TL;DR
GOT-10k is a comprehensive, large-scale benchmark dataset for generic object tracking in the wild, featuring diverse classes, a new evaluation protocol, and extensive baseline experiments to advance tracker development.
Contribution
It introduces a large, diverse tracking dataset based on WordNet hierarchy, a novel zero-overlap evaluation protocol, and a comprehensive platform for the tracking community.
Findings
39 tracking algorithms evaluated on GOT-10k
GOT-10k covers over 560 object classes and 87 motion patterns
The dataset enables unbiased, generalizable tracker evaluation
Abstract
We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts. The contributions of this paper are summarized in the following: (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped. The protocol…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
