{"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/open-vocabulary-object-detection/papers/ran/1","list_of":"/task/open-vocabulary-object-detection","task":"Open Vocabulary Object Detection","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,36],"of":36,"counts":{"archive_papers_tagged":145,"with_a_code_link":92,"where_syntology_ran_a_sample":36,"not_listed_spam_title":0,"listed":145,"listed_where_code_ran":36,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"first_page":"/task/open-vocabulary-object-detection/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/fg-clip-fine-grained-visual-and-textual","slug":"fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","arxiv_id":"2505.05071","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fg-clip-fine-grained-visual-and-textual#ran","syntology_url":"https://syntology.ai/paper/2505.05071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05071"}},"official":{"repos":["360cvgroup/fg-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-rft-visual-reinforcement-fine-tuning","slug":"visual-rft-visual-reinforcement-fine-tuning","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","date":"2025-03-03","arxiv_id":"2503.01785","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 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) · 4 unverified","sample_list":"/paper/visual-rft-visual-reinforcement-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2503.01785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01785"}},"official":{"repos":["liuziyu77/visual-rft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ovt-b-a-new-large-scale-benchmark-for-open","slug":"ovt-b-a-new-large-scale-benchmark-for-open","title":"OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking","date":"2024-10-23","arxiv_id":"2410.17534","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ovt-b-a-new-large-scale-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2410.17534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17534"}},"official":{"repos":["coo1sea/ovt-b-dataset"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/locate-anything-on-earth-advancing-open","slug":"locate-anything-on-earth-advancing-open","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","date":"2024-08-17","arxiv_id":"2408.09110","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/locate-anything-on-earth-advancing-open#ran","syntology_url":"https://syntology.ai/paper/2408.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09110"}},"official":{"repos":["jaychempan/LAE-DINO"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/marvelovd-marrying-object-recognition-and","slug":"marvelovd-marrying-object-recognition-and","title":"MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection","date":"2024-07-31","arxiv_id":"2407.21465","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/marvelovd-marrying-object-recognition-and#ran","syntology_url":"https://syntology.ai/paper/2407.21465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21465"}},"official":{"repos":["wkfdb/marvelovd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lami-detr-open-vocabulary-detection-with#ran","syntology_url":"https://syntology.ai/paper/2407.11335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11335"}},"official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ovmr-open-vocabulary-recognition-with-multi","slug":"ovmr-open-vocabulary-recognition-with-multi","title":"OVMR: Open-Vocabulary Recognition with Multi-Modal References","date":"2024-06-07","arxiv_id":"2406.04675","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ovmr-open-vocabulary-recognition-with-multi#ran","syntology_url":"https://syntology.ai/paper/2406.04675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04675"}},"official":{"repos":["zehong-ma/ovmr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","slug":"ov-dquo-open-vocabulary-detr-with-denoising","title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","date":"2024-05-28","arxiv_id":"2405.17913","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ov-dquo-open-vocabulary-detr-with-denoising#ran","syntology_url":"https://syntology.ai/paper/2405.17913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17913"}},"official":{"repos":["xiaomoguhz/ov-dquo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-devil-is-in-the-object-boundary-towards","slug":"the-devil-is-in-the-object-boundary-towards","title":"The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models","date":"2024-04-18","arxiv_id":"2404.11957","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-devil-is-in-the-object-boundary-towards#ran","syntology_url":"https://syntology.ai/paper/2404.11957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11957"}},"official":{"repos":["chengshiest/zip-your-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-clip-the-main-roadblock-for-fine-grained","slug":"is-clip-the-main-roadblock-for-fine-grained","title":"Is CLIP the main roadblock for fine-grained open-world perception?","date":"2024-04-04","arxiv_id":"2404.03539","repositories_listed":2,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/is-clip-the-main-roadblock-for-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2404.03539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03539"}},"official":{"repos":["lorebianchi98/fg-clip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/generative-region-language-pretraining-for","slug":"generative-region-language-pretraining-for","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","date":"2024-03-15","arxiv_id":"2403.10191","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-region-language-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2403.10191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10191"}},"official":{"repos":["foundationvision/generateu"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-domain-few-shot-object-detection-via","slug":"cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","date":"2024-02-05","arxiv_id":"2402.03094","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/cross-domain-few-shot-object-detection-via#ran","syntology_url":"https://syntology.ai/paper/2402.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03094"}},"official":{"repos":["lovelyqian/CDFSOD-benchmark"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/yolo-world-real-time-open-vocabulary-object","slug":"yolo-world-real-time-open-vocabulary-object","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","date":"2024-01-30","arxiv_id":"2401.17270","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/yolo-world-real-time-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2401.17270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17270"}},"official":{"repos":["ailab-cvc/yolo-world"],"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/clim-contrastive-language-image-mosaic-for","slug":"clim-contrastive-language-image-mosaic-for","title":"CLIM: Contrastive Language-Image Mosaic for Region Representation","date":"2023-12-18","arxiv_id":"2312.11376","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/clim-contrastive-language-image-mosaic-for#ran","syntology_url":"https://syntology.ai/paper/2312.11376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11376"}},"official":{"repos":["wusize/clim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-devil-is-in-the-fine-grained-details","slug":"the-devil-is-in-the-fine-grained-details","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding","date":"2023-11-29","arxiv_id":"2311.17518","repositories_listed":1,"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":3,"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/the-devil-is-in-the-fine-grained-details#ran","syntology_url":"https://syntology.ai/paper/2311.17518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17518"}},"official":{"repos":["lorebianchi98/fg-ovd"],"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/lp-ovod-open-vocabulary-object-detection-by","slug":"lp-ovod-open-vocabulary-object-detection-by","title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","date":"2023-10-26","arxiv_id":"2310.17109","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/lp-ovod-open-vocabulary-object-detection-by#ran","syntology_url":"https://syntology.ai/paper/2310.17109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17109"}},"official":{"repos":["vinairesearch/lp-ovod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codet-co-occurrence-guided-region-word-1","slug":"codet-co-occurrence-guided-region-word-1","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","date":"2023-10-25","arxiv_id":"2310.16667","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":1,"n_no_contract":3,"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, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/codet-co-occurrence-guided-region-word-1#ran","syntology_url":"https://syntology.ai/paper/2310.16667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16667"}},"official":{"repos":["cvmi-lab/codet"],"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/clipself-vision-transformer-distills-itself","slug":"clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","arxiv_id":"2310.01403","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clipself-vision-transformer-distills-itself#ran","syntology_url":"https://syntology.ai/paper/2310.01403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01403"}},"official":{"repos":["wusize/clipself"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mocae-mixture-of-calibrated-experts","slug":"mocae-mixture-of-calibrated-experts","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","date":"2023-09-26","arxiv_id":"2309.14976","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mocae-mixture-of-calibrated-experts#ran","syntology_url":"https://syntology.ai/paper/2309.14976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14976"}},"official":{"repos":["fiveai/MoCaE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/detect-every-thing-with-few-examples","slug":"detect-every-thing-with-few-examples","title":"Detect Everything with Few Examples","date":"2023-09-22","arxiv_id":"2309.12969","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/detect-every-thing-with-few-examples#ran","syntology_url":"https://syntology.ai/paper/2309.12969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12969"}},"official":{"repos":["mlzxy/devit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/openins3d-snap-and-lookup-for-3d-open","slug":"openins3d-snap-and-lookup-for-3d-open","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","date":"2023-09-01","arxiv_id":"2309.00616","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/openins3d-snap-and-lookup-for-3d-open#ran","syntology_url":"https://syntology.ai/paper/2309.00616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00616"}},"official":{"repos":["Pointcept/OpenIns3D"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/described-object-detection-liberating-object-1","slug":"described-object-detection-liberating-object-1","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","date":"2023-07-24","arxiv_id":"2307.12813","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/described-object-detection-liberating-object-1#ran","syntology_url":"https://syntology.ai/paper/2307.12813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12813"}},"official":{"repos":["shikras/d-cube"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}},"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/v3det-vast-vocabulary-visual-detection","slug":"v3det-vast-vocabulary-visual-detection","title":"V3Det: Vast Vocabulary Visual Detection Dataset","date":"2023-04-07","arxiv_id":"2304.03752","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/v3det-vast-vocabulary-visual-detection#ran","syntology_url":"https://syntology.ai/paper/2304.03752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03752"}},"official":null}},{"url":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}},"official":null}},{"url":"/paper/cora-adapting-clip-for-open-vocabulary","slug":"cora-adapting-clip-for-open-vocabulary","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","date":"2023-03-23","arxiv_id":"2303.13076","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cora-adapting-clip-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2303.13076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13076"}},"official":{"repos":["tgxs002/cora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip","slug":"x-paste-revisit-copy-paste-at-scale-with-clip","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","date":"2022-12-07","arxiv_id":"2212.03863","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip#ran","syntology_url":"https://syntology.ai/paper/2212.03863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03863"}},"official":{"repos":["yoctta/xpaste"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-attribute-detection","slug":"open-vocabulary-attribute-detection","title":"Open-vocabulary Attribute Detection","date":"2022-11-23","arxiv_id":"2211.12914","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-attribute-detection#ran","syntology_url":"https://syntology.ai/paper/2211.12914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12914"}},"official":{"repos":["OVAD-Benchmark/ovad-bechmark-code"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","slug":"pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pointclip-v2-adapting-clip-for-powerful-3d#ran","syntology_url":"https://syntology.ai/paper/2211.11682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11682"}},"official":{"repos":["yangyangyang127/pointclip_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-gap-between-object-and-image","slug":"bridging-the-gap-between-object-and-image","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","date":"2022-07-07","arxiv_id":"2207.03482","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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) · 1 unverified","sample_list":"/paper/bridging-the-gap-between-object-and-image#ran","syntology_url":"https://syntology.ai/paper/2207.03482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03482"}},"official":null}},{"url":"/paper/open-vocabulary-object-detection-with","slug":"open-vocabulary-object-detection-with","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","date":"2022-06-22","arxiv_id":"2206.11134","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-object-detection-with#ran","syntology_url":"https://syntology.ai/paper/2206.11134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11134"}},"official":{"repos":["pealing/medet","peixianchen/medet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/glipv2-unifying-localization-and-vision","slug":"glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","date":"2022-06-12","arxiv_id":"2206.05836","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glipv2-unifying-localization-and-vision#ran","syntology_url":"https://syntology.ai/paper/2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}},"official":{"repos":["microsoft/GLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-prompt-for-open-vocabulary-object","slug":"learning-to-prompt-for-open-vocabulary-object","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","date":"2022-03-28","arxiv_id":"2203.14940","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/learning-to-prompt-for-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2203.14940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14940"}},"official":{"repos":["dyabel/detpro"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-detr-with-conditional","slug":"open-vocabulary-detr-with-conditional","title":"Open-Vocabulary DETR with Conditional Matching","date":"2022-03-22","arxiv_id":"2203.11876","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_constructed":2,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"6 ran (of which 2 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) · 2 unverified","sample_list":"/paper/open-vocabulary-detr-with-conditional#ran","syntology_url":"https://syntology.ai/paper/2203.11876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11876"}},"official":{"repos":["yuhangzang/ov-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/open-vocabulary-one-stage-detection-with","slug":"open-vocabulary-one-stage-detection-with","title":"Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation","date":"2022-03-20","arxiv_id":"2203.10593","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/open-vocabulary-one-stage-detection-with#ran","syntology_url":"https://syntology.ai/paper/2203.10593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10593"}},"official":{"repos":["mengqidyangge/hierkd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-open-vocabulary-object-detection","slug":"towards-open-vocabulary-object-detection","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","date":"2021-11-18","arxiv_id":"2111.09452","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-open-vocabulary-object-detection#ran","syntology_url":"https://syntology.ai/paper/2111.09452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09452"}},"official":{"repos":["salesforce/pb-ovd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"6454f9bd400eb82c2f69ed3da6c32bb8482a41b97e60ad45af8a5aef21090d81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}