{"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/bit-biologically-inspired-tracker","title":"BIT: Biologically Inspired Tracker","arxiv_id":"1904.10411","date":"2019-04-23","proceeding":null,"authors":["Bolun Cai","Xiangmin Xu","Xiaofen Xing","Kui Jia","Jie Miao","DaCheng Tao"],"abstract":"Visual tracking is challenging due to image variations caused by various\nfactors, such as object deformation, scale change, illumination change and\nocclusion. Given the superior tracking performance of human visual system\n(HVS), an ideal design of biologically inspired model is expected to improve\ncomputer visual tracking. This is however a difficult task due to the\nincomplete understanding of neurons' working mechanism in HVS. This paper aims\nto address this challenge based on the analysis of visual cognitive mechanism\nof the ventral stream in the visual cortex, which simulates shallow neurons (S1\nunits and C1 units) to extract low-level biologically inspired features for the\ntarget appearance and imitates an advanced learning mechanism (S2 units and C2\nunits) to combine generative and discriminative models for target location. In\naddition, fast Gabor approximation (FGA) and fast Fourier transform (FFT) are\nadopted for real-time learning and detection in this framework. Extensive\nexperiments on large-scale benchmark datasets show that the proposed\nbiologically inspired tracker performs favorably against state-of-the-art\nmethods in terms of efficiency, accuracy, and robustness. The acceleration\ntechnique in particular ensures that BIT maintains a speed of approximately 45\nframes per second.","url_abs":"http://arxiv.org/abs/1904.10411v1","url_pdf":"http://arxiv.org/pdf/1904.10411v1.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":"bit-biologically-inspired-tracker","repo_url":"https://github.com/caibolun/BIT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}