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

Person re-identification (ReID) is aimed at identifying the same personacross videos captured from different cameras. In the view that networksextracting global features using ordinary network architectures are difficultto extract local features due to their weak attention mechanisms, researchershave proposed a lot of elaborately designed ReID networks, while greatlyimproving the accuracy, the model size and the feature extraction latency arealso soaring. We argue that a relatively compact ordinary network extractingglobally pooled features has the capability to extract discriminative localfeatures and can achieve state-of-the-art precision if only the model'sparameters are properly learnt. In order to reduce the difficulty in learninghard identity labels, we propose a novel knowledge distillation method:Factorized Distillation, which factorizes both feature maps and retrievalfeatures of holistic ReID network to mimic representations of multiple partialReID models, thus transferring the knowledge from partial ReID models to theholistic network. Experiments show that the performance of model trained withthe proposed method can outperform state-of-the-art with relatively few networkparameters.

Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models