{"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/trackingnet-a-large-scale-dataset-and","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","arxiv_id":"1803.10794","date":"2018-03-28","proceeding":"ECCV 2018 9","authors":["Matthias Müller","Adel Bibi","Silvio Giancola","Salman Al-Subaihi","Bernard Ghanem"],"abstract":"Despite the numerous developments in object tracking, further development of\ncurrent tracking algorithms is limited by small and mostly saturated datasets.\nAs a matter of fact, data-hungry trackers based on deep-learning currently rely\non object detection datasets due to the scarcity of dedicated large-scale\ntracking datasets. In this work, we present TrackingNet, the first large-scale\ndataset and benchmark for object tracking in the wild. We provide more than 30K\nvideos with more than 14 million dense bounding box annotations. Our dataset\ncovers a wide selection of object classes in broad and diverse context. By\nreleasing such a large-scale dataset, we expect deep trackers to further\nimprove and generalize. In addition, we introduce a new benchmark composed of\n500 novel videos, modeled with a distribution similar to our training dataset.\nBy sequestering the annotation of the test set and providing an online\nevaluation server, we provide a fair benchmark for future development of object\ntrackers. Deep trackers fine-tuned on a fraction of our dataset improve their\nperformance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We\nprovide an extensive benchmark on TrackingNet by evaluating more than 20\ntrackers. Our results suggest that object tracking in the wild is far from\nbeing solved.","url_abs":"http://arxiv.org/abs/1803.10794v1","url_pdf":"http://arxiv.org/pdf/1803.10794v1.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":"trackingnet-a-large-scale-dataset-and","repo_url":"https://github.com/SilvioGiancola/TrackingNet-devkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"trackingnet","name":"TrackingNet","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10794","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}