{"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/image-retrieval/papers/5","list_of":"/task/image-retrieval","task":"Image Retrieval","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":5,"pages_in_order":23,"rows_per_page":100,"rows":[401,500],"of":2239,"counts":{"archive_papers_tagged":2239,"with_a_code_link":835,"where_syntology_ran_a_sample":218,"not_listed_spam_title":0,"listed":2239,"listed_where_code_ran":218,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":185,"every_run_a_failure_of_syntologys_instrument":33,"listed_with_a_run_with_no_instrument_failure":185,"listed_every_run_a_failure_of_syntologys_instrument":33,"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/image-retrieval","prev":"/task/image-retrieval/papers/4","next":"/task/image-retrieval/papers/6","papers":[{"url":"/paper/zero-shot-everything-sketch-based-image","slug":"zero-shot-everything-sketch-based-image","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","date":"2023-03-25","arxiv_id":"2303.14348","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":9,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/zero-shot-everything-sketch-based-image#ran","syntology_url":"https://syntology.ai/paper/2303.14348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14348"}},"official":{"repos":["buptlinfy/zse-sbir"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":9,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-step-by-step-instructional-diagrams","slug":"aligning-step-by-step-instructional-diagrams","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","date":"2023-03-24","arxiv_id":"2303.13800","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":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) · 0 unverified","sample_list":"/paper/aligning-step-by-step-instructional-diagrams#ran","syntology_url":"https://syntology.ai/paper/2303.13800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13800"}},"official":{"repos":["DavidZhang73/AssemblyVideoManualAlignment"],"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/panovpr-towards-unified-perspective-to","slug":"panovpr-towards-unified-perspective-to","title":"PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic View","date":"2023-03-24","arxiv_id":"2303.14095","repositories_listed":1,"syntology":null},{"url":"/paper/plug-and-play-regulators-for-image-text","slug":"plug-and-play-regulators-for-image-text","title":"Plug-and-Play Regulators for Image-Text Matching","date":"2023-03-23","arxiv_id":"2303.13371","repositories_listed":1,"syntology":null},{"url":"/paper/compodiff-versatile-composed-image-retrieval","slug":"compodiff-versatile-composed-image-retrieval","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","date":"2023-03-21","arxiv_id":"2303.11916","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compodiff-versatile-composed-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11916"}},"official":{"repos":["navervision/compodiff"],"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/location-free-scene-graph-generation","slug":"location-free-scene-graph-generation","title":"Location-Free Scene Graph Generation","date":"2023-03-20","arxiv_id":"2303.10944","repositories_listed":1,"syntology":null},{"url":"/paper/irgen-generative-modeling-for-image-retrieval","slug":"irgen-generative-modeling-for-image-retrieval","title":"IRGen: Generative Modeling for Image Retrieval","date":"2023-03-17","arxiv_id":"2303.10126","repositories_listed":1,"syntology":null},{"url":"/paper/data-roaming-and-early-fusion-for-composed","slug":"data-roaming-and-early-fusion-for-composed","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","date":"2023-03-16","arxiv_id":"2303.09429","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-facial-expression-representation","slug":"unsupervised-facial-expression-representation","title":"Unsupervised Facial Expression Representation Learning with Contrastive Local Warping","date":"2023-03-16","arxiv_id":"2303.09034","repositories_listed":1,"syntology":null},{"url":"/paper/data-free-sketch-based-image-retrieval","slug":"data-free-sketch-based-image-retrieval","title":"Data-Free Sketch-Based Image Retrieval","date":"2023-03-14","arxiv_id":"2303.07775","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/data-free-sketch-based-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.07775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07775"}},"official":{"repos":["abhrac/data-free-sbir"],"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/sketch-based-medical-image-retrieval","slug":"sketch-based-medical-image-retrieval","title":"Sketch-based