{"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/a-twofold-siamese-network-for-real-time","title":"A Twofold Siamese Network for Real-Time Object Tracking","arxiv_id":"1802.08817","date":"2018-02-24","proceeding":"CVPR 2018 6","authors":["Anfeng He","Chong Luo","Xinmei Tian","Wen-Jun Zeng"],"abstract":"Observing that Semantic features learned in an image classification task and\nAppearance features learned in a similarity matching task complement each\nother, we build a twofold Siamese network, named SA-Siam, for real-time object\ntracking. SA-Siam is composed of a semantic branch and an appearance branch.\nEach branch is a similarity-learning Siamese network. An important design\nchoice in SA-Siam is to separately train the two branches to keep the\nheterogeneity of the two types of features. In addition, we propose a channel\nattention mechanism for the semantic branch. Channel-wise weights are computed\naccording to the channel activations around the target position. While the\ninherited architecture from SiamFC \\cite{SiamFC} allows our tracker to operate\nbeyond real-time, the twofold design and the attention mechanism significantly\nimprove the tracking performance. The proposed SA-Siam outperforms all other\nreal-time trackers by a large margin on OTB-2013/50/100 benchmarks.","url_abs":"http://arxiv.org/abs/1802.08817v1","url_pdf":"http://arxiv.org/pdf/1802.08817v1.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":"a-twofold-siamese-network-for-real-time","repo_url":"https://github.com/Microsoft/SA-Siam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-otb-2013","task":"Visual Object Tracking","dataset":"OTB-2013","model":"SA-Siam","rank_in_archive_order":2,"of":7,"metrics":{"AUC":"0.677"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"SA-Siam","rank_in_archive_order":14,"of":18,"metrics":{"AUC":"0.657"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-50","task":"Visual Object Tracking","dataset":"OTB-50","model":"SA-Siam","rank_in_archive_order":2,"of":4,"metrics":{"AUC":"0.610"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.08817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08817"}},"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/Microsoft/SA-Siam","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"19796cd7aaf0298b","entry":"downsample","repo":"Microsoft/SA-Siam","repo_kind":"listed","path":"datasets/vid.py","file_url":"https://github.com/Microsoft/SA-Siam/blob/HEAD/datasets/vid.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":"19796cd7aaf0298b"}},{"code_sha256_prefix":"ca914fa2a746770c","entry":"upsample","repo":"Microsoft/SA-Siam","repo_kind":"listed","path":"datasets/vid.py","file_url":"https://github.com/Microsoft/SA-Siam/blob/HEAD/datasets/vid.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":"ca914fa2a746770c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}