AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Deep Neural Networks for Vehicle Re-ID With Visual-Spatio-Temporal Path Proposals

Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang

ICCV 2017 · Video › Video segmentation and tracking · approach: Spatial-temporal video person re-identification · 315 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 Path-LSTM on proposed visual-spatio-temporal paths (ablation)Siamese-CNN · VeRi-776mAP: 54.21 -> 58.27Improved
add Path-LSTM on proposed visual-spatio-temporal paths (ablation)Siamese-CNN · VeRi-776top-1 accuracy: 79.32 -> 83.49Improved
add Siamese-CNN score to Path-LSTM (ablation)Path-LSTM only · VeRi-776mAP: 54.49 -> 58.27Improved
add Siamese-CNN score to Path-LSTM (ablation)Path-LSTM only · VeRi-776top-1 accuracy: 82.89 -> 83.49Improved
replace empirical average with trained Path-LSTM to score paths (ablation)Chain MRF model · VeRi-776mAP: 44.31 -> 54.49Improved
replace empirical average with trained Path-LSTM to score paths (ablation)Chain MRF model · VeRi-776top-1 accuracy: 54.41 -> 82.89Improved
add spatio-temporal branch to Siamese-Visual (ablation)Siamese-Visual · VeRi-776mAP: 29.48 -> 54.21Improved
add spatio-temporal branch to Siamese-Visual (ablation)Siamese-Visual · VeRi-776top-1 accuracy: 41.12 -> 79.32Improved
learn spatio-temporal relation with a network instead of hand-set STR score (ablation)Siamese-Visual+STR · VeRi-776mAP: 40.26 -> 54.21Improved
use ResNet50 backbone instead of VGG16 for full model (ablation)Siamese-CNN+Path-LSTM · VeRi-776mAP: 46.85 -> 58.27Improved
add Path-LSTM on VGG16 Siamese-CNN (ablation)Siamese-CNN-VGG16 · VeRi-776mAP: 44.32 -> 45.56Improved
add Path-LSTM and Siamese-CNN combination on VGG16 (ablation)Siamese-CNN-VGG16 · VeRi-776mAP: 44.32 -> 46.85Improved

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