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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The recent trend in multiple object tracking (MOT) is heading towardsleveraging deep learning to boost the tracking performance. In this paper, wepropose a novel solution named TransSTAM, which leverages Transformer toeffectively model both the appearance features of each object and thespatial-temporal relationships among objects. TransSTAM consists of two majorparts: (1) The encoder utilizes the powerful self-attention mechanism ofTransformer to learn discriminative features for each tracklet; (2) The decoderadopts the standard cross-attention mechanism to model the affinities betweenthe tracklets and the detections by taking both spatial-temporal and appearancefeatures into account. TransSTAM has two major advantages: (1) It is solelybased on the encoder-decoder architecture and enjoys a compact network design,hence being computationally efficient; (2) It can effectively learnspatial-temporal and appearance features within one model, hence achievingbetter tracking accuracy. The proposed method is evaluated on multiple publicbenchmarks including MOT16, MOT17, and MOT20, and it achieves a clearperformance improvement in both IDF1 and HOTA with respect to previousstate-of-the-art approaches on all the benchmarks. Our code is available at\url{https://github.com/icicle4/TranSTAM}.

Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking