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

Data association across frames is at the core of Multiple Object Tracking(MOT) task. This problem is usually solved by a traditional graph-basedoptimization or directly learned via deep learning. Despite their popularity,we find some points worth studying in current paradigm: 1) Existing methodsmostly ignore the context information among tracklets and intra-framedetections, which makes the tracker hard to survive in challenging cases likesevere occlusion. 2) The end-to-end association methods solely rely on the datafitting power of deep neural networks, while they hardly utilize the advantageof optimization-based assignment methods. 3) The graph-based optimizationmethods mostly utilize a separate neural network to extract features, whichbrings the inconsistency between training and inference. Therefore, in thispaper we propose a novel learnable graph matching method to address theseissues. Briefly speaking, we model the relationships between tracklets and theintra-frame detections as a general undirected graph. Then the associationproblem turns into a general graph matching between tracklet graph anddetection graph. Furthermore, to make the optimization end-to-enddifferentiable, we relax the original graph matching into continuous quadraticprogramming and then incorporate the training of it into a deep graph networkwith the help of the implicit function theorem. Lastly, our method GMTracker,achieves state-of-the-art performance on several standard MOT datasets. Ourcode will be available at https://github.com/jiaweihe1996/GMTracker .

Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking