{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lasot-a-high-quality-benchmark-for-large","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","arxiv_id":"1809.07845","date":"2018-09-20","proceeding":"CVPR 2019 6","authors":["Heng Fan","Liting Lin","Fan Yang","Peng Chu","Ge Deng","Sijia Yu","Hexin Bai","Yong Xu","Chunyuan Liao","Haibin Ling"],"abstract":"In this paper, we present LaSOT, a high-quality benchmark for Large-scale\nSingle Object Tracking. LaSOT consists of 1,400 sequences with more than 3.5M\nframes in total. Each frame in these sequences is carefully and manually\nannotated with a bounding box, making LaSOT the largest, to the best of our\nknowledge, densely annotated tracking benchmark. The average video length of\nLaSOT is more than 2,500 frames, and each sequence comprises various challenges\nderiving from the wild where target objects may disappear and re-appear again\nin the view. By releasing LaSOT, we expect to provide the community with a\nlarge-scale dedicated benchmark with high quality for both the training of deep\ntrackers and the veritable evaluation of tracking algorithms. Moreover,\nconsidering the close connections of visual appearance and natural language, we\nenrich LaSOT by providing additional language specification, aiming at\nencouraging the exploration of natural linguistic feature for tracking. A\nthorough experimental evaluation of 35 tracking algorithms on LaSOT is\npresented with detailed analysis, and the results demonstrate that there is\nstill a big room for improvements.","url_abs":"http://arxiv.org/abs/1809.07845v2","url_pdf":"http://arxiv.org/pdf/1809.07845v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lasot-a-high-quality-benchmark-for-large","repo_url":"https://github.com/HengLan/LaSOT_Evaluation_Toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[{"slug":"lasot","name":"LaSOT","full_name":"Large-scale Single Object Tracking"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07845","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}