{"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":"/method/clip/papers/ran/6","list_of":"/method/clip","method":"CLIP","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":6,"pages_in_order":7,"rows_per_page":100,"rows":[501,600],"of":649,"counts":{"archive_papers_tagged":3094,"with_a_code_link":1617,"where_syntology_ran_a_sample":649,"not_listed_spam_title":0,"listed":3094,"listed_where_code_ran":649,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":554,"every_run_a_failure_of_syntologys_instrument":95,"listed_with_a_run_with_no_instrument_failure":554,"listed_every_run_a_failure_of_syntologys_instrument":95,"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":"/method/clip/papers/ran/1","prev":"/method/clip/papers/ran/5","next":"/method/clip/papers/ran/7","papers":[{"paper":"/paper/open-ended-medical-visual-question-answering","slug":"open-ended-medical-visual-question-answering","title":"Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models","date":"2023-03-10","arxiv_id":"2303.05977","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tjvsonsbeek/open-ended-medical-vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-guided-prototype-modulating-for-few-shot","slug":"clip-guided-prototype-modulating-for-few-shot","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","date":"2023-03-06","arxiv_id":"2303.02982","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":3,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alibaba-mmai-research/clip-fsar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cleanclip-mitigating-data-poisoning-attacks","slug":"cleanclip-mitigating-data-poisoning-attacks","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","date":"2023-03-06","arxiv_id":"2303.03323","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nishadsinghi/cleanclip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fedclip-fast-generalization-and","slug":"fedclip-fast-generalization-and","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","date":"2023-02-27","arxiv_id":"2302.13485","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":8,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["microsoft/personalizedfl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-framework-for-benchmarking-class-out-of-1","slug":"a-framework-for-benchmarking-class-out-of-1","title":"A framework for benchmarking class-out-of-distribution detection and its application to ImageNet","date":"2023-02-23","arxiv_id":"2302.11893","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mdabbah/COOD_benchmarking"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/side-adapter-network-for-open-vocabulary","slug":"side-adapter-network-for-open-vocabulary","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","date":"2023-02-23","arxiv_id":"2302.12242","n_code_links":3,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mendelxu/san"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/distribution-normalization-an-effortless-test","slug":"distribution-normalization-an-effortless-test","title":"Test-Time Distribution Normalization for Contrastively Learned Vision-language Models","date":"2023-02-22","arxiv_id":"2302.11084","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["fengyuli2002/distribution-normalization"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/open-domain-visual-entity-recognition-towards","slug":"open-domain-visual-entity-recognition-towards","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","date":"2023-02-22","arxiv_id":"2302.11154","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"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) · 3 unverified","official":{"repos":["edchengg/oven_eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-efficient-visual-adaption-via","slug":"towards-efficient-visual-adaption-via","title":"Towards Efficient Visual Adaption via Structural Re-parameterization","date":"2023-02-16","arxiv_id":"2302.08106","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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","official":{"repos":["luogen1996/repadapter"],"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"]}}},{"paper":"/paper/boosting-zero-shot-classification-with","slug":"boosting-zero-shot-classification-with","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","date":"2023-02-07","arxiv_id":"2302.03298","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jordan-hs/diversity_is_definitely_needed"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/auditing-gender-presentation-differences-in","slug":"auditing-gender-presentation-differences-in","title":"Auditing Gender Presentation Differences in Text-to-Image Models","date":"2023-02-07","arxiv_id":"2302.03675","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["SALT-NLP/GEP_data"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chils-zero-shot-image-classification-with","slug":"chils-zero-shot-image-classification-with","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","date":"2023-02-06","arxiv_id":"2302.02551","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["acmi-lab/chils"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mose-a-new-dataset-for-video-object","slug":"mose-a-new-dataset-for-video-object","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","date":"2023-02-03","arxiv_id":"2302.01872","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["henghuiding/MOSE-api"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/clipood-generalizing-clip-to-out-of","slug":"clipood-generalizing-clip-to-out-of","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","date":"2023-02-02","arxiv_id":"2302.00864","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["thuml/clipood"],"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"]}}},{"paper":"/paper/galip-generative-adversarial-clips-for-text","slug":"galip-generative-adversarial-clips-for-text","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","date":"2023-01-30","arxiv_id":"2301.12959","n_code_links":2,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["tobran/galip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/masked-visual-reconstruction-in-language","slug":"masked-visual-reconstruction-in-language","title":"RILS: Masked Visual Reconstruction in Language Semantic Space","date":"2023-01-17","arxiv_id":"2301.06958","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["hustvl/rils"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-customized-visual-models-with","slug":"learning-customized-visual-models-with","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","date":"2023-01-17","arxiv_id":"2301.07094","n_code_links":1,"syntology":{"ran":9,"of":17,"n_ran_checked":5,"n_instrument":4,"unverified":8,"pointer_only":8,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["microsoft/react"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodality-helps-unimodality-cross-modal","slug":"multimodality-helps-unimodality-cross-modal","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","date":"2023-01-16","arxiv_id":"2301.06267","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["linzhiqiu/cross_modal_adaptation"],"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"]}}},{"paper":"/paper/muse-text-to-image-generation-via-masked","slug":"muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","arxiv_id":"2301.00704","n_code_links":5,"syntology":{"ran":19,"of":21,"n_ran_checked":8,"n_instrument":11,"unverified":2,"pointer_only":11,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/clip-driven-universal-model-for-organ","slug":"clip-driven-universal-model-for-organ","title":"CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection","date":"2023-01-02","arxiv_id":"2301.00785","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["ljwztc/clip-driven-universal-model"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","n_code_links":4,"syntology":{"ran":20,"of":25,"n_ran_checked":12,"n_instrument":8,"unverified":5,"pointer_only":11,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/unleashing-the-power-of-visual-prompting-at","slug":"unleashing-the-power-of-visual-prompting-at","title":"Unleashing the Power of Visual Prompting At the Pixel Level","date":"2022-12-20","arxiv_id":"2212.10556","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["ucsc-vlaa/evp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-is-also-an-efficient-segmenter-a-text","slug":"clip-is-also-an-efficient-segmenter-a-text","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","date":"2022-12-16","arxiv_id":"2212.09506","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["linyq2117/clip-es"],"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"]}}},{"paper":"/paper/mm-shap-a-performance-agnostic-metric-for","slug":"mm-shap-a-performance-agnostic-metric-for","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","date":"2022-12-15","arxiv_id":"2212.08158","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["heidelberg-nlp/mm-shap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/clipsep-learning-text-queried-sound","slug":"clipsep-learning-text-queried-sound","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","date":"2022-12-14","arxiv_id":"2212.07065","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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","official":{"repos":["sony/clipsep"],"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"]}}},{"paper":"/paper/reproducible-scaling-laws-for-contrastive","slug":"reproducible-scaling-laws-for-contrastive","title":"Reproducible scaling laws for contrastive language-image learning","date":"2022-12-14","arxiv_id":"2212.07143","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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","official":{"repos":["laion-ai/scaling-laws-openclip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vasr-visual-analogies-of-situation","slug":"vasr-visual-analogies-of-situation","title":"VASR: Visual Analogies of Situation Recognition","date":"2022-12-08","arxiv_id":"2212.04542","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vasr-dataset/vasr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/zegclip-towards-adapting-clip-for-zero-shot","slug":"zegclip-towards-adapting-clip-for-zero-shot","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","date":"2022-12-07","arxiv_id":"2212.03588","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":6,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"9 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZiqinZhou66/ZegCLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptive-testing-of-computer-vision-models","slug":"adaptive-testing-of-computer-vision-models","title":"Adaptive Testing of Computer Vision Models","date":"2022-12-06","arxiv_id":"2212.02774","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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","official":{"repos":["i-gao/adavision"],"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"]}}},{"paper":"/paper/fine-tuned-clip-models-are-efficient-video","slug":"fine-tuned-clip-models-are-efficient-video","title":"Fine-tuned CLIP Models are Efficient Video Learners","date":"2022-12-06","arxiv_id":"2212.03640","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":9,"n_instrument":4,"unverified":4,"pointer_only":5,"phrase":"13 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; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["muzairkhattak/vifi-clip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/location-aware-self-supervised-transformers","slug":"location-aware-self-supervised-transformers","title":"Location-Aware Self-Supervised Transformers for Semantic Segmentation","date":"2022-12-05","arxiv_id":"2212.02400","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["google-research/scenic"],"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"]}}},{"paper":"/paper/finetune-like-you-pretrain-improved","slug":"finetune-like-you-pretrain-improved","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","date":"2022-12-01","arxiv_id":"2212.00638","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["locuslab/flyp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-language-image-pre-training-via","slug":"scaling-language-image-pre-training-via","title":"Scaling Language-Image Pre-training via Masking","date":"2022-12-01","arxiv_id":"2212.00794","n_code_links":6,"syntology":{"ran":12,"of":14,"n_ran_checked":9,"n_instrument":3,"unverified":2,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 5 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/flip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/sinddm-a-single-image-denoising-diffusion","slug":"sinddm-a-single-image-denoising-diffusion","title":"SinDDM: A Single Image Denoising Diffusion Model","date":"2022-11-29","arxiv_id":"2211.16582","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":2,"phrase":"9 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fallenshock/SinDDM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/openscene-3d-scene-understanding-with-open","slug":"openscene-3d-scene-understanding-with-open","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","date":"2022-11-28","arxiv_id":"2211.15654","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/sus-x-training-free-name-only-transfer-of","slug":"sus-x-training-free-name-only-transfer-of","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","date":"2022-11-28","arxiv_id":"2211.16198","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vishaal27/sus-x"],"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"]}}},{"paper":"/paper/shifted-diffusion-for-text-to-image","slug":"shifted-diffusion-for-text-to-image","title":"Shifted Diffusion for Text-to-image Generation","date":"2022-11-24","arxiv_id":"2211.15388","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":10,"n_instrument":3,"unverified":4,"pointer_only":6,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["drboog/Shifted_Diffusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/expectation-maximization-contrastive-learning","slug":"expectation-maximization-contrastive-learning","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","date":"2022-11-21","arxiv_id":"2211.11427","n_code_links":4,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["jpthu17/emcl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"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","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"]}}},{"paper":"/paper/cross-modal-adapter-for-text-video-retrieval","slug":"cross-modal-adapter-for-text-video-retrieval","title":"Cross-Modal Adapter for Text-Video Retrieval","date":"2022-11-17","arxiv_id":"2211.09623","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":13,"n_instrument":2,"unverified":0,"pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 2 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["leaplabthu/cross-modal-adapter"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-domain-federated-adaptive-prompt-tuning","slug":"cross-domain-federated-adaptive-prompt-tuning","title":"Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning","date":"2022-11-15","arxiv_id":"2211.07864","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["leondada/fedapt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-text-conditional-discrete-denoising-on","slug":"fast-text-conditional-discrete-denoising-on","title":"A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces","date":"2022-11-14","arxiv_id":"2211.07292","n_code_links":4,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["dome272/paella"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","n_code_links":6,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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","official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"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"]}}},{"paper":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","n_code_links":2,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ediffi-text-to-image-diffusion-models-with-an","slug":"ediffi-text-to-image-diffusion-models-with-an","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","date":"2022-11-02","arxiv_id":"2211.01324","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/chinese-clip-contrastive-vision-language","slug":"chinese-clip-contrastive-vision-language","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","date":"2022-11-02","arxiv_id":"2211.01335","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ofa-sys/chinese-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidhuji/capdec"],"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":["listed","official"]}}},{"paper":"/paper/ohmg-zero-shot-open-vocabulary-human-motion","slug":"ohmg-zero-shot-open-vocabulary-human-motion","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","date":"2022-10-28","arxiv_id":"2210.15929","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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","official":{"repos":["junfanlin/oohmg"],"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"]}}},{"paper":"/paper/movieclip-visual-scene-recognition-in-movies","slug":"movieclip-visual-scene-recognition-in-movies","title":"MovieCLIP: Visual Scene Recognition in Movies","date":"2022-10-20","arxiv_id":"2210.11065","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["usc-sail/mica-MovieCLIP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/general-image-descriptors-for-open-world","slug":"general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["ivanaer/g-universal-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"]}}},{"paper":"/paper/clip-driven-fine-grained-text-image-person-re","slug":"clip-driven-fine-grained-text-image-person-re","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","date":"2022-10-19","arxiv_id":"2210.10276","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":2,"n_instrument":8,"unverified":2,"pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shuanglinyan/CFine"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/laion-5b-an-open-large-scale-dataset-for-1","slug":"laion-5b-an-open-large-scale-dataset-for-1","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","date":"2022-10-16","arxiv_id":"2210.08402","n_code_links":5,"syntology":{"ran":14,"of":18,"n_ran_checked":12,"n_instrument":2,"unverified":4,"pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mlfoundations/open_clip"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"paper":"/paper/visual-classification-via-description-from","slug":"visual-classification-via-description-from","title":"Visual Classification via Description from Large Language Models","date":"2022-10-13","arxiv_id":"2210.07183","n_code_links":3,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":3,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sachit-menon/classify_by_description_release"],"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":["listed","official"]}}},{"paper":"/paper/unifying-diffusion-models-latent-space-with","slug":"unifying-diffusion-models-latent-space-with","title":"Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance","date":"2022-10-11","arxiv_id":"2210.05559","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chenwu98/cycle-diffusion","chenwu98/unified-generative-zoo"],"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","unlocated"]}}},{"paper":"/paper/clip-fields-weakly-supervised-semantic-fields","slug":"clip-fields-weakly-supervised-semantic-fields","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","date":"2022-10-11","arxiv_id":"2210.05663","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["clip-fields/clip-fields.github.io","notmahi/clip-fields"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-semantic-segmentation-with","slug":"open-vocabulary-semantic-segmentation-with","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","date":"2022-10-09","arxiv_id":"2210.04150","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["facebookresearch/ov-seg"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/clip-model-is-an-efficient-continual-learner","slug":"clip-model-is-an-efficient-continual-learner","title":"CLIP model is an Efficient Continual Learner","date":"2022-10-06","arxiv_id":"2210.03114","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["vgthengane/continual-clip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","n_code_links":3,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"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) · 2 unverified","official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/variational-prompt-tuning-improves","slug":"variational-prompt-tuning-improves","title":"Bayesian Prompt Learning for Image-Language Model Generalization","date":"2022-10-05","arxiv_id":"2210.02390","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["saic-fi/bayesian-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/when-and-why-vision-language-models-behave","slug":"when-and-why-vision-language-models-behave","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","date":"2022-10-04","arxiv_id":"2210.01936","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":7,"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) · 5 unverified","official":{"repos":["mertyg/vision-language-models-are-bows"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-aware-soft-prompting-for-vision","slug":"language-aware-soft-prompting-for-vision","title":"LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models","date":"2022-10-03","arxiv_id":"2210.01115","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":1,"n_instrument":3,"unverified":3,"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","official":{"repos":["1adrianb/lasp"],"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"]}}},{"paper":"/paper/prompt-learning-with-optimal-transport-for","slug":"prompt-learning-with-optimal-transport-for","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","date":"2022-10-03","arxiv_id":"2210.01253","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["CHENGY12/PLOT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/linearly-mapping-from-image-to-text-space","slug":"linearly-mapping-from-image-to-text-space","title":"Linearly Mapping from Image to Text Space","date":"2022-09-30","arxiv_id":"2209.15162","n_code_links":2,"syntology":{"ran":13,"of":14,"n_ran_checked":10,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"13 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jmerullo/limber"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/data-poisoning-attacks-against-multimodal","slug":"data-poisoning-attacks-against-multimodal","title":"Data Poisoning Attacks Against Multimodal Encoders","date":"2022-09-30","arxiv_id":"2209.15266","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zqypku/mm_poison"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/namedmask-distilling-segmenters-from","slug":"namedmask-distilling-segmenters-from","title":"NamedMask: Distilling Segmenters from Complementary Foundation Models","date":"2022-09-22","arxiv_id":"2209.11228","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["noelshin/namedmask"],"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"]}}},{"paper":"/paper/gama-generative-adversarial-multi-object","slug":"gama-generative-adversarial-multi-object","title":"GAMA: Generative Adversarial Multi-Object Scene Attacks","date":"2022-09-20","arxiv_id":"2209.09502","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["abhishekaich27/GAMA-pytorch"],"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"]}}},{"paper":"/paper/the-biased-artist-exploiting-cultural-biases","slug":"the-biased-artist-exploiting-cultural-biases","title":"Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis","date":"2022-09-19","arxiv_id":"2209.08891","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["lukasstruppek/exploiting-cultural-biases-via-homoglyphs","lukasstruppek/the-biased-artist"],"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"]}}},{"paper":"/paper/clipping-privacy-identity-inference-attacks","slug":"clipping-privacy-identity-inference-attacks","title":"Does CLIP Know My Face?","date":"2022-09-15","arxiv_id":"2209.07341","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["d0mih/clipping_privacy","d0mih/does-clip-know-my-face"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/test-time-prompt-tuning-for-zero-shot","slug":"test-time-prompt-tuning-for-zero-shot","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","date":"2022-09-15","arxiv_id":"2209.07511","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["azshue/TPT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-vip-adapting-pre-trained-image-text","slug":"clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","arxiv_id":"2209.06430","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/xpretrain"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/video-guided-curriculum-learning-for-spoken","slug":"video-guided-curriculum-learning-for-spoken","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","date":"2022-09-01","arxiv_id":"2209.00277","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marmot-xy/spoken-video-grounding"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-vision-language-pretraining-with","slug":"efficient-vision-language-pretraining-with","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","date":"2022-08-29","arxiv_id":"2208.13628","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mshukor/vicha"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-panoptic-segmentation-with","slug":"open-vocabulary-panoptic-segmentation-with","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","date":"2022-08-18","arxiv_id":"2208.08984","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["mlpc-ucsd/maskclip"],"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"]}}},{"paper":"/paper/patching-open-vocabulary-models-by","slug":"patching-open-vocabulary-models-by","title":"Patching open-vocabulary models by interpolating weights","date":"2022-08-10","arxiv_id":"2208.05592","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mlfoundations/patching"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/frozen-clip-models-are-efficient-video","slug":"frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","arxiv_id":"2208.03550","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":10,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-dynamic-facial-radiance-fields-for","slug":"learning-dynamic-facial-radiance-fields-for","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","date":"2022-07-24","arxiv_id":"2207.11770","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["sstzal/DFRF"],"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"]}}},{"paper":"/paper/semantic-abstraction-open-world-3d-scene","slug":"semantic-abstraction-open-world-3d-scene","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","date":"2022-07-23","arxiv_id":"2207.11514","n_code_links":1,"syntology":{"ran":15,"of":18,"n_ran_checked":15,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["columbia-ai-robotics/semantic-abstraction"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/devis-making-deformable-transformers-work-for","slug":"devis-making-deformable-transformers-work-for","title":"DeVIS: Making Deformable Transformers Work for Video Instance Segmentation","date":"2022-07-22","arxiv_id":"2207.11103","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["acaelles97/devis"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tip-adapter-training-free-adaption-of-clip","slug":"tip-adapter-training-free-adaption-of-clip","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","date":"2022-07-19","arxiv_id":"2207.09519","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"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","official":{"repos":["gaopengcuhk/tip-adapter"],"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":["listed","official"]}}},{"paper":"/paper/towards-diverse-and-faithful-one-shot","slug":"towards-diverse-and-faithful-one-shot","title":"Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks","date":"2022-07-18","arxiv_id":"2207.08736","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["1170300521/DiFa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/paper/can-language-understand-depth","slug":"can-language-understand-depth","title":"Can Language Understand Depth?","date":"2022-07-03","arxiv_id":"2207.01077","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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","official":{"repos":["adonis-galaxy/depthclip"],"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"]}}},{"paper":"/paper/reler-zju-alibaba-submission-to-the-ego4d","slug":"reler-zju-alibaba-submission-to-the-ego4d","title":"ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022","date":"2022-07-01","arxiv_id":"2207.00383","n_code_links":1,"syntology":{"ran":17,"of":19,"n_ran_checked":16,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nnnnai/ego4d_nlq_2022_1st_place_solution"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/video-clip-baseline-for-ego4d-long-term","slug":"video-clip-baseline-for-ego4d-long-term","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","date":"2022-07-01","arxiv_id":"2207.00579","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["srijandas07/clip_baseline_lta_ego4d"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/masked-unsupervised-self-training-for-zero","slug":"masked-unsupervised-self-training-for-zero","title":"Masked Unsupervised Self-training for Label-free Image Classification","date":"2022-06-07","arxiv_id":"2206.02967","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":4,"n_instrument":3,"unverified":4,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["salesforce/must"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/recurrent-video-restoration-transformer-with","slug":"recurrent-video-restoration-transformer-with","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","date":"2022-06-05","arxiv_id":"2206.02146","n_code_links":4,"syntology":{"ran":12,"of":14,"n_ran_checked":5,"n_instrument":7,"unverified":2,"pointer_only":7,"phrase":"12 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; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jingyunliang/rvrt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/rethinking-the-openness-of-clip","slug":"rethinking-the-openness-of-clip","title":"Delving into the Openness of CLIP","date":"2022-06-04","arxiv_id":"2206.01986","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":2,"n_instrument":3,"unverified":5,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["lancopku/clip-openness"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/cyclip-cyclic-contrastive-language-image","slug":"cyclip-cyclic-contrastive-language-image","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","date":"2022-05-28","arxiv_id":"2205.14459","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":7,"phrase":"5 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["goel-shashank/CyCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/contrastive-learning-rivals-masked-image","slug":"contrastive-learning-rivals-masked-image","title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","date":"2022-05-27","arxiv_id":"2205.14141","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":1,"n_instrument":2,"unverified":5,"pointer_only":8,"phrase":"3 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["SwinTransformer/Feature-Distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/mutual-information-divergence-a-unified","slug":"mutual-information-divergence-a-unified","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","date":"2022-05-25","arxiv_id":"2205.13445","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"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","official":{"repos":["naver-ai/mid.metric"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/markedness-in-visual-semantic-ai","slug":"markedness-in-visual-semantic-ai","title":"Markedness in Visual Semantic AI","date":"2022-05-23","arxiv_id":"2205.11378","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["wolferobert3/visual_semantic_markedness"],"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"]}}},{"paper":"/paper/exposing-outlier-exposure-what-can-be-learned","slug":"exposing-outlier-exposure-what-can-be-learned","title":"Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images","date":"2022-05-23","arxiv_id":"2205.11474","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["liznerski/eoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/evidence-for-hypodescent-in-visual-semantic","slug":"evidence-for-hypodescent-in-visual-semantic","title":"Evidence for Hypodescent in Visual Semantic AI","date":"2022-05-22","arxiv_id":"2205.10764","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["wolferobert3/evidence_for_hypodescent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-clop-clip-guided-collage-and","slug":"clip-clop-clip-guided-collage-and","title":"CLIP-CLOP: CLIP-Guided Collage and Photomontage","date":"2022-05-06","arxiv_id":"2205.03146","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":8,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["deepmind/arnheim"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","n_code_links":6,"syntology":{"ran":10,"of":17,"n_ran_checked":10,"n_instrument":0,"unverified":7,"pointer_only":2,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/visual-spatial-reasoning","slug":"visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","arxiv_id":"2205.00363","n_code_links":4,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cambridgeltl/visual-spatial-reasoning","sohojoe/clip_visual-spatial-reasoning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-art-contrastive-pre-training-for-fine-1","slug":"clip-art-contrastive-pre-training-for-fine-1","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","date":"2022-04-29","arxiv_id":"2204.14244","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["KeremTurgutlu/clip_art","KeremTurgutlu/self_supervised"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-augmented-diffusion-models","slug":"retrieval-augmented-diffusion-models","title":"Semi-Parametric Neural Image Synthesis","date":"2022-04-25","arxiv_id":"2204.11824","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["compvis/latent-diffusion","lucidrains/retrieval-augmented-ddpm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/vqgan-clip-open-domain-image-generation-and","slug":"vqgan-clip-open-domain-image-generation-and","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","date":"2022-04-18","arxiv_id":"2204.08583","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/vqgan-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hierarchical-text-conditional-image","slug":"hierarchical-text-conditional-image","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","date":"2022-04-13","arxiv_id":"2204.06125","n_code_links":8,"syntology":{"ran":33,"of":38,"n_ran_checked":26,"n_instrument":7,"unverified":5,"pointer_only":4,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 26 with no instrument failure: 3 honoured, 5 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","official":null}}],"record_sha256":"dc46ccabc7114f7990f6f911bbe107fd8f73f18b89b69f39d1b6eeb698ccf097","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}