The Second-place Solution for CVPR 2022 SoccerNet Tracking Challenge
Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang

TL;DR
This paper presents a high-performing two-step tracking solution for SoccerNet, combining online short-term tracking with offline long-term tracking, achieving state-of-the-art accuracy in the CVPR 2022 challenge.
Contribution
The paper introduces a novel Cascaded Buffer-IoU Tracker and a hierarchical clustering method for offline long-term tracking, enhancing tracking accuracy.
Findings
Online tracking achieved HOTA scores near 90
Offline tracking improved HOTA to around 93.2
Method outperforms previous solutions in SoccerNet challenge
Abstract
This is our second-place solution for CVPR 2022 SoccerNet Tracking Challenge. Our method mainly includes two steps: online short-term tracking using our Cascaded Buffer-IoU (C-BIoU) Tracker, and, offline long-term tracking using appearance feature and hierarchical clustering. At each step, online tracking yielded HOTA scores near 90, and offline tracking further improved HOTA scores to around 93.2.
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Analysis and Summarization · Anomaly Detection Techniques and Applications · Music and Audio Processing
