AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Person Search by Text Attribute Query As Zero-Shot Learning

Qi Dong, Shaogang Gong, Xiatian Zhu

ICCV 2019 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 45 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 local attribute-level embedding to global-only (ablation)AIHM · Market-1501Rank-1 (%): 30.6 -> 43.3Improved
add local attribute-level embedding to global-only (ablation)AIHM · DukeMTMCRank-1 (%): 40.7 -> 50.5Improved
add local attribute-level embedding to global-only (ablation)AIHM · PA100KRank-1 (%): 26.1 -> 31.3Improved
add global category-level embedding to local-only (ablation)AIHM · Market-1501Rank-1 (%): 39.5 -> 43.3Improved
add global category-level embedding to local-only (ablation)AIHM · DukeMTMCRank-1 (%): 46.9 -> 50.5Improved
add global category-level embedding to local-only (ablation)AIHM · PA100KRank-1 (%): 29.4 -> 31.3Improved
use quality-aware fusion instead of average pooling (ablation)AIHM · Market-1501Rank-1 (%): 39.0 -> 43.3Improved
use quality-aware fusion instead of average pooling (ablation)AIHM · DukeMTMCRank-1 (%): 44.9 -> 50.5Improved
use quality-aware fusion instead of average pooling (ablation)AIHM · PA100KRank-1 (%): 26.1 -> 31.3Improved
add 10k negative category augmentation (ablation)AIHM · Market-1501Rank-1 (%): +4.4% Rank-1Improved
increase negative augmentation from 10k to 20k (ablation)AIHM · Market-1501, DukeMTMC, PA100KRank-1 (%)Hurt
use CNN instead of RNN to aggregate attribute embeddings (one-hot) (ablation)AIHM global embedding · Market-1501Rank-1 (%): 35.7 -> 37.1Improved

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