{"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/referit3d","name":"ReferIt3D","full_name":null,"description_markdown":"ReferIt3D provides two large-scale and complementary visio-linguistic datasets: i) Sr3D, which contains 83.5K template-based utterances leveraging spatial relations among fine-grained object classes to localize a referred object in a scene, and ii) Nr3D which contains 41.5K natural, free-form, utterances collected by deploying a 2-player object reference game in 3D scenes. This dataset can be used for 3D visual grounding and 3D dense captioning tasks.","description_withheld":null,"homepage":"https://referit3d.github.io/","introduced_date":"2020-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/referit3d-neural-listeners-for-fine-grained","title":"ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes","first_author":"Panos Achlioptas","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"}],"tasks":[{"name":"3D dense captioning","url":"/task/3d-dense-captioning","datasets_with_task":"/datasets/task/3d-dense-captioning"},{"name":"Natural Language Visual Grounding","url":"/task/natural-language-visual-grounding","datasets_with_task":"/datasets/task/natural-language-visual-grounding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ReferIt3D","Nr3D"],"data_loaders":[],"num_papers_in_archive":104,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-dense-captioning-on-nr3d","task":"3D dense captioning","dataset_variant":"Nr3D","rows":10,"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":"29.29","CIDEr":"52.84","METEOR":"25.55","ROUGE-L":"56.43"},"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":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":4,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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/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/complete-3d-relationships-extraction-modality","slug":"complete-3d-relationships-extraction-modality","title":"Complete 3d relationships extraction modality alignment network for 3d dense captioning","date":"2024-08-01","arxiv_id":null,"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/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/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/d3net-a-speaker-listener-architecture-for","slug":"d3net-a-speaker-listener-architecture-for","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","date":"2021-12-02","arxiv_id":"2112.01551","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/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/complete-3d-relationships-extraction-modality","slug":"complete-3d-relationships-extraction-modality","title":"Complete 3d relationships extraction modality alignment network for 3d dense captioning","date":"2024-08-01","arxiv_id":null,"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/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/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/d3net-a-speaker-listener-architecture-for","slug":"d3net-a-speaker-listener-architecture-for","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","date":"2021-12-02","arxiv_id":"2112.01551","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":1,"papers_where_code_ran_first_page":"/dataset/referit3d/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/referit3d/papers/ran/1","json":"/dataset/referit3d/papers/ran/1.json","rows":1}],"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":1,"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,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"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":"267f1362089e7751ae4a8af9e403481cc49e485d19b9c299090324c1d5a19d3e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}