{"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/learning-to-track-at-100-fps-with-deep","title":"Learning to Track at 100 FPS with Deep Regression Networks","arxiv_id":"1604.01802","date":"2016-04-06","proceeding":null,"authors":["David Held","Sebastian Thrun","Silvio Savarese"],"abstract":"Machine learning techniques are often used in computer vision due to their\nability to leverage large amounts of training data to improve performance.\nUnfortunately, most generic object trackers are still trained from scratch\nonline and do not benefit from the large number of videos that are readily\navailable for offline training. We propose a method for offline training of\nneural networks that can track novel objects at test-time at 100 fps. Our\ntracker is significantly faster than previous methods that use neural networks\nfor tracking, which are typically very slow to run and not practical for\nreal-time applications. Our tracker uses a simple feed-forward network with no\nonline training required. The tracker learns a generic relationship between\nobject motion and appearance and can be used to track novel objects that do not\nappear in the training set. We test our network on a standard tracking\nbenchmark to demonstrate our tracker's state-of-the-art performance. Further,\nour performance improves as we add more videos to our offline training set. To\nthe best of our knowledge, our tracker is the first neural-network tracker that\nlearns to track generic objects at 100 fps.","url_abs":"http://arxiv.org/abs/1604.01802v2","url_pdf":"http://arxiv.org/pdf/1604.01802v2.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":"learning-to-track-at-100-fps-with-deep","repo_url":"https://github.com/davheld/GOTURN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-track-at-100-fps-with-deep","repo_url":"https://github.com/nrupatunga/PY-GOTURN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-track-at-100-fps-with-deep","repo_url":"https://github.com/nrupatunga/goturn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.01802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.01802"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nrupatunga/goturn-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nrupatunga/PY-GOTURN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davheld/GOTURN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6a6b06075546fa8a","entry":"computeCropPadImageLocation","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/image_proc.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/image_proc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a6b06075546fa8a"}},{"code_sha256_prefix":"fba892526abf688d","entry":"cropPadImage","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/image_proc.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/image_proc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fba892526abf688d"}},{"code_sha256_prefix":"3d636918f322cabc","entry":"image_to_tensor","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/image_io.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/image_io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d636918f322cabc"}},{"code_sha256_prefix":"4a38735b9863f21c","entry":"load","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/image_io.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/image_io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a38735b9863f21c"}},{"code_sha256_prefix":"027d7a0fd56afc0b","entry":"load_grayscale","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/image_io.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/image_io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"027d7a0fd56afc0b"}},{"code_sha256_prefix":"897e5bce9dfb1804","entry":"sample_exp_two_sides","repo":"nrupatunga/goturn-pytorch","repo_kind":"listed","path":"src/goturn/helper/helper.py","file_url":"https://github.com/nrupatunga/goturn-pytorch/blob/HEAD/src/goturn/helper/helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"897e5bce9dfb1804"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}