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

Similarity learning has been recognized as a crucial step for objecttracking. However, existing multiple object tracking methods only use sparseground truth matching as the training objective, while ignoring the majority ofthe informative regions in images. In this paper, we present Quasi-DenseSimilarity Learning, which densely samples hundreds of object regions on a pairof images for contrastive learning. We combine this similarity learning withmultiple existing object detectors to build Quasi-Dense Tracking (QDTrack),which does not require displacement regression or motion priors. We find thatthe resulting distinctive feature space admits a simple nearest neighbor searchat inference time for object association. In addition, we show that oursimilarity learning scheme is not limited to video data, but can learneffective instance similarity even from static input, enabling a competitivetracking performance without training on videos or using tracking supervision.We conduct extensive experiments on a wide variety of popular MOT benchmarks.We find that, despite its simplicity, QDTrack rivals the performance ofstate-of-the-art tracking methods on all benchmarks and sets a newstate-of-the-art on the large-scale BDD100K MOT benchmark, while introducingnegligible computational overhead to the detector.

QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking