 22.4Improved
replace original features with camera-correlation-aware augmentation (CRAFT)MFA, no kernel · VIPeRrank-1 (%): 43.3 -> 47.8Improved
replace zero-padding augmentation with CRAFTMFA, no kernel · Market-1501rank-1 (%): 38.2 -> 67.9Improved
use zero-padding augmentation instead of original featuresMFA, no kernel · VIPeRrank-1 (%): 43.3 -> 37.5Hurt
use baseline feature augmentation instead of original featuresMFA, no kernel · CUHK01rank-1 (%): 64.3 -> 59.0Hurt
add Bhattacharyya kernelization to CRAFTCRAFT (MFA) · VIPeRrank-1 (%): 47.8 -> 50.3Improved
add Bhattacharyya kernelization to CRAFTCRAFT (MFA) · QMUL GRIDrank-1 (%): 25.4 -> 22.4Hurt
replace TFLDA domain adaptation with CRAFTre-id model · CUHK03rank-1 (%): 76.7 -> 84.3Improved

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