Medical Image Retrieval","date":"2023-03-07","arxiv_id":"2303.03633","repositories_listed":1,"syntology":null},{"url":"/paper/mabnet-master-assistant-buddy-network-with","slug":"mabnet-master-assistant-buddy-network-with","title":"MABNet: Master Assistant Buddy Network with Hybrid Learning for Image Retrieval","date":"2023-03-06","arxiv_id":"2303.03050","repositories_listed":1,"syntology":null},{"url":"/paper/fame-vil-multi-tasking-vision-language-model","slug":"fame-vil-multi-tasking-vision-language-model","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","date":"2023-03-04","arxiv_id":"2303.02483","repositories_listed":1,"syntology":null},{"url":"/paper/mixvpr-feature-mixing-for-visual-place","slug":"mixvpr-feature-mixing-for-visual-place","title":"MixVPR: Feature Mixing for Visual Place Recognition","date":"2023-03-03","arxiv_id":"2303.02190","repositories_listed":1,"syntology":null},{"url":"/paper/global-proxy-based-hard-mining-for-visual","slug":"global-proxy-based-hard-mining-for-visual","title":"Global Proxy-based Hard Mining for Visual Place Recognition","date":"2023-02-28","arxiv_id":"2302.14217","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-clip-to-count-to-ten","slug":"teaching-clip-to-count-to-ten","title":"Teaching CLIP to Count to Ten","date":"2023-02-23","arxiv_id":"2302.12066","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/teaching-clip-to-count-to-ten#ran","syntology_url":"https://syntology.ai/paper/2302.12066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12066"}},"official":null}},{"url":"/paper/iqpp-a-benchmark-for-image-query-performance","slug":"iqpp-a-benchmark-for-image-query-performance","title":"iQPP: A Benchmark for Image Query Performance Prediction","date":"2023-02-20","arxiv_id":"2302.10126","repositories_listed":1,"syntology":null},{"url":"/paper/patent-image-retrieval-using-cross-entropy","slug":"patent-image-retrieval-using-cross-entropy","title":"Patent Image Retrieval Using Cross-entropy-based Metric Learning","date":"2023-02-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-unifying-medical-vision-and-language","slug":"towards-unifying-medical-vision-and-language","title":"Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts","date":"2023-02-17","arxiv_id":"2302.08958","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-hashing-via-similarity","slug":"unsupervised-hashing-via-similarity","title":"Unsupervised Hashing with Similarity Distribution Calibration","date":"2023-02-15","arxiv_id":"2302.07669","repositories_listed":1,"syntology":null},{"url":"/paper/correspondence-free-domain-alignment-for","slug":"correspondence-free-domain-alignment-for","title":"Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval","date":"2023-02-13","arxiv_id":"2302.06081","repositories_listed":1,"syntology":null},{"url":"/paper/sketch-less-face-image-retrieval-a-new","slug":"sketch-less-face-image-retrieval-a-new","title":"Sketch Less Face Image Retrieval: A New Challenge","date":"2023-02-11","arxiv_id":"2302.05576","repositories_listed":1,"syntology":null},{"url":"/paper/is-multi-modal-vision-supervision-beneficial","slug":"is-multi-modal-vision-supervision-beneficial","title":"Is Multimodal Vision Supervision Beneficial to Language?","date":"2023-02-10","arxiv_id":"2302.05016","repositories_listed":1,"syntology":null},{"url":"/paper/pic2word-mapping-pictures-to-words-for-zero","slug":"pic2word-mapping-pictures-to-words-for-zero","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","date":"2023-02-06","arxiv_id":"2302.03084","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/pic2word-mapping-pictures-to-words-for-zero#ran","syntology_url":"https://syntology.ai/paper/2302.03084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03084"}},"official":{"repos":["google-research/composed_image_retrieval"],"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"]}}},{"url":"/paper/probabilistic-contrastive-learning-recovers","slug":"probabilistic-contrastive-learning-recovers","title":"Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs","date":"2023-02-06","arxiv_id":"2302.02865","repositories_listed":1,"syntology":null},{"url":"/paper/simple-effective-and-general-a-new-backbone","slug":"simple-effective-and-general-a-new-backbone","title":"Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization","date":"2023-02-03","arxiv_id":"2302.01572","repositories_listed":1,"syntology":null},{"url":"/paper/lexi-self-supervised-learning-of-the-ui","slug":"lexi-self-supervised-learning-of-the-ui","title":"Lexi: Self-Supervised Learning of the UI Language","date":"2023-01-23","arxiv_id":"2301.10165","repositories_listed":1,"syntology":null},{"url":"/paper/text2poster-laying-out-stylized-texts-on","slug":"text2poster-laying-out-stylized-texts-on","title":"Text2Poster: Laying out Stylized Texts on Retrieved Images","date":"2023-01-06","arxiv_id":"2301.02363","repositories_listed":1,"syntology":null},{"url":"/paper/divide-classify-fine-grained-classification-1","slug":"divide-classify-fine-grained-classification-1","title":"Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dlbd-a-self-supervised-direct-learned-binary","slug":"dlbd-a-self-supervised-direct-learned-binary","title":"DLBD: A Self-Supervised Direct-Learned Binary Descriptor","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fan-beam-binarization-difference-projection","slug":"fan-beam-binarization-difference-projection","title":"Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-relationship-among","slug":"learning-semantic-relationship-among","title":"Learning Semantic Relationship Among Instances for Image-Text Matching","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-spatial-context-aware-global-visual","slug":"learning-spatial-context-aware-global-visual","title":"Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/photo-pre-training-but-for-sketch","slug":"photo-pre-training-but-for-sketch","title":"Photo Pre-Training, but for Sketch","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prototypical-mixing-and-retrieval-based","slug":"prototypical-mixing-and-retrieval-based","title":"Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-self-similarity-structural","slug":"revisiting-self-similarity-structural","title":"Revisiting Self-Similarity: Structural Embedding for Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-feature-representation-learning","slug":"unsupervised-feature-representation-learning","title":"Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hpointloc-point-based-indoor-place","slug":"hpointloc-point-based-indoor-place","title":"HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images","date":"2022-12-30","arxiv_id":"2212.14649","repositories_listed":1,"syntology":null},{"url":"/paper/query-by-example-in-remote-sensing-image","slug":"query-by-example-in-remote-sensing-image","title":"Query by example in remote sensing image archive using enhanced deep support vector data description","date":"2022-12-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/noise-aware-learning-from-web-crawled-image","slug":"noise-aware-learning-from-web-crawled-image","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","date":"2022-12-27","arxiv_id":"2212.13563","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/noise-aware-learning-from-web-crawled-image#ran","syntology_url":"https://syntology.ai/paper/2212.13563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13563"}},"official":{"repos":["kakaobrain/noc"],"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"]}}},{"url":"/paper/crepe-can-vision-language-foundation-models","slug":"crepe-can-vision-language-foundation-models","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","date":"2022-12-13","arxiv_id":"2212.07796","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/crepe-can-vision-language-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.07796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07796"}},"official":{"repos":["raivnlab/crepe"],"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"]}}},{"url":"/paper/intra-class-adaptive-augmentation-with","slug":"intra-class-adaptive-augmentation-with","title":"Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning","date":"2022-11-29","arxiv_id":"2211.16264","repositories_listed":1,"syntology":null},{"url":"/paper/rankdnn-learning-to-rank-for-few-shot","slug":"rankdnn-learning-to-rank-for-few-shot","title":"RankDNN: Learning to Rank for Few-shot Learning","date":"2022-11-28","arxiv_id":"2211.15320","repositories_listed":1,"syntology":null},{"url":"/paper/instance-level-heterogeneous-domain-1","slug":"instance-level-heterogeneous-domain-1","title":"Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval","date":"2022-11-26","arxiv_id":"2211.14515","repositories_listed":1,"syntology":null},{"url":"/paper/roboflow-100-a-rich-multi-domain-object","slug":"roboflow-100-a-rich-multi-domain-object","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","date":"2022-11-24","arxiv_id":"2211.13523","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/roboflow-100-a-rich-multi-domain-object#ran","syntology_url":"https://syntology.ai/paper/2211.13523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13523"}},"official":{"repos":["roboflow-ai/roboflow-100-benchmark"],"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"]}}},{"url":"/paper/indirect-language-guided-zero-shot-deep","slug":"indirect-language-guided-zero-shot-deep","title":"InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images","date":"2022-11-23","arxiv_id":"2211.12760","repositories_listed":1,"syntology":null},{"url":"/paper/composed-image-retrieval-with-text-feedback","slug":"composed-image-retrieval-with-text-feedback","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","date":"2022-11-14","arxiv_id":"2211.07394","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"10 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/composed-image-retrieval-with-text-feedback#ran","syntology_url":"https://syntology.ai/paper/2211.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07394"}},"official":{"repos":["Monoxide-Chen/uncertainty_retrieval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-named-entity-linking-a-new-dataset-and","slug":"visual-named-entity-linking-a-new-dataset-and","title":"Visual Named Entity Linking: A New Dataset and A Baseline","date":"2022-11-09","arxiv_id":"2211.04872","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/chinese-clip-contrastive-vision-language#ran","syntology_url":"https://syntology.ai/paper/2211.01335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01335"}},"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"]}}},{"url":"/paper/why-is-winoground-hard-investigating-failures","slug":"why-is-winoground-hard-investigating-failures","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","date":"2022-11-01","arxiv_id":"2211.00768","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/why-is-winoground-hard-investigating-failures#ran","syntology_url":"https://syntology.ai/paper/2211.00768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00768"}},"official":{"repos":["ajd12342/why-winoground-hard"],"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"]}}},{"url":"/paper/structuring-user-generated-content-on-social","slug":"structuring-user-generated-content-on-social","title":"Retrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis","date":"2022-10-27","arxiv_id":"2210.15377","repositories_listed":1,"syntology":null},{"url":"/paper/reliability-aware-prediction-via-uncertainty","slug":"reliability-aware-prediction-via-uncertainty","title":"Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval","date":"2022-10-24","arxiv_id":"2210.13440","repositories_listed":1,"syntology":null},{"url":"/paper/neural-eigenfunctions-are-structured","slug":"neural-eigenfunctions-are-structured","title":"Neural Eigenfunctions Are Structured Representation Learners","date":"2022-10-23","arxiv_id":"2210.12637","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-vision-transformers-for-image","slug":"boosting-vision-transformers-for-image","title":"Boosting vision transformers for image retrieval","date":"2022-10-21","arxiv_id":"2210.11909","repositories_listed":1,"syntology":null},{"url":"/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","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/general-image-descriptors-for-open-world#ran","syntology_url":"https://syntology.ai/paper/2210.11141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11141"}},"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"]}}},{"url":"/paper/cross-modal-fusion-distillation-for-fine","slug":"cross-modal-fusion-distillation-for-fine","title":"Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval","date":"2022-10-19","arxiv_id":"2210.10486","repositories_listed":1,"syntology":null},{"url":"/paper/gsv-cities-toward-appropriate-supervised","slug":"gsv-cities-toward-appropriate-supervised","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","date":"2022-10-19","arxiv_id":"2210.10239","repositories_listed":1,"syntology":null},{"url":"/paper/cofar-commonsense-and-factual-reasoning-in","slug":"cofar-commonsense-and-factual-reasoning-in","title":"COFAR: Commonsense and Factual Reasoning in Image Search","date":"2022-10-16","arxiv_id":"2210.08554","repositories_listed":1,"syntology":null},{"url":"/paper/learning-self-regularized-adversarial-views","slug":"learning-self-regularized-adversarial-views","title":"Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers","date":"2022-10-16","arxiv_id":"2210.08458","repositories_listed":1,"syntology":null},{"url":"/paper/cross-scale-context-extracted-hashing-for","slug":"cross-scale-context-extracted-hashing-for","title":"Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding","date":"2022-10-14","arxiv_id":"2210.07572","repositories_listed":1,"syntology":null},{"url":"/paper/large-to-small-image-resolution-asymmetry-in","slug":"large-to-small-image-resolution-asymmetry-in","title":"Large-to-small Image Resolution Asymmetry in Deep Metric Learning","date":"2022-10-11","arxiv_id":"2210.05463","repositories_listed":1,"syntology":null},{"url":"/paper/medical-image-retrieval-via-nearest-neighbor","slug":"medical-image-retrieval-via-nearest-neighbor","title":"Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features","date":"2022-10-05","arxiv_id":"2210.02401","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-metric-learning-for-retrieval-via","slug":"supervised-metric-learning-for-retrieval-via","title":"Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization","date":"2022-10-04","arxiv_id":"2210.01908","repositories_listed":1,"syntology":null},{"url":"/paper/ernie-vil-2-0-multi-view-contrastive-learning","slug":"ernie-vil-2-0-multi-view-contrastive-learning","title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","date":"2022-09-30","arxiv_id":"2209.15270","repositories_listed":1,"syntology":null},{"url":"/paper/mr-right-multimodal-retrieval-on","slug":"mr-right-multimodal-retrieval-on","title":"Mr. Right: Multimodal Retrieval on Representation of ImaGe witH Text","date":"2022-09-28","arxiv_id":"2209.13764","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-algorithm-dependent","slug":"exploring-the-algorithm-dependent","title":"Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability","date":"2022-09-27","arxiv_id":"2209.13262","repositories_listed":1,"syntology":null},{"url":"/paper/learning-based-dimensionality-reduction-for","slug":"learning-based-dimensionality-reduction-for","title":"Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptors","date":"2022-09-27","arxiv_id":"2209.13586","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-saliency-in-task-oriented","slug":"personalized-saliency-in-task-oriented","title":"Personalized Saliency in Task-Oriented Semantic Communications: Image Transmission and Performance Analysis","date":"2022-09-25","arxiv_id":"2209.12274","repositories_listed":1,"syntology":null},{"url":"/paper/query-based-hard-image-retrieval-for-object","slug":"query-based-hard-image-retrieval-for-object","title":"Query-based Hard-Image Retrieval for Object Detection at Test Time","date":"2022-09-23","arxiv_id":"2209.11559","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-hashing-with-semantic-concept","slug":"unsupervised-hashing-with-semantic-concept","title":"Unsupervised Hashing with Semantic Concept Mining","date":"2022-09-23","arxiv_id":"2209.11475","repositories_listed":1,"syntology":null},{"url":"/paper/deep-metric-learning-with-chance-constraints","slug":"deep-metric-learning-with-chance-constraints","title":"Deep Metric Learning with Chance Constraints","date":"2022-09-19","arxiv_id":"2209.09060","repositories_listed":1,"syntology":null},{"url":"/paper/lavis-a-library-for-language-vision","slug":"lavis-a-library-for-language-vision","title":"LAVIS: A Library for Language-Vision Intelligence","date":"2022-09-15","arxiv_id":"2209.09019","repositories_listed":1,"syntology":null},{"url":"/paper/feta-towards-specializing-foundation-models","slug":"feta-towards-specializing-foundation-models","title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","date":"2022-09-08","arxiv_id":"2209.03648","repositories_listed":1,"syntology":null},{"url":"/paper/scaleface-uncertainty-aware-deep-metric","slug":"scaleface-uncertainty-aware-deep-metric","title":"ScaleFace: Uncertainty-aware Deep Metric Learning","date":"2022-09-05","arxiv_id":"2209.01880","repositories_listed":1,"syntology":null},{"url":"/paper/universal-multi-modality-retrieval-with-one","slug":"universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","arxiv_id":"2209.00179","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"12 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/universal-multi-modality-retrieval-with-one#ran","syntology_url":"https://syntology.ai/paper/2209.00179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00179"}},"official":{"repos":["openmatch/univl-dr"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evit-privacy-preserving-image-retrieval-via","slug":"evit-privacy-preserving-image-retrieval-via","title":"EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing","date":"2022-08-31","arxiv_id":"2208.14657","repositories_listed":1,"syntology":null},{"url":"/paper/ttt-ucdr-test-time-training-for-universal","slug":"ttt-ucdr-test-time-training-for-universal","title":"Test-time Training for Data-efficient UCDR","date":"2022-08-19","arxiv_id":"2208.09198","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-attention-for-vision-and-1","slug":"understanding-attention-for-vision-and-1","title":"Understanding Attention for Vision-and-Language Tasks","date":"2022-08-17","arxiv_id":"2208.08104","repositories_listed":1,"syntology":null},{"url":"/paper/visual-cross-view-metric-localization-with","slug":"visual-cross-view-metric-localization-with","title":"Visual Cross-View Metric Localization with Dense Uncertainty Estimates","date":"2022-08-17","arxiv_id":"2208.08519","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/visual-cross-view-metric-localization-with#ran","syntology_url":"https://syntology.ai/paper/2208.08519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08519"}},"official":{"repos":["tudelft-iv/crossviewmetriclocalization"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/hyp-2-loss-beyond-hypersphere-metric-space","slug":"hyp-2-loss-beyond-hypersphere-metric-space","title":"HyP$^2$ Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval","date":"2022-08-14","arxiv_id":"2208.06866","repositories_listed":1,"syntology":null},{"url":"/paper/finding-point-with-image-an-end-to-end","slug":"finding-point-with-image-an-end-to-end","title":"Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization","date":"2022-08-13","arxiv_id":"2208.06561","repositories_listed":1,"syntology":null},{"url":"/paper/category-level-pose-retrieval-with","slug":"category-level-pose-retrieval-with","title":"Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation","date":"2022-08-12","arxiv_id":"2208.06195","repositories_listed":1,"syntology":null},{"url":"/paper/chiqa-a-large-scale-image-based-real-world","slug":"chiqa-a-large-scale-image-based-real-world","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","date":"2022-08-05","arxiv_id":"2208.03030","repositories_listed":1,"syntology":null},{"url":"/paper/das-densely-anchored-sampling-for-deep-metric","slug":"das-densely-anchored-sampling-for-deep-metric","title":"DAS: Densely-Anchored Sampling for Deep Metric Learning","date":"2022-07-30","arxiv_id":"2208.00119","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/das-densely-anchored-sampling-for-deep-metric#ran","syntology_url":"https://syntology.ai/paper/2208.00119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00119"}},"official":{"repos":["lizhaoliu-Lec/DAS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/towards-privacy-preserving-real-time-and","slug":"towards-privacy-preserving-real-time-and","title":"Towards Privacy-Preserving, Real-Time and Lossless Feature Matching","date":"2022-07-30","arxiv_id":"2208.00214","repositories_listed":1,"syntology":null},{"url":"/paper/abstracting-sketches-through-simple","slug":"abstracting-sketches-through-simple","title":"Abstracting Sketches through Simple Primitives","date":"2022-07-27","arxiv_id":"2207.13543","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":4,"n_violates":0,"n_no_contract":2,"n_pointer_only":16,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/abstracting-sketches-through-simple#ran","syntology_url":"https://syntology.ai/paper/2207.13543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13543"}},"official":{"repos":["explainableml/sketch-primitives"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/feature-representation-learning-for","slug":"feature-representation-learning-for","title":"Feature Representation Learning for Unsupervised Cross-domain Image Retrieval","date":"2022-07-20","arxiv_id":"2207.09721","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/feature-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2207.09721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09721"}},"official":{"repos":["conghuihu/ucdir"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-hotels-50k-and-hotel-id","slug":"revisiting-hotels-50k-and-hotel-id","title":"Revisiting Hotels-50K and Hotel-ID","date":"2022-07-20","arxiv_id":"2207.10200","repositories_listed":1,"syntology":null},{"url":"/paper/context-unaware-knowledge-distillation-for","slug":"context-unaware-knowledge-distillation-for","title":"Context Unaware Knowledge Distillation for Image Retrieval","date":"2022-07-19","arxiv_id":"2207.09070","repositories_listed":1,"syntology":null},{"url":"/paper/fashionvil-fashion-focused-vision-and","slug":"fashionvil-fashion-focused-vision-and","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","date":"2022-07-17","arxiv_id":"2207.08150","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-fine-grained-sketch-based-image","slug":"adaptive-fine-grained-sketch-based-image","title":"Adaptive Fine-Grained Sketch-Based Image Retrieval","date":"2022-07-04","arxiv_id":"2207.01723","repositories_listed":1,"syntology":null},{"url":"/paper/embedding-contrastive-unsupervised-features","slug":"embedding-contrastive-unsupervised-features","title":"Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets","date":"2022-07-04","arxiv_id":"2207.01573","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/embedding-contrastive-unsupervised-features#ran","syntology_url":"https://syntology.ai/paper/2207.01573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01573"}},"official":{"repos":["paulalbert31/sncf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/badhash-invisible-backdoor-attacks-against","slug":"badhash-invisible-backdoor-attacks-against","title":"BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label","date":"2022-07-01","arxiv_id":"2207.00278","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/badhash-invisible-backdoor-attacks-against#ran","syntology_url":"https://syntology.ai/paper/2207.00278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00278"}},"official":{"repos":["cgcl-codes/badhash"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/clear-a-fully-user-side-image-search-system","slug":"clear-a-fully-user-side-image-search-system","title":"CLEAR: A Fully User-side Image Search System","date":"2022-06-17","arxiv_id":"2206.08521","repositories_listed":1,"syntology":null},{"url":"/paper/norppa-novel-ringed-seal-re-identification-by","slug":"norppa-novel-ringed-seal-re-identification-by","title":"NORPPA: NOvel Ringed seal re-identification by Pelage Pattern Aggregation","date":"2022-06-06","arxiv_id":"2206.02498","repositories_listed":1,"syntology":null},{"url":"/paper/expressive-scene-graph-generation-using","slug":"expressive-scene-graph-generation-using","title":"Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and Reasoning","date":"2022-05-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-role-of-image-retrieval-for","slug":"investigating-the-role-of-image-retrieval-for","title":"Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark","date":"2022-05-31","arxiv_id":"2205.15761","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-image-captioning-with-clip","slug":"fine-grained-image-captioning-with-clip","title":"Fine-grained Image Captioning with CLIP Reward","date":"2022-05-26","arxiv_id":"2205.13115","repositories_listed":1,"syntology":null},{"url":"/paper/geo-localization-via-ground-to-satellite","slug":"geo-localization-via-ground-to-satellite","title":"Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval","date":"2022-05-22","arxiv_id":"2205.10878","repositories_listed":1,"syntology":null},{"url":"/paper/visually-augmented-language-modeling","slug":"visually-augmented-language-modeling","title":"Visually-Augmented Language Modeling","date":"2022-05-20","arxiv_id":"2205.10178","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/visually-augmented-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2205.10178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10178"}},"official":{"repos":["victorwz/valm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}],"record_sha256":"445e72f82d23946c3939ded5e4f0cbe719ef74cd487b01b147670d748455f0ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}