Without manually annotated identities, unsupervised multi-object trackers are inferior to
learning reliable feature embeddings. It causes the similarity-based inter-frame association …

This paper presents a new large scale multi-person tracking dataset. Our dataset is over an
order of magnitude larger than currently available high quality multi-object tracking datasets …

The development of person search techniques has been greatly promoted in recent years
for its superior practicality and challenging goals. Despite their significant progress, existing …

Download Copy BibTeX@ Article {Lu2024, author={Zijia Lu and Bing Shuai and Yanbei
Chen and Zhenlin Xu and Davide Modolo}, title={Self-supervised multi-object tracking with …

Large-scale pre-training has proven to be an effective method for improving performance
across different tasks. Current person search methods use ImageNet pre-trained models for …

End-to-end transformer-based trackers have achieved remarkable performance on most
human-related datasets. However, training these trackers in heterogeneous scenarios …

This paper introduces a novel framework to learn data association for multi-object tracking in
a self-supervised manner. Fully-supervised learning methods are known to achieve …

End-to-end transformer-based trackers have achieved remarkable performance on most
human-related datasets. However, training these trackers in heterogeneous scenarios …

Abstract Deep Metric Learning (DML) methods aim at learning an embedding space in
which distances are closely related to the inherent semantic similarity of the inputs. Previous …