{"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/scanrefer-dataset","name":"ScanRefer Dataset","full_name":null,"description_markdown":"Contains 51,583 descriptions of 11,046 objects from 800 ScanNet scenes. ScanRefer is the first large-scale effort to perform object localization via natural language expression directly in 3D.\r\n\r\nSource: [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](/paper/scanrefer-3d-object-localization-in-rgb-d)","description_withheld":null,"homepage":"https://github.com/daveredrum/ScanRefer","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/scanrefer-3d-object-localization-in-rgb-d","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","first_author":"Dave Zhenyu Chen","url":null},"license":null,"modalities":[],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Object Localization","url":"/task/object-localization","datasets_with_task":"/datasets/task/object-localization"},{"name":"Sentence Embeddings","url":"/task/sentence-embeddings","datasets_with_task":"/datasets/task/sentence-embeddings"},{"name":"3D dense captioning","url":"/task/3d-dense-captioning","datasets_with_task":"/datasets/task/3d-dense-captioning"}],"languages":[],"variants":["ScanRefer Dataset"],"data_loaders":[{"repo":"https://github.com/daveredrum/ScanRefer","url":"https://github.com/daveredrum/ScanRefer","frameworks":["pytorch"]}],"num_papers_in_archive":63,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-dense-captioning-on-scanrefer-dataset","task":"3D dense captioning","dataset_variant":"ScanRefer Dataset","rows":12,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"3D CoCa","paper":"/paper/3d-coca-contrastive-learners-are-3d","metrics":{"BLEU-4":"45.56","CIDEr":"85.42","METEOR":"30.95","ROUGE-L":"61.98"},"code_links":[{"title":"AIGeeksGroup/3DCoCa","url":"https://github.com/AIGeeksGroup/3DCoCa"}]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":7,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/3d-coca-contrastive-learners-are-3d","slug":"3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/see-it-all-contextualized-late-aggregation","slug":"see-it-all-contextualized-late-aggregation","title":"See It All: Contextualized Late Aggregation for 3D Dense Captioning","date":"2024-08-14","arxiv_id":"2408.07648","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bi-directional-contextual-attention-for-3d","slug":"bi-directional-contextual-attention-for-3d","title":"Bi-directional Contextual Attention for 3D Dense Captioning","date":"2024-08-13","arxiv_id":"2408.06662","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vote2cap-detr-decoupling-localization-and","slug":"vote2cap-detr-decoupling-localization-and","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","date":"2023-09-06","arxiv_id":"2309.02999","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-3d-dense-captioning-with-vote2cap","slug":"end-to-end-3d-dense-captioning-with-vote2cap","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","date":"2023-01-06","arxiv_id":"2301.02508","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ch3cook-fdu/vote2cap-detr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-3d-dense-captioning-with-vote2cap#ran","syntology_url":"https://syntology.ai/paper/2301.02508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02508"}}}},{"paper":"/paper/context-aware-alignment-and-mutual-masking","slug":"context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contextual-modeling-for-3d-dense-captioning","slug":"contextual-modeling-for-3d-dense-captioning","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","date":"2022-10-08","arxiv_id":"2210.03925","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatiality-guided-transformer-for-3d-dense","slug":"spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/more-multi-order-relation-mining-for-dense","slug":"more-multi-order-relation-mining-for-dense","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","date":"2022-03-10","arxiv_id":"2203.05203","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["SxJyJay/MORE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/more-multi-order-relation-mining-for-dense#ran","syntology_url":"https://syntology.ai/paper/2203.05203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05203"}}}},{"paper":"/paper/x-trans2cap-cross-modal-knowledge-transfer","slug":"x-trans2cap-cross-modal-knowledge-transfer","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","date":"2022-03-02","arxiv_id":"2203.00843","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3djcg-a-unified-framework-for-joint-dense","slug":"3djcg-a-unified-framework-for-joint-dense","title":"3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scan2cap-context-aware-dense-captioning-in","slug":"scan2cap-context-aware-dense-captioning-in","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","date":"2020-12-03","arxiv_id":"2012.02206","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/3d-coca-contrastive-learners-are-3d","slug":"3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/see-it-all-contextualized-late-aggregation","slug":"see-it-all-contextualized-late-aggregation","title":"See It All: Contextualized Late Aggregation for 3D Dense Captioning","date":"2024-08-14","arxiv_id":"2408.07648","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bi-directional-contextual-attention-for-3d","slug":"bi-directional-contextual-attention-for-3d","title":"Bi-directional Contextual Attention for 3D Dense Captioning","date":"2024-08-13","arxiv_id":"2408.06662","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vote2cap-detr-decoupling-localization-and","slug":"vote2cap-detr-decoupling-localization-and","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","date":"2023-09-06","arxiv_id":"2309.02999","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-3d-dense-captioning-with-vote2cap","slug":"end-to-end-3d-dense-captioning-with-vote2cap","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","date":"2023-01-06","arxiv_id":"2301.02508","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ch3cook-fdu/vote2cap-detr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-3d-dense-captioning-with-vote2cap#ran","syntology_url":"https://syntology.ai/paper/2301.02508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02508"}}}},{"paper":"/paper/context-aware-alignment-and-mutual-masking","slug":"context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contextual-modeling-for-3d-dense-captioning","slug":"contextual-modeling-for-3d-dense-captioning","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","date":"2022-10-08","arxiv_id":"2210.03925","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatiality-guided-transformer-for-3d-dense","slug":"spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/more-multi-order-relation-mining-for-dense","slug":"more-multi-order-relation-mining-for-dense","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","date":"2022-03-10","arxiv_id":"2203.05203","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["SxJyJay/MORE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/more-multi-order-relation-mining-for-dense#ran","syntology_url":"https://syntology.ai/paper/2203.05203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05203"}}}},{"paper":"/paper/x-trans2cap-cross-modal-knowledge-transfer","slug":"x-trans2cap-cross-modal-knowledge-transfer","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","date":"2022-03-02","arxiv_id":"2203.00843","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3djcg-a-unified-framework-for-joint-dense","slug":"3djcg-a-unified-framework-for-joint-dense","title":"3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scan2cap-context-aware-dense-captioning-in","slug":"scan2cap-context-aware-dense-captioning-in","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","date":"2020-12-03","arxiv_id":"2012.02206","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/scanrefer-dataset/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/scanrefer-dataset/papers/ran/1","json":"/dataset/scanrefer-dataset/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"a2ab925316901c6b2c27f70e8cc4c84d34236f98e753d0d4c0a6727a274b2958","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}