AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search

Ya Jing, Chenyang Si, Junbo Wang, Wei Wang, Liang Wang, Tieniu Tan

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 205 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 PMA instead of Dual Path with VGG-16 featuresText-based person search · CUHK-PEDES testtop-1 accuracy: 32.15 -> 47.02Improved
Use PMA instead of Dual Path with ResNet-50 featuresText-based person search · CUHK-PEDES testtop-1 accuracy: 44.40 -> 53.81Improved
Use the full 9408-word vocabulary instead of the reduced vocabulary (ablation)Text representation · CUHK-PEDES testtop-1 accuracy: 48.67 -> 46.51Hurt
Use bidirectional rather than unidirectional LSTM encoding (ablation)Text representation · CUHK-PEDES testtop-1 accuracy: 47.02 -> 48.67Improved
Add pose confidence maps to the visual CNN input (ablation)Global-feature baseline · CUHK-PEDES testtop-1 accuracy: 48.67 -> 50.06Improved
Add coarse alignment to pose-augmented visual features (ablation)Con-pose · CUHK-PEDES testtop-1 accuracy: 50.06 -> 52.20Improved
Add fine-grained alignment to Con-pose + CA (ablation)Con-pose + CA · CUHK-PEDES testtop-1 accuracy: 52.20 -> 53.81Improved
Use pose guidance in fine-grained alignment (ablation)PMA fine-grained alignment · CUHK-PEDES testtop-1 accuracy: 52.54 -> 53.81Improved
Use noun phrases rather than every sentence word in fine-grained alignment (ablation)PMA fine-grained alignment · CUHK-PEDES testtop-1 accuracy: 52.71 -> 53.81Improved
Use adaptive hard attention rather than soft attention over regions (ablation)PMA coarse alignment · CUHK-PEDES testtop-1 accuracy: 52.35 -> 53.81Improved
Select a fixed 5, 10, or 20 regions rather than using adaptive hard attention (ablation)PMA coarse alignment · CUHK-PEDES testtop-1 accuracy: 51.24; 53.56; 53.21; adaptive: 53.81Mixed

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