{"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/siam-r-cnn-visual-tracking-by-re-detection","title":"Siam R-CNN: Visual Tracking by Re-Detection","arxiv_id":"1911.12836","date":"2019-11-28","proceeding":"CVPR 2020 6","authors":["Paul Voigtlaender","Jonathon Luiten","Philip H. S. Torr","Bastian Leibe"],"abstract":"We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which takes advantage of re-detections of both the first-frame template and previous-frame predictions, to model the full history of both the object to be tracked and potential distractor objects. This enables our approach to make better tracking decisions, as well as to re-detect tracked objects after long occlusion. Finally, we propose a novel hard example mining strategy to improve Siam R-CNN's robustness to similar looking objects. Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. We make our code and models available at www.vision.rwth-aachen.de/page/siamrcnn.","url_abs":"https://arxiv.org/abs/1911.12836v2","url_pdf":"https://arxiv.org/pdf/1911.12836v2.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":"siam-r-cnn-visual-tracking-by-re-detection","repo_url":"https://github.com/VisualComputingInstitute/SiamR-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"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":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-tracking-on-coesot","task":"Object Tracking","dataset":"COESOT","model":"SiamR-CNN","rank_in_archive_order":5,"of":12,"metrics":{"Precision Rate":"67.5","Success Rate":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"Siam R-CNN","rank_in_archive_order":63,"of":78,"metrics":{"F-measure (Decay)":"4.0","F-measure (Mean)":"80.4","F-measure (Recall)":"87.6","J&F":"78.6","Jaccard (Decay)":"2.2","Jaccard (Mean)":"76.8","Jaccard (Recall)":"86.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"Siam R-CNN","rank_in_archive_order":50,"of":59,"metrics":{"F-measure (Decay)":"20.2","F-measure (Mean)":"58.6","F-measure (Recall)":"62.3","J&F":"53.3","Jaccard (Decay)":"21.8","Jaccard (Mean)":"48.0","Jaccard (Recall)":"53.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"Siam R-CNN","rank_in_archive_order":60,"of":81,"metrics":{"F-measure (Decay)":"16.2","F-measure (Mean)":"75.0","F-measure (Recall)":"82.8","J&F":"70.55","Jaccard (Decay)":"15.8","Jaccard (Mean)":"66.1","Jaccard (Recall)":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"Siam R-CNN","rank_in_archive_order":33,"of":42,"metrics":{"Average Overlap":"64.9","Success Rate 0.5":"72.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"Siam R-CNN","rank_in_archive_order":38,"of":46,"metrics":{"AUC":"64.8","Normalized Precision":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"Siam R-CNN","rank_in_archive_order":28,"of":40,"metrics":{"Accuracy":"81.2","Normalized Precision":"85.4","Precision":"80.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.12836","atlas_url":"https://app.syntology.ai/?focus=1911.12836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12836"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/VisualComputingInstitute/SiamR-CNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"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":"dd749a6b43682a14","entry":"box_to_point8","repo":"VisualComputingInstitute/SiamR-CNN","repo_kind":"listed","path":"common.py","file_url":"https://github.com/VisualComputingInstitute/SiamR-CNN/blob/HEAD/common.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd749a6b43682a14"}},{"code_sha256_prefix":"e99bbed8ef483eba","entry":"point8_to_box","repo":"VisualComputingInstitute/SiamR-CNN","repo_kind":"listed","path":"common.py","file_url":"https://github.com/VisualComputingInstitute/SiamR-CNN/blob/HEAD/common.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e99bbed8ef483eba"}},{"code_sha256_prefix":"69d5512d768ea9dd","entry":"freeze_affine_getter","repo":"VisualComputingInstitute/SiamR-CNN","repo_kind":"listed","path":"basemodel.py","file_url":"https://github.com/VisualComputingInstitute/SiamR-CNN/blob/HEAD/basemodel.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":"69d5512d768ea9dd"}},{"code_sha256_prefix":"72f76b2aba37ad06","entry":"segmentation_to_mask","repo":"VisualComputingInstitute/SiamR-CNN","repo_kind":"listed","path":"common.py","file_url":"https://github.com/VisualComputingInstitute/SiamR-CNN/blob/HEAD/common.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":"72f76b2aba37ad06"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}