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

3D single object tracking has been a crucial problem for decades withnumerous applications such as autonomous driving. Despite its wide-ranging use,this task remains challenging due to the significant appearance variationcaused by occlusion and size differences among tracked targets. To addressthese issues, we present MBPTrack, which adopts a Memory mechanism to utilizepast information and formulates localization in a coarse-to-fine scheme usingBox Priors given in the first frame. Specifically, past frames with targetnessmasks serve as an external memory, and a transformer-based module propagatestracked target cues from the memory to the current frame. To precisely localizeobjects of all sizes, MBPTrack first predicts the target center via Houghvoting. By leveraging box priors given in the first frame, we adaptively samplereference points around the target center that roughly cover the target ofdifferent sizes. Then, we obtain dense feature maps by aggregating pointfeatures into the reference points, where localization can be performed moreeffectively. Extensive experiments demonstrate that MBPTrack achievesstate-of-the-art performance on KITTI, nuScenes and Waymo Open Dataset, whilerunning at 50 FPS on a single RTX3090 GPU.

MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors