AI Paper Atlas

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

Unsupervised Learning of Multi-Level Descriptors for Person Re-Identification

Yang Yang, Longyin Wen, Siwei Lyu, Stan Li

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 49 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
use WLC coding instead of LLCpixel-level descriptor with KISSME · VIPeRRank-1 matching rate (%): 12.5 -> 22.9Improved
use WLC coding instead of SCpatch-level descriptor · VIPeRRank-1 matching rate (%): 16.6 -> 22.3Improved
use WLC instead of LLC/SC for image-level descriptorsimage-level descriptor · VIPeRRank-1 matching rate (%): 0.4 -> 6.6Improved
increase similarity constraint weight lambda1 from 0 to 0.001d^2 (ablation)WLC · VIPeRRank-1 matching rateImproved
partition image into horizontal stripes for image-level feature (ablation)image-level descriptor · VIPeRRank-1 matching rateImproved
use WLC instead of SC for speedWLC · pixel-level extraction timeseconds: 0.12 -> 0.03Improved
increase number of bases for patch-level WLC from 70 to 100 (ablation)WLC patch-level · VIPeRRank-1 matching rate (%): 22.3 -> 19.0Hurt
compare against GOG at Rank 5WLC multi-level fusion · VIPeRRank-5 matching rate: 79.7% vs 76.4%Hurt

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