{"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/3","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":3,"pages_in_order":23,"rows_per_page":100,"rows":[201,300],"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/2","next":"/task/image-retrieval/papers/4","papers":[{"url":"/paper/adversarial-hubness-in-multi-modal-retrieval","slug":"adversarial-hubness-in-multi-modal-retrieval","title":"Adversarial Hubness in Multi-Modal Retrieval","date":"2024-12-18","arxiv_id":"2412.14113","repositories_listed":1,"syntology":null},{"url":"/paper/reason-before-retrieve-one-stage-reflective","slug":"reason-before-retrieve-one-stage-reflective","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval","date":"2024-12-15","arxiv_id":"2412.11077","repositories_listed":1,"syntology":null},{"url":"/paper/a-flexible-plug-and-play-module-for","slug":"a-flexible-plug-and-play-module-for","title":"A Flexible Plug-and-Play Module for Generating Variable-Length","date":"2024-12-12","arxiv_id":"2412.08922","repositories_listed":1,"syntology":null},{"url":"/paper/impact-a-large-scale-integrated-multimodal","slug":"impact-a-large-scale-integrated-multimodal","title":"IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents","date":"2024-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/compositional-image-retrieval-via-instruction","slug":"compositional-image-retrieval-via-instruction","title":"Compositional Image Retrieval via Instruction-Aware Contrastive Learning","date":"2024-12-07","arxiv_id":"2412.05756","repositories_listed":1,"syntology":null},{"url":"/paper/composed-image-retrieval-for-training-free","slug":"composed-image-retrieval-for-training-free","title":"Composed Image Retrieval for Training-Free Domain Conversion","date":"2024-12-04","arxiv_id":"2412.03297","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-via-classifier-impact-and","slug":"active-learning-via-classifier-impact-and","title":"Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval","date":"2024-12-03","arxiv_id":"2412.02310","repositories_listed":1,"syntology":null},{"url":"/paper/image-generation-diversity-issues-and-how-to","slug":"image-generation-diversity-issues-and-how-to","title":"Image Generation Diversity Issues and How to Tame Them","date":"2024-11-25","arxiv_id":"2411.16171","repositories_listed":1,"syntology":null},{"url":"/paper/peng-pose-enhanced-geo-localisation","slug":"peng-pose-enhanced-geo-localisation","title":"PEnG: Pose-Enhanced Geo-Localisation","date":"2024-11-24","arxiv_id":"2411.15742","repositories_listed":1,"syntology":null},{"url":"/paper/globally-correlation-aware-hard-negative","slug":"globally-correlation-aware-hard-negative","title":"Globally Correlation-Aware Hard Negative Generation","date":"2024-11-20","arxiv_id":"2411.13145","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/globally-correlation-aware-hard-negative#ran","syntology_url":"https://syntology.ai/paper/2411.13145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13145"}},"official":{"repos":["pwenjay/gca-hng"],"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/hopfield-fenchel-young-networks-a-unified","slug":"hopfield-fenchel-young-networks-a-unified","title":"Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval","date":"2024-11-13","arxiv_id":"2411.08590","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/hopfield-fenchel-young-networks-a-unified#ran","syntology_url":"https://syntology.ai/paper/2411.08590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08590"}},"official":{"repos":["deep-spin/HFYN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/saliency-map-based-image-retrieval-using","slug":"saliency-map-based-image-retrieval-using","title":"Saliency Map-based Image Retrieval using Invariant Krawtchouk Moments","date":"2024-11-13","arxiv_id":"2411.08567","repositories_listed":1,"syntology":null},{"url":"/paper/inquire-a-natural-world-text-to-image","slug":"inquire-a-natural-world-text-to-image","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","date":"2024-11-04","arxiv_id":"2411.02537","repositories_listed":1,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":16,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":15,"n_pointer_only":3,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/inquire-a-natural-world-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2411.02537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02537"}},"official":{"repos":["inquire-benchmark/INQUIRE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/nearest-neighbor-normalization-improves","slug":"nearest-neighbor-normalization-improves","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","date":"2024-10-31","arxiv_id":"2410.24114","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-semantic-similarity-from-spatial","slug":"decoupling-semantic-similarity-from-spatial","title":"Decoupling Semantic Similarity from Spatial Alignment for Neural Networks","date":"2024-10-30","arxiv_id":"2410.23107","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-text-optimizing-rag-with-multimodal","slug":"beyond-text-optimizing-rag-with-multimodal","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","date":"2024-10-29","arxiv_id":"2410.21943","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-text-optimizing-rag-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2410.21943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21943"}},"official":{"repos":["riedlerm/multimodal_rag_for_industry"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chatsearch-a-dataset-and-a-generative","slug":"chatsearch-a-dataset-and-a-generative","title":"ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval","date":"2024-10-24","arxiv_id":"2410.18715","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chatsearch-a-dataset-and-a-generative#ran","syntology_url":"https://syntology.ai/paper/2410.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18715"}},"official":{"repos":["joez17/chatsearch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gssf-generalized-structural-sparse-function","slug":"gssf-generalized-structural-sparse-function","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","date":"2024-10-20","arxiv_id":"2410.15266","repositories_listed":1,"syntology":null},{"url":"/paper/visual-navigation-of-digital-libraries","slug":"visual-navigation-of-digital-libraries","title":"Visual Navigation of Digital Libraries: Retrieval and Classification of Images in the National Library of Norway's Digitised Book Collection","date":"2024-10-19","arxiv_id":"2410.14969","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-debiasing-approach-for-vision","slug":"a-unified-debiasing-approach-for-vision","title":"A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks","date":"2024-10-10","arxiv_id":"2410.07593","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/a-unified-debiasing-approach-for-vision#ran","syntology_url":"https://syntology.ai/paper/2410.07593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07593"}},"official":{"repos":["HoinJung/Unified-Debiaisng-VLM-SFID"],"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/medimageinsight-an-open-source-embedding","slug":"medimageinsight-an-open-source-embedding","title":"MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging","date":"2024-10-09","arxiv_id":"2410.06542","repositories_listed":1,"syntology":null},{"url":"/paper/csim-a-copula-based-similarity-index","slug":"csim-a-copula-based-similarity-index","title":"CSIM: A Copula-based similarity index sensitive to local changes for Image quality assessment","date":"2024-10-02","arxiv_id":"2410.01411","repositories_listed":1,"syntology":null},{"url":"/paper/eufcc-cir-a-composed-image-retrieval-dataset","slug":"eufcc-cir-a-composed-image-retrieval-dataset","title":"EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections","date":"2024-10-02","arxiv_id":"2410.01536","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-visual-and-textual-inputs-for","slug":"integrating-visual-and-textual-inputs-for","title":"Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIP","date":"2024-10-02","arxiv_id":"2410.01190","repositories_listed":1,"syntology":null},{"url":"/paper/vlad-buff-burst-aware-fast-feature","slug":"vlad-buff-burst-aware-fast-feature","title":"VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition","date":"2024-09-28","arxiv_id":"2409.19293","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"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","sample_list":"/paper/vlad-buff-burst-aware-fast-feature#ran","syntology_url":"https://syntology.ai/paper/2409.19293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19293"}},"official":{"repos":["ahmedest61/vlad-buff"],"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"]}}},{"url":"/paper/seqnet-sequential-networks-for-one-shot","slug":"seqnet-sequential-networks-for-one-shot","title":"SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning","date":"2024-09-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spagbol-spatial-graph-based-orientated","slug":"spagbol-spatial-graph-based-orientated","title":"SpaGBOL: Spatial-Graph-Based Orientated Localisation","date":"2024-09-23","arxiv_id":"2409.15514","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-and-discriminative-image-feature","slug":"efficient-and-discriminative-image-feature","title":"Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval","date":"2024-09-20","arxiv_id":"2409.13513","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-efficiency-of-visually","slug":"improving-the-efficiency-of-visually","title":"Improving the Efficiency of Visually Augmented Language Models","date":"2024-09-17","arxiv_id":"2409.11148","repositories_listed":1,"syntology":null},{"url":"/paper/referring-expression-generation-in-visually","slug":"referring-expression-generation-in-visually","title":"Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding","date":"2024-09-09","arxiv_id":"2409.05721","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-zs-cir-via-weighted-modality","slug":"training-free-zs-cir-via-weighted-modality","title":"Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity","date":"2024-09-07","arxiv_id":"2409.04918","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/training-free-zs-cir-via-weighted-modality#ran","syntology_url":"https://syntology.ai/paper/2409.04918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04918"}},"official":{"repos":["whats2000/WeiMoCIR"],"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/nudge-lightweight-non-parametric-fine-tuning","slug":"nudge-lightweight-non-parametric-fine-tuning","title":"NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval","date":"2024-09-04","arxiv_id":"2409.02343","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-clip-models-for-image-retrieval","slug":"optimizing-clip-models-for-image-retrieval","title":"Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment","date":"2024-09-03","arxiv_id":"2409.01936","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":8,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 3 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/optimizing-clip-models-for-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2409.01936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01936"}},"official":{"repos":["Visual-Computing/MCIP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-attention-for-cross-view-sequential","slug":"temporal-attention-for-cross-view-sequential","title":"Temporal Attention for Cross-View Sequential Image Localization","date":"2024-08-28","arxiv_id":"2408.15569","repositories_listed":1,"syntology":null},{"url":"/paper/unifashion-a-unified-vision-language-model","slug":"unifashion-a-unified-vision-language-model","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","date":"2024-08-21","arxiv_id":"2408.11305","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifashion-a-unified-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11305"}},"official":{"repos":["xiangyu-mm/unifashion"],"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"]}}},{"url":"/paper/cross-view-image-geo-localization-with","slug":"cross-view-image-geo-localization-with","title":"Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network","date":"2024-08-10","arxiv_id":"2408.05475","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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-view-image-geo-localization-with#ran","syntology_url":"https://syntology.ai/paper/2408.05475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05475"}},"official":{"repos":["yejy53/ep-bev"],"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/2408-03282","slug":"2408-03282","title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","date":"2024-08-06","arxiv_id":"2408.03282","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03282#ran","syntology_url":"https://syntology.ai/paper/2408.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03282"}},"official":{"repos":["pavelsuma/ames"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-haystacks-answering-harder-questions","slug":"visual-haystacks-answering-harder-questions","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark","date":"2024-07-18","arxiv_id":"2407.13766","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/visual-haystacks-answering-harder-questions#ran","syntology_url":"https://syntology.ai/paper/2407.13766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13766"}},"official":{"repos":["visual-haystacks/vhs_benchmark"],"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"]}}},{"url":"/paper/no-train-all-gain-self-supervised-gradients","slug":"no-train-all-gain-self-supervised-gradients","title":"No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations","date":"2024-07-15","arxiv_id":"2407.10964","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/no-train-all-gain-self-supervised-gradients#ran","syntology_url":"https://syntology.ai/paper/2407.10964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10964"}},"official":{"repos":["waltersimoncini/fungivision"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/are-they-the-same-picture-adapting-concept","slug":"are-they-the-same-picture-adapting-concept","title":"Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval","date":"2024-07-12","arxiv_id":"2407.08908","repositories_listed":1,"syntology":null},{"url":"/paper/lifelong-histopathology-whole-slide-image","slug":"lifelong-histopathology-whole-slide-image","title":"Lifelong Histopathology Whole Slide Image Retrieval via Distance Consistency Rehearsal","date":"2024-07-11","arxiv_id":"2407.08153","repositories_listed":1,"syntology":null},{"url":"/paper/multi-group-proportional-representation","slug":"multi-group-proportional-representation","title":"Multi-Group Proportional Representation in Retrieval","date":"2024-07-11","arxiv_id":"2407.08571","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-group-proportional-representation#ran","syntology_url":"https://syntology.ai/paper/2407.08571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08571"}},"official":{"repos":["alex-oesterling/multigroup-proportional-representation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/elevating-all-zero-shot-sketch-based-image","slug":"elevating-all-zero-shot-sketch-based-image","title":"Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning","date":"2024-07-05","arxiv_id":"2407.04207","repositories_listed":1,"syntology":null},{"url":"/paper/visualizing-dialogues-enhancing-image","slug":"visualizing-dialogues-enhancing-image","title":"Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models","date":"2024-07-04","arxiv_id":"2407.03615","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-memory-non-parametric-memory","slug":"learning-from-memory-non-parametric-memory","title":"Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features","date":"2024-07-03","arxiv_id":"2407.17486","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-from-memory-non-parametric-memory#ran","syntology_url":"https://syntology.ai/paper/2407.17486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17486"}},"official":{"repos":["sthalles/massl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wv-net-a-foundation-model-for-sar-wv-mode","slug":"wv-net-a-foundation-model-for-sar-wv-mode","title":"WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million images","date":"2024-06-26","arxiv_id":"2406.18765","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wv-net-a-foundation-model-for-sar-wv-mode#ran","syntology_url":"https://syntology.ai/paper/2406.18765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18765"}},"official":{"repos":["hawaii-ai/wvnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/breaking-the-frame-image-retrieval-by-visual","slug":"breaking-the-frame-image-retrieval-by-visual","title":"Breaking the Frame: Visual Place Recognition by Overlap Prediction","date":"2024-06-23","arxiv_id":"2406.16204","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/breaking-the-frame-image-retrieval-by-visual#ran","syntology_url":"https://syntology.ai/paper/2406.16204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16204"}},"official":{"repos":["weitong8591/vop"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-branches-interactive-fine-tuning-for","slug":"clip-branches-interactive-fine-tuning-for","title":"CLIP-Branches: Interactive Fine-Tuning for Text-Image Retrieval","date":"2024-06-19","arxiv_id":"2406.13322","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-multimodal-framework-for-remote","slug":"towards-a-multimodal-framework-for-remote","title":"Towards a multimodal framework for remote sensing image change retrieval and captioning","date":"2024-06-19","arxiv_id":"2406.13424","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-needle-in-a-haystack-benchmarking","slug":"multimodal-needle-in-a-haystack-benchmarking","title":"Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11230","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-needle-in-a-haystack-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.11230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11230"}},"official":{"repos":["wang-ml-lab/multimodal-needle-in-a-haystack"],"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"]}}},{"url":"/paper/bivlc-extending-vision-language","slug":"bivlc-extending-vision-language","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","date":"2024-06-14","arxiv_id":"2406.09952","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/bivlc-extending-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.09952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09952"}},"official":{"repos":["imirandam/bivlc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/common-and-rare-fundus-diseases","slug":"common-and-rare-fundus-diseases","title":"Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model","date":"2024-06-13","arxiv_id":"2406.09317","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/common-and-rare-fundus-diseases#ran","syntology_url":"https://syntology.ai/paper/2406.09317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09317"}},"official":{"repos":["LooKing9218/RetiZero"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/denoisereid-denoising-model-for","slug":"denoisereid-denoising-model-for","title":"DenoiseRep: Denoising Model for Representation Learning","date":"2024-06-13","arxiv_id":"2406.08773","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":2,"n_ran_checked":17,"n_instrument":0,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":14,"n_pointer_only":6,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 1 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/denoisereid-denoising-model-for#ran","syntology_url":"https://syntology.ai/paper/2406.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08773"}},"official":{"repos":["wangguanan/denoiserep"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reducing-task-discrepancy-of-text-encoders","slug":"reducing-task-discrepancy-of-text-encoders","title":"An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval","date":"2024-06-13","arxiv_id":"2406.09188","repositories_listed":1,"syntology":null},{"url":"/paper/concepthash-interpretable-fine-grained","slug":"concepthash-interpretable-fine-grained","title":"ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery","date":"2024-06-12","arxiv_id":"2406.08457","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-vision-language-contrastive","slug":"benchmarking-vision-language-contrastive","title":"Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning","date":"2024-06-11","arxiv_id":"2406.07450","repositories_listed":1,"syntology":null},{"url":"/paper/image-textualization-an-automatic-framework","slug":"image-textualization-an-automatic-framework","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","date":"2024-06-11","arxiv_id":"2406.07502","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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","sample_list":"/paper/image-textualization-an-automatic-framework#ran","syntology_url":"https://syntology.ai/paper/2406.07502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07502"}},"official":{"repos":["sterzhang/image-textualization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pqpp-a-joint-benchmark-for-text-to-image","slug":"pqpp-a-joint-benchmark-for-text-to-image","title":"PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction","date":"2024-06-07","arxiv_id":"2406.04746","repositories_listed":1,"syntology":null},{"url":"/paper/vista-visualized-text-embedding-for-universal","slug":"vista-visualized-text-embedding-for-universal","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","date":"2024-06-06","arxiv_id":"2406.04292","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/vista-visualized-text-embedding-for-universal#ran","syntology_url":"https://syntology.ai/paper/2406.04292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04292"}},"official":{"repos":["flagopen/flagembedding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/interactive-text-to-image-retrieval-with","slug":"interactive-text-to-image-retrieval-with","title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","date":"2024-06-05","arxiv_id":"2406.03411","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/interactive-text-to-image-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2406.03411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03411"}},"official":{"repos":["saehyung-lee/plugir"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/decomposing-and-interpreting-image","slug":"decomposing-and-interpreting-image","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","date":"2024-06-03","arxiv_id":"2406.01583","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"phrase":"10 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/decomposing-and-interpreting-image#ran","syntology_url":"https://syntology.ai/paper/2406.01583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01583"}},"official":{"repos":["sriramb-98/vit-decompose"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/scale-free-image-keypoints-using","slug":"scale-free-image-keypoints-using","title":"Scale-Free Image Keypoints Using Differentiable Persistent Homology","date":"2024-06-03","arxiv_id":"2406.01315","repositories_listed":1,"syntology":null},{"url":"/paper/cala-complementary-association-learning-for","slug":"cala-complementary-association-learning-for","title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval","date":"2024-05-29","arxiv_id":"2405.19149","repositories_listed":1,"syntology":null},{"url":"/paper/reverse-image-retrieval-cues-parametric","slug":"reverse-image-retrieval-cues-parametric","title":"Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs","date":"2024-05-29","arxiv_id":"2405.18740","repositories_listed":1,"syntology":null},{"url":"/paper/composed-image-retrieval-for-remote-sensing","slug":"composed-image-retrieval-for-remote-sensing","title":"Composed Image Retrieval for Remote Sensing","date":"2024-05-24","arxiv_id":"2405.15587","repositories_listed":1,"syntology":null},{"url":"/paper/emr-merging-tuning-free-high-performance","slug":"emr-merging-tuning-free-high-performance","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","date":"2024-05-23","arxiv_id":"2405.17461","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":5,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/emr-merging-tuning-free-high-performance#ran","syntology_url":"https://syntology.ai/paper/2405.17461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17461"}},"official":{"repos":["harveyhuang18/emr_merging"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hybridhash-hybrid-convolutional-and-self","slug":"hybridhash-hybrid-convolutional-and-self","title":"HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval","date":"2024-05-13","arxiv_id":"2405.07524","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-line-combination-detector","slug":"semantic-line-combination-detector","title":"Semantic Line Combination Detector","date":"2024-04-29","arxiv_id":"2404.18399","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-remote-sensing-with-harmonized","slug":"efficient-remote-sensing-with-harmonized","title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","date":"2024-04-28","arxiv_id":"2404.18253","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/efficient-remote-sensing-with-harmonized#ran","syntology_url":"https://syntology.ai/paper/2404.18253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18253"}},"official":{"repos":["seekerhuang/harma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/crisp-leveraging-tread-depth-maps-for","slug":"crisp-leveraging-tread-depth-maps-for","title":"CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching","date":"2024-04-25","arxiv_id":"2404.16972","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-localization-with-panoramic","slug":"hierarchical-localization-with-panoramic","title":"Hierarchical localization with panoramic views and triplet loss functions","date":"2024-04-22","arxiv_id":"2404.14117","repositories_listed":1,"syntology":null},{"url":"/paper/shotit-compute-efficient-image-to-video","slug":"shotit-compute-efficient-image-to-video","title":"Shotit: compute-efficient image-to-video search engine for the cloud","date":"2024-04-18","arxiv_id":"2404.12169","repositories_listed":1,"syntology":null},{"url":"/paper/improving-composed-image-retrieval-via","slug":"improving-composed-image-retrieval-via","title":"Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives","date":"2024-04-17","arxiv_id":"2404.11317","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 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","sample_list":"/paper/improving-composed-image-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2404.11317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11317"}},"official":{"repos":["BUAADreamer/SPN4CIR"],"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"]}}},{"url":"/paper/semantically-correlated-memories-in-a-dense","slug":"semantically-correlated-memories-in-a-dense","title":"Semantically-correlated memories in a dense associative model","date":"2024-04-10","arxiv_id":"2404.07123","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-deep-hyperspherical-1","slug":"weakly-supervised-deep-hyperspherical-1","title":"Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval","date":"2024-04-07","arxiv_id":"2404.04998","repositories_listed":1,"syntology":null},{"url":"/paper/soft-prompting-with-graph-of-thought-for","slug":"soft-prompting-with-graph-of-thought-for","title":"Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning","date":"2024-04-06","arxiv_id":"2404.04538","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"7 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soft-prompting-with-graph-of-thought-for#ran","syntology_url":"https://syntology.ai/paper/2404.04538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04538"}},"official":{"repos":["shishicode/agot"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/do-vision-language-models-understand-compound","slug":"do-vision-language-models-understand-compound","title":"Do Vision-Language Models Understand Compound Nouns?","date":"2024-03-30","arxiv_id":"2404.00419","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-vision-language-models-understand-compound#ran","syntology_url":"https://syntology.ai/paper/2404.00419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00419"}},"official":{"repos":["sonalkum/compun"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magiclens-self-supervised-image-retrieval","slug":"magiclens-self-supervised-image-retrieval","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","date":"2024-03-28","arxiv_id":"2403.19651","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/magiclens-self-supervised-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2403.19651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19651"}},"official":{"repos":["google-deepmind/magiclens"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-enhanced-dual-stream-zero-shot","slug":"knowledge-enhanced-dual-stream-zero-shot","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","date":"2024-03-24","arxiv_id":"2403.16005","repositories_listed":1,"syntology":{"n":17,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 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; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/knowledge-enhanced-dual-stream-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.16005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16005"}},"official":{"repos":["suoych/keds"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/long-clip-unlocking-the-long-text-capability","slug":"long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","arxiv_id":"2403.15378","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"8 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; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-clip-unlocking-the-long-text-capability#ran","syntology_url":"https://syntology.ai/paper/2403.15378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15378"}},"official":{"repos":["beichenzbc/long-clip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-historical-image-retrieval-with","slug":"enhancing-historical-image-retrieval-with","title":"Enhancing Historical Image Retrieval with Compositional Cues","date":"2024-03-21","arxiv_id":"2403.14287","repositories_listed":1,"syntology":null},{"url":"/paper/mindeye2-shared-subject-models-enable-fmri-to","slug":"mindeye2-shared-subject-models-enable-fmri-to","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","date":"2024-03-17","arxiv_id":"2403.11207","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":11,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mindeye2-shared-subject-models-enable-fmri-to#ran","syntology_url":"https://syntology.ai/paper/2403.11207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11207"}},"official":{"repos":["medarc-ai/mindeyev2"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/does-the-performance-of-text-to-image","slug":"does-the-performance-of-text-to-image","title":"Does the Performance of Text-to-Image Retrieval Models Generalize Beyond Captions-as-a-Query?","date":"2024-03-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-neural-radiance-field-in","slug":"leveraging-neural-radiance-field-in","title":"Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate Regression","date":"2024-03-15","arxiv_id":"2403.10297","repositories_listed":1,"syntology":null},{"url":"/paper/paperclip-associating-astronomical","slug":"paperclip-associating-astronomical","title":"PAPERCLIP: Associating Astronomical Observations and Natural Language with Multi-Modal Models","date":"2024-03-13","arxiv_id":"2403.08851","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paperclip-associating-astronomical#ran","syntology_url":"https://syntology.ai/paper/2403.08851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08851"}},"official":{"repos":["smsharma/paperclip-hubble"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/it-s-all-about-your-sketch-democratising","slug":"it-s-all-about-your-sketch-democratising","title":"It's All About Your Sketch: Democratising Sketch Control in Diffusion Models","date":"2024-03-12","arxiv_id":"2403.07234","repositories_listed":1,"syntology":null},{"url":"/paper/earthloc-astronaut-photography-localization","slug":"earthloc-astronaut-photography-localization","title":"EarthLoc: Astronaut Photography Localization by Indexing Earth from Space","date":"2024-03-11","arxiv_id":"2403.06758","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/earthloc-astronaut-photography-localization#ran","syntology_url":"https://syntology.ai/paper/2403.06758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06758"}},"official":{"repos":["gmberton/earthloc"],"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/leveraging-foundation-models-for-content","slug":"leveraging-foundation-models-for-content","title":"Leveraging Foundation Models for Content-Based Medical Image Retrieval in Radiology","date":"2024-03-11","arxiv_id":"2403.06567","repositories_listed":1,"syntology":null},{"url":"/paper/bit-mask-robust-contrastive-knowledge","slug":"bit-mask-robust-contrastive-knowledge","title":"Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing","date":"2024-03-10","arxiv_id":"2403.06071","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-loftr-semi-dense-local-feature","slug":"efficient-loftr-semi-dense-local-feature","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","date":"2024-03-07","arxiv_id":"2403.04765","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-photographic-image-layout","slug":"self-supervised-photographic-image-layout","title":"Self-supervised Photographic Image Layout Representation Learning","date":"2024-03-06","arxiv_id":"2403.03740","repositories_listed":1,"syntology":null},{"url":"/paper/multi-spectral-remote-sensing-image-retrieval","slug":"multi-spectral-remote-sensing-image-retrieval","title":"Multi-Spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models","date":"2024-03-04","arxiv_id":"2403.02059","repositories_listed":1,"syntology":null},{"url":"/paper/structure-similarity-preservation-learning","slug":"structure-similarity-preservation-learning","title":"Structure Similarity Preservation Learning for Asymmetric Image Retrieval","date":"2024-03-01","arxiv_id":"2403.00648","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-learned-sparse-retrieval-with","slug":"multimodal-learned-sparse-retrieval-with","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","date":"2024-02-27","arxiv_id":"2402.17535","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/multimodal-learned-sparse-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2402.17535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17535"}},"official":{"repos":["thongnt99/lsr-multimodal"],"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/learning-semantic-proxies-from-visual-prompts","slug":"learning-semantic-proxies-from-visual-prompts","title":"Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning","date":"2024-02-04","arxiv_id":"2402.02340","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-semantic-proxies-from-visual-prompts#ran","syntology_url":"https://syntology.ai/paper/2402.02340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02340"}},"official":{"repos":["noahsark/parameterefficient-dml"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/region-based-representations-revisited","slug":"region-based-representations-revisited","title":"Region-Based Representations Revisited","date":"2024-02-04","arxiv_id":"2402.02352","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-sketch-based-remote-sensing-image","slug":"zero-shot-sketch-based-remote-sensing-image","title":"Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization","date":"2024-02-03","arxiv_id":"2402.02141","repositories_listed":1,"syntology":null},{"url":"/paper/approximate-nearest-neighbor-search-with","slug":"approximate-nearest-neighbor-search-with","title":"Approximate Nearest Neighbor Search with Window Filters","date":"2024-02-01","arxiv_id":"2402.00943","repositories_listed":1,"syntology":null},{"url":"/paper/local-feature-matching-using-deep-learning-a","slug":"local-feature-matching-using-deep-learning-a","title":"Local Feature Matching Using Deep Learning: A Survey","date":"2024-01-31","arxiv_id":"2401.17592","repositories_listed":1,"syntology":null}],"record_sha256":"8bfa4c658a40b8e33dface2b2c7989f24a29ef03159bd4d3c6586f2703f65cdf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}