{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/ocean-object-aware-anchor-free-tracking","title":"Ocean: Object-aware Anchor-free Tracking","arxiv_id":"2006.10721","date":"2020-06-18","proceeding":"ECCV 2020 8","authors":["Zhipeng Zhang","Houwen Peng","Jianlong Fu","Bing Li","Weiming Hu"],"abstract":"Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., $IoU \\geq0.6$). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at https://github.com/researchmm/TracKit.","url_abs":"https://arxiv.org/abs/2006.10721v2","url_pdf":"https://arxiv.org/pdf/2006.10721v2.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":"ocean-object-aware-anchor-free-tracking","repo_url":"https://github.com/researchmm/TracKit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ocean-object-aware-anchor-free-tracking","repo_url":"https://github.com/researchmm/SiamDW","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ocean-object-aware-anchor-free-tracking","repo_url":"https://github.com/2023-MindSpore-1/ms-code-218/tree/main/ocean_model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ocean-object-aware-anchor-free-tracking","repo_url":"https://github.com/code-implementation1/Code9/tree/main/ocean_model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"Ocean","rank_in_archive_order":26,"of":43,"metrics":{"AUC":"32.86","Precision":"46.72"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"Ocean","rank_in_archive_order":39,"of":42,"metrics":{"Average Overlap":"61.1","Success Rate 0.5":"72.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot2018","task":"Visual Object Tracking","dataset":"VOT2018","model":"Ocean","rank_in_archive_order":2,"of":2,"metrics":{"Expected Average Overlap (EAO)":"0.467"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot2019","task":"Visual Object Tracking","dataset":"VOT2019","model":"Ocean","rank_in_archive_order":2,"of":3,"metrics":{"Expected Average Overlap (EAO)":"0.327"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.10721","atlas_url":"https://app.syntology.ai/?focus=2006.10721","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2006.10721"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.10721\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.10721"},"call":"get_concepts_for_paper(arxiv_id=\"2006.10721\")"}],"by_repo":[{"repo":"researchmm/TracKit","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2008.02745"],"harvested_for_calls":[{"arxiv_id":"2008.02745","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2008.02745"},"call":"get_harvested_code_for_paper(arxiv_id=\"2008.02745\")"}]},{"repo":"researchmm/SiamDW","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["1409.4842","1512.03385","1901.01660"],"harvested_for_calls":[{"arxiv_id":"1409.4842","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1409.4842"},"call":"get_harvested_code_for_paper(arxiv_id=\"1409.4842\")"},{"arxiv_id":"1512.03385","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1512.03385"},"call":"get_harvested_code_for_paper(arxiv_id=\"1512.03385\")"},{"arxiv_id":"1901.01660","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.01660"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.01660\")"}]},{"repo":"2023-MindSpore-1/ms-code-218","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"code-implementation1/Code9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4552d92d75ec1edd4943e97f772bd72059747797b72e51123c9b0096fe4847f7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}