{"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":"/task/video-object-tracking","name":"Video Object Tracking","slug":"video-object-tracking","description_markdown":"Video Object Detection aims to detect targets in videos using both spatial and temporal information. It's usually deeply integrated with tasks such as Object Detection and Object Tracking.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":98,"papers_with_code":72,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":13,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","slug":"video-object-tracking-on-nv-vot211","dataset":"NT-VOT211","dataset_url":"/dataset/nv-vot211","rows_in_archive":43,"metrics":["AUC","Precision"],"first_row_in_archive_order":{"model":"ProContEXT","paper_title":"ProContEXT: Exploring Progressive Context Transformer for Tracking","paper_url":"/paper/procontext-exploring-progressive-context","paper_date":"2022-10-27","arxiv_id":"2210.15511","code_links":[{"title":"jp-lan/procontext","url":"https://github.com/jp-lan/procontext"},{"title":"yangyucheng000/Paper-4","url":"https://github.com/yangyucheng000/Paper-4/tree/main/ProC-KD-main"},{"title":"zhiqic/procontext","url":"https://github.com/zhiqic/procontext"},{"title":"yangyucheng000/papercode-2","url":"https://github.com/yangyucheng000/papercode-2/tree/main/ProC-KD-main"}],"syntology":null}},{"leaderboard":"/sota/video-object-tracking-on-cater","slug":"video-object-tracking-on-cater","dataset":"CATER","dataset_url":"/dataset/cater","rows_in_archive":7,"metrics":["Top 1 Accuracy","L1","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"Loci","paper_title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","paper_url":"/paper/learning-what-and-where-unsupervised","paper_date":"2022-05-26","arxiv_id":"2205.13349","code_links":[{"title":"CognitiveModeling/Loci","url":"https://github.com/CognitiveModeling/Loci"}],"syntology":null}},{"leaderboard":"/sota/video-object-tracking-on-got-10k-1","slug":"video-object-tracking-on-got-10k-1","dataset":"GOT-10k","dataset_url":"/dataset/got-10k","rows_in_archive":1,"metrics":["Average Overlap"],"first_row_in_archive_order":{"model":"TATrack-L-GOT","paper_title":"Target-Aware Tracking with Long-term Context Attention","paper_url":"/paper/target-aware-tracking-with-long-term-context","paper_date":"2023-02-27","arxiv_id":"2302.13840","code_links":[{"title":"hekaijie123/TATrack","url":"https://github.com/hekaijie123/TATrack"}],"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/target-aware-tracking-with-long-term-context#ran","syntology_url":"https://syntology.ai/paper/2302.13840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13840"}},"official":{"repos":["hekaijie123/TATrack"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/video-object-tracking-on-soccernet-v2","slug":"video-object-tracking-on-soccernet-v2","dataset":"SoccerNet-v2","dataset_url":"/dataset/soccernet-v2","rows_in_archive":1,"metrics":["HOTA"],"first_row_in_archive_order":{"model":"CO-MOT","paper_title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","paper_url":"/paper/bridging-the-gap-between-end-to-end-and-non","paper_date":"2023-05-22","arxiv_id":"2305.12724","code_links":[{"title":"bingfengyan/visam","url":"https://github.com/bingfengyan/visam"},{"title":"BingfengYan/CO-MOT","url":"https://github.com/BingfengYan/CO-MOT"}],"syntology":null}}],"datasets":[{"url":"/dataset/got-10k","name":"GOT-10k","full_name":"Generic Object Tracking Benchmark","num_papers_in_archive":239},{"url":"/dataset/soccernet-v2","name":"SoccerNet-v2","full_name":"","num_papers_in_archive":58},{"url":"/dataset/cater","name":"CATER","full_name":"","num_papers_in_archive":51},{"url":"/dataset/nv-vot211","name":"NT-VOT211","full_name":"","num_papers_in_archive":41},{"url":"/dataset/vot","name":"VOTChallenge","full_name":"Visual Object Tracking","num_papers_in_archive":36},{"url":"/dataset/vot2014","name":"VOT2014","full_name":"Visual Object Tracking Challenge 2014","num_papers_in_archive":12},{"url":"/dataset/bl30k","name":"BL30K","full_name":"","num_papers_in_archive":11},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/trek150","name":"TREK-150","full_name":"","num_papers_in_archive":7},{"url":"/dataset/videocube","name":"VideoCube","full_name":"","num_papers_in_archive":6},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/sotverse","name":"SOTVerse","full_name":"","num_papers_in_archive":1},{"url":"/dataset/visem-tracking","name":"VISEM-Tracking","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/object-tracking","name":"Object Tracking"},{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":98,"of":98,"of_with_code":72,"tagged_in_all":98,"counts":{"archive_papers_tagged":98,"with_a_code_link":72,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":98,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":25,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":25,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","repositories_listed":34,"syntology":{"n":28,"n_ran":16,"n_constructed":7,"n_ran_checked":10,"n_instrument":6,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}},"official":null}},{"url":"/paper/yolov7-trainable-bag-of-freebies-sets-new","slug":"yolov7-trainable-bag-of-freebies-sets-new","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","date":"2022-07-06","arxiv_id":"2207.02696","repositories_listed":21,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}},"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","repositories_listed":13,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}},"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/high-speed-tracking-with-kernelized","slug":"high-speed-tracking-with-kernelized","title":"High-Speed Tracking with Kernelized Correlation Filters","date":"2014-04-30","arxiv_id":"1404.7584","repositories_listed":9,"syntology":null},{"url":"/paper/deeper-and-wider-siamese-networks-for-real","slug":"deeper-and-wider-siamese-networks-for-real","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","date":"2019-01-07","arxiv_id":"1901.01660","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deeper-and-wider-siamese-networks-for-real#ran","syntology_url":"https://syntology.ai/paper/1901.01660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01660"}},"official":{"repos":["researchmm/SiamDW"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fully-convolutional-siamese-networks-for","slug":"fully-convolutional-siamese-networks-for","title":"Fully Convolutional Siamese Networks for Change Detection","date":"2018-10-19","arxiv_id":"1810.08462","repositories_listed":5,"syntology":null},{"url":"/paper/high-performance-visual-tracking-with-siamese","slug":"high-performance-visual-tracking-with-siamese","title":"High Performance Visual Tracking With Siamese Region Proposal Network","date":"2018-06-01","arxiv_id":null,"repositories_listed":5,"syntology":null},{"url":"/paper/procontext-exploring-progressive-context","slug":"procontext-exploring-progressive-context","title":"ProContEXT: Exploring Progressive Context Transformer for Tracking","date":"2022-10-27","arxiv_id":"2210.15511","repositories_listed":4,"syntology":null},{"url":"/paper/video-polyp-segmentation-a-deep-learning","slug":"video-polyp-segmentation-a-deep-learning","title":"Video Polyp Segmentation: A Deep Learning Perspective","date":"2022-03-27","arxiv_id":"2203.14291","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-polyp-segmentation-a-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2203.14291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14291"}},"official":{"repos":["DengPingFan/PraNet","GewelsJI/PNS-Net","gewelsji/vps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/ocean-object-aware-anchor-free-tracking","slug":"ocean-object-aware-anchor-free-tracking","title":"Ocean: Object-aware Anchor-free Tracking","date":"2020-06-18","arxiv_id":"2006.10721","repositories_listed":4,"syntology":null},{"url":"/paper/fast-online-object-tracking-and-segmentation","slug":"fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","date":"2018-12-12","arxiv_id":"1812.05050","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fast-online-object-tracking-and-segmentation#ran","syntology_url":"https://syntology.ai/paper/1812.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05050"}},"official":null}},{"url":"/paper/staple-complementary-learners-for-real-time","slug":"staple-complementary-learners-for-real-time","title":"Staple: Complementary Learners for Real-Time Tracking","date":"2015-12-04","arxiv_id":"1512.01355","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/staple-complementary-learners-for-real-time#ran","syntology_url":"https://syntology.ai/paper/1512.01355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.01355"}},"official":null}},{"url":"/paper/2408-00874","slug":"2408-00874","title":"Medical SAM 2: Segment medical images as video via Segment Anything Model 2","date":"2024-08-01","arxiv_id":"2408.00874","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-00874#ran","syntology_url":"https://syntology.ai/paper/2408.00874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00874"}},"official":{"repos":["medicinetoken/medical-sam2"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-generalist-and-blind-rgb-x-tracker","slug":"towards-a-generalist-and-blind-rgb-x-tracker","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","date":"2024-05-28","arxiv_id":"2405.17773","repositories_listed":2,"syntology":null},{"url":"/paper/bridging-the-gap-between-end-to-end-and-non","slug":"bridging-the-gap-between-end-to-end-and-non","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","date":"2023-05-22","arxiv_id":"2305.12724","repositories_listed":2,"syntology":null},{"url":"/paper/towards-sequence-level-training-for-visual","slug":"towards-sequence-level-training-for-visual","title":"Towards Sequence-Level Training for Visual Tracking","date":"2022-08-11","arxiv_id":"2208.05810","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-sequence-level-training-for-visual#ran","syntology_url":"https://syntology.ai/paper/2208.05810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05810"}},"official":{"repos":["byminji/SLTtrack"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-visual-tracking-by-segmentation","slug":"robust-visual-tracking-by-segmentation","title":"Robust Visual Tracking by Segmentation","date":"2022-03-21","arxiv_id":"2203.11191","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-visual-tracking-with-exemplar","slug":"efficient-visual-tracking-with-exemplar","title":"Efficient Visual Tracking with Exemplar Transformers","date":"2021-12-17","arxiv_id":"2112.09686","repositories_listed":2,"syntology":null},{"url":"/paper/cater-a-diagnostic-dataset-for-compositional","slug":"cater-a-diagnostic-dataset-for-compositional","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","date":"2019-10-10","arxiv_id":"1910.04744","repositories_listed":2,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cater-a-diagnostic-dataset-for-compositional#ran","syntology_url":"https://syntology.ai/paper/1910.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04744"}},"official":null}},{"url":"/paper/190407220","slug":"190407220","title":"Learning Discriminative Model Prediction for Tracking","date":"2019-04-15","arxiv_id":"1904.07220","repositories_listed":2,"syntology":null},{"url":"/paper/robust-estimation-of-similarity","slug":"robust-estimation-of-similarity","title":"Robust Estimation of Similarity Transformation for Visual Object Tracking","date":"2017-12-14","arxiv_id":"1712.05231","repositories_listed":2,"syntology":null},{"url":"/paper/him2sam-enhancing-sam2-with-hierarchical","slug":"him2sam-enhancing-sam2-with-hierarchical","title":"HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking","date":"2025-07-10","arxiv_id":"2507.07603","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-multimodal-spatial-temporal","slug":"exploiting-multimodal-spatial-temporal","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","date":"2024-12-20","arxiv_id":"2412.15691","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploiting-multimodal-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2412.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15691"}},"official":{"repos":["nju-pcalab/sttrack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-enhanced-contextual-information-for-1","slug":"exploring-enhanced-contextual-information-for-1","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","date":"2024-12-15","arxiv_id":"2412.11023","repositories_listed":1,"syntology":null},{"url":"/paper/referring-video-object-segmentation-via","slug":"referring-video-object-segmentation-via","title":"Referring Video Object Segmentation via Language-aligned Track Selection","date":"2024-12-02","arxiv_id":"2412.01136","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-vlms-to-localize-specific-objects","slug":"teaching-vlms-to-localize-specific-objects","title":"Teaching VLMs to Localize Specific Objects from In-context Examples","date":"2024-11-20","arxiv_id":"2411.13317","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-vlms-to-localize-specific-objects#ran","syntology_url":"https://syntology.ai/paper/2411.13317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13317"}},"official":{"repos":["sivandoveh/iploc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/depth-attention-for-robust-rgb-tracking","slug":"depth-attention-for-robust-rgb-tracking","title":"Depth Attention for Robust RGB Tracking","date":"2024-10-27","arxiv_id":"2410.20395","repositories_listed":1,"syntology":null},{"url":"/paper/nt-vot211-a-large-scale-benchmark-for-night","slug":"nt-vot211-a-large-scale-benchmark-for-night","title":"NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking","date":"2024-10-27","arxiv_id":"2410.20421","repositories_listed":1,"syntology":null},{"url":"/paper/associate-everything-detected-facilitating","slug":"associate-everything-detected-facilitating","title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","date":"2024-09-14","arxiv_id":"2409.09293","repositories_listed":1,"syntology":null},{"url":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}},"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/odtrack-online-dense-temporal-token-learning","slug":"odtrack-online-dense-temporal-token-learning","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","date":"2024-01-03","arxiv_id":"2401.01686","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/odtrack-online-dense-temporal-token-learning#ran","syntology_url":"https://syntology.ai/paper/2401.01686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01686"}},"official":{"repos":["gxnu-zhonglab/odtrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/artrackv2-prompting-autoregressive-tracker","slug":"artrackv2-prompting-autoregressive-tracker","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","date":"2023-12-28","arxiv_id":"2312.17133","repositories_listed":1,"syntology":null},{"url":"/paper/single-model-and-any-modality-for-video","slug":"single-model-and-any-modality-for-video","title":"Single-Model and Any-Modality for Video Object Tracking","date":"2023-11-27","arxiv_id":"2311.15851","repositories_listed":1,"syntology":null},{"url":"/paper/track-anything-segment-anything-meets-videos","slug":"track-anything-segment-anything-meets-videos","title":"Track Anything: Segment Anything Meets Videos","date":"2023-04-24","arxiv_id":"2304.11968","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/track-anything-segment-anything-meets-videos#ran","syntology_url":"https://syntology.ai/paper/2304.11968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11968"}},"official":{"repos":["gaomingqi/track-anything"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/target-aware-tracking-with-long-term-context","slug":"target-aware-tracking-with-long-term-context","title":"Target-Aware Tracking with Long-term Context Attention","date":"2023-02-27","arxiv_id":"2302.13840","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/target-aware-tracking-with-long-term-context#ran","syntology_url":"https://syntology.ai/paper/2302.13840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13840"}},"official":{"repos":["hekaijie123/TATrack"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/autoregressive-visual-tracking","slug":"autoregressive-visual-tracking","title":"Autoregressive Visual Tracking","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neighbortrack-improving-single-object","slug":"neighbortrack-improving-single-object","title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","date":"2022-11-12","arxiv_id":"2211.06663","repositories_listed":1,"syntology":null},{"url":"/paper/a-real-time-wrong-way-vehicle-detection-based","slug":"a-real-time-wrong-way-vehicle-detection-based","title":"A Real-Time Wrong-Way Vehicle Detection Based on YOLO and Centroid Tracking","date":"2022-10-19","arxiv_id":"2210.10226","repositories_listed":1,"syntology":null},{"url":"/paper/aiatrack-attention-in-attention-for","slug":"aiatrack-attention-in-attention-for","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","date":"2022-07-20","arxiv_id":"2207.09603","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/aiatrack-attention-in-attention-for#ran","syntology_url":"https://syntology.ai/paper/2207.09603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09603"}},"official":{"repos":["Little-Podi/AiATrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-grand-unification-of-object-tracking","slug":"towards-grand-unification-of-object-tracking","title":"Towards Grand Unification of Object Tracking","date":"2022-07-14","arxiv_id":"2207.07078","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":1,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-grand-unification-of-object-tracking#ran","syntology_url":"https://syntology.ai/paper/2207.07078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07078"}},"official":{"repos":["masterbin-iiau/unicorn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/learning-what-and-where-unsupervised","slug":"learning-what-and-where-unsupervised","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","date":"2022-05-26","arxiv_id":"2205.13349","repositories_listed":1,"syntology":null},{"url":"/paper/revealing-the-dark-secrets-of-masked-image","slug":"revealing-the-dark-secrets-of-masked-image","title":"Revealing the Dark Secrets of Masked Image Modeling","date":"2022-05-26","arxiv_id":"2205.13543","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revealing-the-dark-secrets-of-masked-image#ran","syntology_url":"https://syntology.ai/paper/2205.13543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13543"}},"official":{"repos":["SwinTransformer/MIM-Depth-Estimation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-feature-learning-and-relation-modeling","slug":"joint-feature-learning-and-relation-modeling","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","date":"2022-03-22","arxiv_id":"2203.11991","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/joint-feature-learning-and-relation-modeling#ran","syntology_url":"https://syntology.ai/paper/2203.11991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11991"}},"official":{"repos":["botaoye/ostrack"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/mixformer-end-to-end-tracking-with-iterative-1","slug":"mixformer-end-to-end-tracking-with-iterative-1","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","date":"2022-03-21","arxiv_id":"2203.11082","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/mixformer-end-to-end-tracking-with-iterative-1#ran","syntology_url":"https://syntology.ai/paper/2203.11082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11082"}},"official":{"repos":["MCG-NJU/MixFormer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transforming-model-prediction-for-tracking","slug":"transforming-model-prediction-for-tracking","title":"Transforming Model Prediction for Tracking","date":"2022-03-21","arxiv_id":"2203.11192","repositories_listed":1,"syntology":null},{"url":"/paper/bundletrack-6d-pose-tracking-for-novel","slug":"bundletrack-6d-pose-tracking-for-novel","title":"BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models","date":"2021-08-01","arxiv_id":"2108.00516","repositories_listed":1,"syntology":null},{"url":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_constructed":4,"n_ran_checked":4,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}},"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/adtrack-target-aware-dual-filter-learning-for","slug":"adtrack-target-aware-dual-filter-learning-for","title":"ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking","date":"2021-06-04","arxiv_id":"2106.02495","repositories_listed":1,"syntology":null},{"url":"/paper/lighttrack-finding-lightweight-neural","slug":"lighttrack-finding-lightweight-neural","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","date":"2021-04-29","arxiv_id":"2104.14545","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":2,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lighttrack-finding-lightweight-neural#ran","syntology_url":"https://syntology.ai/paper/2104.14545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14545"}},"official":{"repos":["researchmm/LightTrack"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stmtrack-template-free-visual-tracking-with","slug":"stmtrack-template-free-visual-tracking-with","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","date":"2021-04-01","arxiv_id":"2104.00324","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":2,"n_ran_checked":2,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stmtrack-template-free-visual-tracking-with#ran","syntology_url":"https://syntology.ai/paper/2104.00324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00324"}},"official":{"repos":["fzh0917/STMTrack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-spatio-temporal-transformer-for","slug":"learning-spatio-temporal-transformer-for","title":"Learning Spatio-Temporal Transformer for Visual Tracking","date":"2021-03-31","arxiv_id":"2103.17154","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-spatio-temporal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2103.17154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17154"}},"official":{"repos":["researchmm/Stark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-target-candidate-association-to-keep","slug":"learning-target-candidate-association-to-keep","title":"Learning Target Candidate Association to Keep Track of What Not to Track","date":"2021-03-30","arxiv_id":"2103.16556","repositories_listed":1,"syntology":null},{"url":"/paper/2103-15436","slug":"2103-15436","title":"Transformer Tracking","date":"2021-03-29","arxiv_id":"2103.15436","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/2103-15436#ran","syntology_url":"https://syntology.ai/paper/2103.15436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15436"}},"official":{"repos":["chenxin-dlut/TransT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transformer-meets-tracker-exploiting-temporal","slug":"transformer-meets-tracker-exploiting-temporal","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","date":"2021-03-22","arxiv_id":"2103.11681","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":5,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/transformer-meets-tracker-exploiting-temporal#ran","syntology_url":"https://syntology.ai/paper/2103.11681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11681"}},"official":{"repos":["594422814/TransformerTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hopper-multi-hop-transformer-for-1","slug":"hopper-multi-hop-transformer-for-1","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","date":"2021-03-19","arxiv_id":"2103.10574","repositories_listed":1,"syntology":null},{"url":"/paper/tdiot-target-driven-inference-for-deep-video","slug":"tdiot-target-driven-inference-for-deep-video","title":"TDIOT: Target-driven Inference for Deep Video Object Tracking","date":"2021-03-19","arxiv_id":"2103.11017","repositories_listed":1,"syntology":null},{"url":"/paper/object-based-attention-for-spatio-temporal","slug":"object-based-attention-for-spatio-temporal","title":"Attention over learned object embeddings enables complex visual reasoning","date":"2020-12-15","arxiv_id":"2012.08508","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-transformation-for-self","slug":"contrastive-transformation-for-self","title":"Contrastive Transformation for Self-supervised Correspondence Learning","date":"2020-12-09","arxiv_id":"2012.05057","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-fuse-asymmetric-feature-maps-in","slug":"learning-to-fuse-asymmetric-feature-maps-in","title":"Learning to Fuse Asymmetric Feature Maps in Siamese Trackers","date":"2020-12-04","arxiv_id":"2012.02776","repositories_listed":1,"syntology":null},{"url":"/paper/approxdet-content-and-contention-aware","slug":"approxdet-content-and-contention-aware","title":"ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles","date":"2020-10-21","arxiv_id":"2010.10754","repositories_listed":1,"syntology":null},{"url":"/paper/a-distilled-model-for-tracking-and-tracker","slug":"a-distilled-model-for-tracking-and-tracker","title":"Tracking-by-Trackers with a Distilled and Reinforced Model","date":"2020-07-08","arxiv_id":"2007.04108","repositories_listed":1,"syntology":null},{"url":"/paper/fast-template-matching-and-update-for-video","slug":"fast-template-matching-and-update-for-video","title":"Fast Template Matching and Update for Video Object Tracking and Segmentation","date":"2020-04-16","arxiv_id":"2004.07538","repositories_listed":1,"syntology":null},{"url":"/paper/know-your-surroundings-exploiting-scene","slug":"know-your-surroundings-exploiting-scene","title":"Know Your Surroundings: Exploiting Scene Information for Object Tracking","date":"2020-03-24","arxiv_id":"2003.11014","repositories_listed":1,"syntology":null},{"url":"/paper/learning-object-permanence-from-video","slug":"learning-object-permanence-from-video","title":"Learning Object Permanence from Video","date":"2020-03-23","arxiv_id":"2003.10469","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-object-permanence-from-video#ran","syntology_url":"https://syntology.ai/paper/2003.10469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10469"}},"official":null}},{"url":"/paper/argus-efficient-activity-detection-system-for","slug":"argus-efficient-activity-detection-system-for","title":"Argus: Efficient Activity Detection System for Extended Video Analysis","date":"2020-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spatial-aware-online-adversarial","slug":"spatial-aware-online-adversarial","title":"SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking","date":"2019-10-19","arxiv_id":"1910.08681","repositories_listed":1,"syntology":null},{"url":"/paper/fast-visual-object-tracking-with-rotated","slug":"fast-visual-object-tracking-with-rotated","title":"Fast Visual Object Tracking with Rotated Bounding Boxes","date":"2019-07-08","arxiv_id":"1907.03892","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-convolutional-lstm-approach","slug":"weakly-supervised-convolutional-lstm-approach","title":"Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos","date":"2018-12-04","arxiv_id":"1812.01366","repositories_listed":1,"syntology":null},{"url":"/paper/distractor-aware-siamese-networks-for-visual","slug":"distractor-aware-siamese-networks-for-visual","title":"Distractor-aware Siamese Networks for Visual Object Tracking","date":"2018-08-18","arxiv_id":"1808.06048","repositories_listed":1,"syntology":null},{"url":"/paper/learning-adaptive-discriminative-correlation","slug":"learning-adaptive-discriminative-correlation","title":"Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking","date":"2018-07-30","arxiv_id":"1807.11348","repositories_listed":1,"syntology":null},{"url":"/paper/learning-spatial-temporal-regularized","slug":"learning-spatial-temporal-regularized","title":"Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking","date":"2018-03-23","arxiv_id":"1803.08679","repositories_listed":1,"syntology":null},{"url":"/paper/learning-background-aware-correlation-filters","slug":"learning-background-aware-correlation-filters","title":"Learning Background-Aware Correlation Filters for Visual Tracking","date":"2017-03-14","arxiv_id":"1703.04590","repositories_listed":1,"syntology":null},{"url":null,"slug":"enhancing-self-supervised-fine-grained-video","title":"Enhancing Self-Supervised Fine-Grained Video Object Tracking with Dynamic Memory Prediction","date":"2025-04-30","arxiv_id":"2504.21692","repositories_listed":0,"syntology":null},{"url":null,"slug":"vovtrack-exploring-the-potentiality-in-videos","title":"VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking","date":"2024-10-11","arxiv_id":"2410.08529","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaga-group-any-gaussians-via-3d-aware-memory","title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","date":"2024-04-11","arxiv_id":"2404.07977","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-visual-tracking-by-motion-analyzing","title":"Robust Visual Tracking by Motion Analyzing","date":"2023-09-06","arxiv_id":"2309.03247","repositories_listed":0,"syntology":null},{"url":null,"slug":"zju-reler-submission-for-epic-kitchen-1","title":"ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking","date":"2023-07-05","arxiv_id":"2307.02508","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-object-tracking-based-on-yolov7-and","title":"Video object tracking based on YOLOv7 and DeepSORT","date":"2022-07-25","arxiv_id":"2207.12202","repositories_listed":0,"syntology":null},{"url":"/paper/tfcnet-temporal-fully-connected-networks-for","slug":"tfcnet-temporal-fully-connected-networks-for","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","date":"2022-03-11","arxiv_id":"2203.05928","repositories_listed":0,"syntology":null},{"url":null,"slug":"come-again-re-query-in-referring-expression","title":"Evaluating and Improving Interactions with Hazy Oracles","date":"2021-10-19","arxiv_id":"2110.10206","repositories_listed":0,"syntology":null},{"url":"/paper/inferno-inferring-object-centric-3d-scene","slug":"inferno-inferring-object-centric-3d-scene","title":"INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-deep-object-tracking-with-circular","title":"End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box","date":"2020-12-17","arxiv_id":"2012.09771","repositories_listed":0,"syntology":null},{"url":"/paper/fast-video-object-segmentation-with-temporal-1","slug":"fast-video-object-segmentation-with-temporal-1","title":"Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching","date":"2020-07-11","arxiv_id":"2007.05687","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-regularized-l1-tracking-and","title":"Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking","date":"2019-12-30","arxiv_id":"1912.12883","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-human-annotation-in-single-object","title":"Improving Human Annotation in Single Object Tracking","date":"2019-11-07","arxiv_id":"1911.02807","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-cnn-and-classic-features-for","title":"A Comparison of CNN and Classic Features for Image Retrieval","date":"2019-08-25","arxiv_id":"1908.09300","repositories_listed":0,"syntology":null},{"url":null,"slug":"dawn-dual-augmented-memory-network-for","title":"DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking","date":"2019-08-02","arxiv_id":"1908.00777","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-based-long-term","title":"Unsupervised learning-based long-term superpixel tracking","date":"2019-02-25","arxiv_id":"1902.09596","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-siamese-networks-with-bayesian-non","title":"Deep Siamese Networks with Bayesian non-Parametrics for Video Object Tracking","date":"2018-11-18","arxiv_id":"1811.07386","repositories_listed":0,"syntology":null},{"url":"/paper/high-speed-tracking-with-multi-kernel","slug":"high-speed-tracking-with-multi-kernel","title":"High-speed Tracking with Multi-kernel Correlation Filters","date":"2018-06-17","arxiv_id":"1806.06418","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-adaptive-computational-policies-for","title":"Depth-Adaptive Computational Policies for Efficient Visual Tracking","date":"2018-01-01","arxiv_id":"1801.00508","repositories_listed":0,"syntology":null},{"url":null,"slug":"mavot-memory-augmented-video-object-tracking","title":"MAVOT: Memory-Augmented Video Object Tracking","date":"2017-11-26","arxiv_id":"1711.09414","repositories_listed":0,"syntology":null},{"url":"/paper/context-aware-correlation-filter-tracking","slug":"context-aware-correlation-filter-tracking","title":"Context-Aware Correlation Filter Tracking","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-spatially-regularized-correlation","slug":"learning-spatially-regularized-correlation","title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","date":"2016-08-19","arxiv_id":"1608.05571","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-video-object-tracking-via-bayesian","title":"Robust video object tracking via Bayesian model averaging based feature fusion","date":"2016-04-02","arxiv_id":"1604.00475","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-video-object-tracking-using-particle","title":"Robust video object tracking using particle filter with likelihood based feature fusion and adaptive template updating","date":"2015-09-28","arxiv_id":"1509.08182","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-tracking-of-protein-vesicles","title":"Automatic tracking of protein vesicles","date":"2015-06-05","arxiv_id":"1506.02083","repositories_listed":0,"syntology":null},{"url":"/paper/in-defense-of-color-based-model-free-tracking","slug":"in-defense-of-color-based-model-free-tracking","title":"In Defense of Color-Based Model-Free Tracking","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":28,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/video-object-tracking-on-got-10k-1","since_archive":"/sota/video-object-tracking-on-got-10k-1#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":26,"papers_where_code_ran_first_page":"/task/video-object-tracking/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-object-tracking/papers/ran/1","json":"/task/video-object-tracking/papers/ran/1.json","rows":26}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"778553dac3d865a4a1f14faabc4349c8e3f87204f1a35286f0194dd30ec1210a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}