English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Vehicle re-identification (re-ID) focuses on matching images of the samevehicle across different cameras. It is fundamentally challenging becausedifferences between vehicles are sometimes subtle. While several studiesincorporate spatial-attention mechanisms to help vehicle re-ID, they oftenrequire expensive keypoint labels or suffer from noisy attention mask if nottrained with expensive labels. In this work, we propose a dedicatedSemantics-guided Part Attention Network (SPAN) to robustly predict partattention masks for different views of vehicles given only image-level semanticlabels during training. With the help of part attention masks, we can extractdiscriminative features in each part separately. Then we introduceCo-occurrence Part-attentive Distance Metric (CPDM) which places greateremphasis on co-occurrence vehicle parts when evaluating the feature distance oftwo images. Extensive experiments validate the effectiveness of the proposedmethod and show that our framework outperforms the state-of-the-art approaches.

Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network