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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper we tackle the problem of vehicle re-identification in a cameranetwork utilizing triplet embeddings. Re-identification is the problem ofmatching appearances of objects across different cameras. With theproliferation of surveillance cameras enabling smart and safer cities, there isan ever-increasing need to re-identify vehicles across cameras. Typicalchallenges arising in smart city scenarios include variations of viewpoints,illumination and self occlusions. Most successful approaches forre-identification involve (deep) learning an embedding space such that thevehicles of same identities are projected closer to one another, compared tothe vehicles representing different identities. Popular loss functions forlearning an embedding (space) include contrastive or triplet loss. In thispaper we provide an extensive evaluation of these losses applied to vehiclere-identification and demonstrate that using the best practices for learningembeddings outperform most of the previous approaches proposed in the vehiclere-identification literature. Compared to most existing state-of-the-artapproaches, our approach is simpler and more straightforward for trainingutilizing only identity-level annotations, along with one of the smallestpublished embedding dimensions for efficient inference. Furthermore in thiswork we introduce a formal evaluation of a triplet sampling variant (batchsample) into the re-identification literature.

Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding