UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Tracking by animation: Unsupervised learning of multi-object attentive trackers

He, Z; Li, J; Liu, D; He, H; Barber, D; (2020) Tracking by animation: Unsupervised learning of multi-object attentive trackers. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 1318-1327). IEEE: Long Beach, CA, USA. Green open access

[img]
Preview
Text
He_Tracking_by_Animation_Unsupervised_Learning_of_Multi-Object_Attentive_Trackers_CVPR_2019_paper.pdf - Accepted version

Download (1MB) | Preview

Abstract

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with popular machine learning approaches which largely reduce the human effort to tune algorithm parameters. However, the commonly used supervised learning approaches require the labeled data (e.g., bounding boxes), which is expensive for videos. Also, the TBD framework is usually suboptimal since it is not end-to-end, i.e., it considers the task as detection and tracking, but not jointly. To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames. Learning is then driven by the reconstruction error through backpropagation. We further propose a Reprioritized Attentive Tracking to improve the robustness of data association. Experiments conducted on both synthetic and real video datasets show the potential of the proposed model. Our project page is publicly available at: https://github.com/zhen-he/tracking-by-animation.

Type: Proceedings paper
Title: Tracking by animation: Unsupervised learning of multi-object attentive trackers
Event: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISBN-13: 9781728132938
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2019.00141
Publisher version: https://doi.org/10.1109/CVPR.2019.00141
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Motion and Tracking, Deep Learning, Representation Learning, Vision + Graphics, Visual Reasoning
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10091658
Downloads since deposit
99Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item