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

Multi-object tracking is a fundamental vision problem that has been studiedfor a long time. As deep learning brings excellent performances to objectdetection algorithms, Tracking by Detection (TBD) has become the mainstreamtracking framework. Despite the success of TBD, this two-step method is toocomplicated to train in an end-to-end manner and induces many challenges aswell, such as insufficient exploration of video spatial-temporal information,vulnerability when facing object occlusion, and excessive reliance on detectionresults. To address these challenges, we propose a concise end-to-end modelTubeTK which only needs one step training by introducing the ``bounding-tube"to indicate temporal-spatial locations of objects in a short video clip. TubeTKprovides a novel direction of multi-object tracking, and we demonstrate itspotential to solve the above challenges without bells and whistles. We analyzethe performance of TubeTK on several MOT benchmarks and provide empiricalevidence to show that TubeTK has the ability to overcome occlusions to someextent without any ancillary technologies like Re-ID. Compared with othermethods that adopt private detection results, our one-stage end-to-end modelachieves state-of-the-art performances even if it adopts no ready-madedetection results. We hope that the proposed TubeTK model can serve as a simplebut strong alternative for video-based MOT task. The code and models areavailable at https://github.com/BoPang1996/TubeTK.

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model