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 Multi-object tracking (MOT) is crucial to autonomous systems. Recent workuses a standard tracking-by-detection pipeline, where feature extraction isfirst performed independently for each object in order to compute an affinitymatrix. Then the affinity matrix is passed to the Hungarian algorithm for dataassociation. A key process of this standard pipeline is to learn discriminativefeatures for different objects in order to reduce confusion during dataassociation. In this work, we propose two techniques to improve thediscriminative feature learning for MOT: (1) instead of obtaining features foreach object independently, we propose a novel feature interaction mechanism byintroducing the Graph Neural Network. As a result, the feature of one object isinformed of the features of other objects so that the object feature can leantowards the object with similar feature (i.e., object probably with a same ID)and deviate from objects with dissimilar features (i.e., object probably withdifferent IDs), leading to a more discriminative feature for each object; (2)instead of obtaining the feature from either 2D or 3D space in prior work, wepropose a novel joint feature extractor to learn appearance and motion featuresfrom 2D and 3D space simultaneously. As features from different modalitiesoften have complementary information, the joint feature can be morediscriminate than feature from each individual modality. To ensure that thejoint feature extractor does not heavily rely on one modality, we also proposean ensemble training paradigm. Through extensive evaluation, our proposedmethod achieves state-of-the-art performance on KITTI and nuScenes 3D MOTbenchmarks. Our code will be made available athttps://github.com/xinshuoweng/GNN3DMOT

GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning