{"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":"/dataset/google-refexp","name":"Google Refexp","full_name":null,"description_markdown":"A new large-scale dataset for referring expressions, based on MS-COCO.\r\n\r\nSource: [Generation and Comprehension of Unambiguous Object Descriptions](/paper/generation-and-comprehension-of-unambiguous)","description_withheld":null,"homepage":"https://github.com/mjhucla/Google_Refexp_toolbox","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/generation-and-comprehension-of-unambiguous","title":"Generation and Comprehension of Unambiguous Object Descriptions","first_author":"Junhua Mao","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Referring Expression Segmentation","url":"/task/referring-expression-segmentation","datasets_with_task":"/datasets/task/referring-expression-segmentation"},{"name":"Referring Expression Comprehension","url":"/task/referring-expression-comprehension","datasets_with_task":"/datasets/task/referring-expression-comprehension"},{"name":"Zero-Shot Region Description","url":"/task/zero-shot-region-description","datasets_with_task":"/datasets/task/zero-shot-region-description"},{"name":"Natural Language Visual Grounding","url":"/task/natural-language-visual-grounding","datasets_with_task":"/datasets/task/natural-language-visual-grounding"},{"name":"Deep Attention","url":"/task/deep-attention","datasets_with_task":"/datasets/task/deep-attention"}],"languages":[],"variants":["Google Refexp","RefCOCOg-val","RefCOCOg-test"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/gref","frameworks":["tf","jax"]},{"repo":"https://github.com/mjhucla/Google_Refexp_toolbox","url":"https://github.com/mjhucla/Google_Refexp_toolbox","frameworks":[]}],"num_papers_in_archive":46,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","task":"Referring Expression Segmentation","dataset_variant":"RefCOCOg-val","rows":23,"metrics":["Overall IoU","Mean IoU","IoU","mIoU"],"first_row_in_archive_order":{"model":"MLCD-Seg-7B","paper":"/paper/multi-label-cluster-discrimination-for-visual","metrics":{"Overall IoU":"79.9"},"code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","task":"Referring Expression Segmentation","dataset_variant":"RefCOCOg-test","rows":18,"metrics":["Overall IoU","Mean IoU","mIoU"],"first_row_in_archive_order":{"model":"UniLSeg-100","paper":"/paper/universal-segmentation-at-arbitrary","metrics":{"Overall IoU":"80.54"},"code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":20,"of":20,"counts":{"papers_with_a_benchmark_row":20,"with_a_code_link":18,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":20,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/deris-decoupling-perception-and-cognition-for","slug":"deris-decoupling-perception-and-cognition-for","title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","date":"2025-07-02","arxiv_id":"2507.01738","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/densely-connected-parameter-efficient-tuning","slug":"densely-connected-parameter-efficient-tuning","title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","date":"2025-01-15","arxiv_id":"2501.08580","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":9,"samples_unverified":4,"pointer_only_for_licence":9,"official":{"repos":["jiaqihuang01/detris"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/densely-connected-parameter-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2501.08580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08580"}}}},{"paper":"/paper/multi-task-visual-grounding-with-coarse-to","slug":"multi-task-visual-grounding-with-coarse-to","title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","date":"2025-01-12","arxiv_id":"2501.06710","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["dmmm1997/c3vg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-visual-grounding-with-coarse-to#ran","syntology_url":"https://syntology.ai/paper/2501.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06710"}}}},{"paper":"/paper/maskris-semantic-distortion-aware-data","slug":"maskris-semantic-distortion-aware-data","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","date":"2024-11-28","arxiv_id":"2411.19067","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}}}},{"paper":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":7,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}}}},{"paper":"/paper/safari-adaptive-sequence-transformer-for","slug":"safari-adaptive-sequence-transformer-for","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","date":"2024-07-02","arxiv_id":"2407.02389","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["hustvl/evf-sam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evf-sam-early-vision-language-fusion-for-text#ran","syntology_url":"https://syntology.ai/paper/2406.20076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20076"}}}},{"paper":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/groundhog-grounding-large-language-models-to","slug":"groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","arxiv_id":"2402.16846","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mask-grounding-for-referring-image","slug":"mask-grounding-for-referring-image","title":"Mask Grounding for Referring Image Segmentation","date":"2023-12-19","arxiv_id":"2312.12198","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":3,"pointer_only_for_licence":13,"official":{"repos":["yxchng/mask-grounding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mask-grounding-for-referring-image#ran","syntology_url":"https://syntology.ai/paper/2312.12198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12198"}}}},{"paper":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"paper":"/paper/universal-segmentation-at-arbitrary","slug":"universal-segmentation-at-arbitrary","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","date":"2023-12-04","arxiv_id":"2312.01623","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":12,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["workforai/UniLSeg","yongliu20/UniLSeg"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universal-segmentation-at-arbitrary#ran","syntology_url":"https://syntology.ai/paper/2312.01623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01623"}}}},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}}}},{"paper":"/paper/generalized-decoding-for-pixel-image-and","slug":"generalized-decoding-for-pixel-image-and","title":"Generalized Decoding for Pixel, Image, and Language","date":"2022-12-21","arxiv_id":"2212.11270","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}}}},{"paper":"/paper/lavt-language-aware-vision-transformer-for","slug":"lavt-language-aware-vision-transformer-for","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","date":"2021-12-04","arxiv_id":"2112.02244","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vision-language-transformer-and-query","slug":"vision-language-transformer-and-query","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2021-08-12","arxiv_id":"2108.05565","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/comprehensive-multi-modal-interactions-for","slug":"comprehensive-multi-modal-interactions-for","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","date":"2021-04-21","arxiv_id":"2104.10412","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/deris-decoupling-perception-and-cognition-for","slug":"deris-decoupling-perception-and-cognition-for","title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","date":"2025-07-02","arxiv_id":"2507.01738","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/densely-connected-parameter-efficient-tuning","slug":"densely-connected-parameter-efficient-tuning","title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","date":"2025-01-15","arxiv_id":"2501.08580","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":9,"samples_unverified":4,"pointer_only_for_licence":9,"official":{"repos":["jiaqihuang01/detris"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/densely-connected-parameter-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2501.08580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08580"}}}},{"paper":"/paper/multi-task-visual-grounding-with-coarse-to","slug":"multi-task-visual-grounding-with-coarse-to","title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","date":"2025-01-12","arxiv_id":"2501.06710","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["dmmm1997/c3vg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-task-visual-grounding-with-coarse-to#ran","syntology_url":"https://syntology.ai/paper/2501.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06710"}}}},{"paper":"/paper/maskris-semantic-distortion-aware-data","slug":"maskris-semantic-distortion-aware-data","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","date":"2024-11-28","arxiv_id":"2411.19067","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}}}},{"paper":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":7,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}}}},{"paper":"/paper/safari-adaptive-sequence-transformer-for","slug":"safari-adaptive-sequence-transformer-for","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","date":"2024-07-02","arxiv_id":"2407.02389","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["hustvl/evf-sam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evf-sam-early-vision-language-fusion-for-text#ran","syntology_url":"https://syntology.ai/paper/2406.20076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20076"}}}},{"paper":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/groundhog-grounding-large-language-models-to","slug":"groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","arxiv_id":"2402.16846","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mask-grounding-for-referring-image","slug":"mask-grounding-for-referring-image","title":"Mask Grounding for Referring Image Segmentation","date":"2023-12-19","arxiv_id":"2312.12198","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":3,"pointer_only_for_licence":13,"official":{"repos":["yxchng/mask-grounding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mask-grounding-for-referring-image#ran","syntology_url":"https://syntology.ai/paper/2312.12198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12198"}}}},{"paper":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"paper":"/paper/universal-segmentation-at-arbitrary","slug":"universal-segmentation-at-arbitrary","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","date":"2023-12-04","arxiv_id":"2312.01623","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":12,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["workforai/UniLSeg","yongliu20/UniLSeg"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universal-segmentation-at-arbitrary#ran","syntology_url":"https://syntology.ai/paper/2312.01623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01623"}}}},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}}}},{"paper":"/paper/generalized-decoding-for-pixel-image-and","slug":"generalized-decoding-for-pixel-image-and","title":"Generalized Decoding for Pixel, Image, and Language","date":"2022-12-21","arxiv_id":"2212.11270","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}}}},{"paper":"/paper/lavt-language-aware-vision-transformer-for","slug":"lavt-language-aware-vision-transformer-for","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","date":"2021-12-04","arxiv_id":"2112.02244","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vision-language-transformer-and-query","slug":"vision-language-transformer-and-query","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2021-08-12","arxiv_id":"2108.05565","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/comprehensive-multi-modal-interactions-for","slug":"comprehensive-multi-modal-interactions-for","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","date":"2021-04-21","arxiv_id":"2104.10412","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":10,"papers_where_code_ran_first_page":"/dataset/google-refexp/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/google-refexp/papers/ran/1","json":"/dataset/google-refexp/papers/ran/1.json","rows":10}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":10,"samples_harvested":115,"samples_ran":88,"samples_constructed":7,"samples_ran_checked":35,"samples_ran_instrument_failed":53,"samples_unverified":27,"pointer_only_for_licence":42,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":10,"papers_with_a_run_with_no_instrument_failure":9,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","since_archive":"/sota/referring-expression-segmentation-on-refcocog#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"c1e0006f3d764b0fc0cc9bd91887d46c283a0aca162deffab38e625f047188f1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}