{"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/dense-captioning","name":"Dense Captioning","slug":"dense-captioning","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":69,"papers_with_code":34,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/dense-captioning-on-visual-genome","slug":"dense-captioning-on-visual-genome","dataset":"Visual Genome","dataset_url":"/dataset/visual-genome","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"ControlCap","paper_title":"ControlCap: Controllable Region-level Captioning","paper_url":"/paper/controllable-dense-captioner-with-multimodal","paper_date":"2024-01-31","arxiv_id":"2401.17910","code_links":[{"title":"callsys/controlcap","url":"https://github.com/callsys/controlcap"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controllable-dense-captioner-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2401.17910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17910"}},"official":{"repos":["callsys/controlcap"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/visual-genome","name":"Visual Genome","full_name":"","num_papers_in_archive":1256},{"url":"/dataset/visargs","name":"VisArgs","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/live-video-captioning","name":"Live Video Captioning"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":69,"of":69,"of_with_code":34,"tagged_in_all":69,"counts":{"archive_papers_tagged":69,"with_a_code_link":34,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":69,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":13,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/3d-llm-injecting-the-3d-world-into-large","slug":"3d-llm-injecting-the-3d-world-into-large","title":"3D-LLM: Injecting the 3D World into Large Language Models","date":"2023-07-24","arxiv_id":"2307.12981","repositories_listed":5,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"6 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/3d-llm-injecting-the-3d-world-into-large#ran","syntology_url":"https://syntology.ai/paper/2307.12981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12981"}},"official":null}},{"url":"/paper/dense-captioning-events-in-videos","slug":"dense-captioning-events-in-videos","title":"Dense-Captioning Events in Videos","date":"2017-05-02","arxiv_id":"1705.00754","repositories_listed":4,"syntology":null},{"url":"/paper/a-hierarchical-approach-for-generating","slug":"a-hierarchical-approach-for-generating","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","date":"2016-11-20","arxiv_id":"1611.06607","repositories_listed":3,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-hierarchical-approach-for-generating#ran","syntology_url":"https://syntology.ai/paper/1611.06607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06607"}},"official":null}},{"url":"/paper/comicap-a-vlms-pipeline-for-dense-captioning","slug":"comicap-a-vlms-pipeline-for-dense-captioning","title":"ComiCap: A VLMs pipeline for dense captioning of Comic Panels","date":"2024-09-24","arxiv_id":"2409.16159","repositories_listed":2,"syntology":null},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/stsbench-a-spatio-temporal-scenario-benchmark","slug":"stsbench-a-spatio-temporal-scenario-benchmark","title":"STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving","date":"2025-06-06","arxiv_id":"2506.06218","repositories_listed":1,"syntology":null},{"url":"/paper/tempura-temporal-event-masked-prediction-and","slug":"tempura-temporal-event-masked-prediction-and","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","date":"2025-05-02","arxiv_id":"2505.01583","repositories_listed":1,"syntology":null},{"url":"/paper/perla-perceptive-3d-language-assistant","slug":"perla-perceptive-3d-language-assistant","title":"PerLA: Perceptive 3D Language Assistant","date":"2024-11-29","arxiv_id":"2411.19774","repositories_listed":1,"syntology":null},{"url":"/paper/pavecap-the-first-multimodal-framework-for","slug":"pavecap-the-first-multimodal-framework-for","title":"PaveCap: The First Multimodal Framework for Comprehensive Pavement Condition Assessment with Dense Captioning and PCI Estimation","date":"2024-08-07","arxiv_id":"2408.04110","repositories_listed":1,"syntology":null},{"url":"/paper/3d-vision-and-language-pretraining-with-large","slug":"3d-vision-and-language-pretraining-with-large","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","date":"2024-07-08","arxiv_id":"2407.06084","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-vision-and-language-pretraining-with-large#ran","syntology_url":"https://syntology.ai/paper/2407.06084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06084"}},"official":{"repos":["idejie/3DSyn"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/details-make-a-difference-object-state","slug":"details-make-a-difference-object-state","title":"Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning","date":"2024-06-14","arxiv_id":"2406.09988","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/details-make-a-difference-object-state#ran","syntology_url":"https://syntology.ai/paper/2406.09988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09988"}},"official":{"repos":["xiao-wen-sun/ossa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-3d-llm-with-referent-tokens","slug":"grounded-3d-llm-with-referent-tokens","title":"Grounded 3D-LLM with Referent Tokens","date":"2024-05-16","arxiv_id":"2405.10370","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":17,"phrase":"13 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; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/grounded-3d-llm-with-referent-tokens#ran","syntology_url":"https://syntology.ai/paper/2405.10370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10370"}},"official":{"repos":["OpenRobotLab/Grounded_3D-LLM"],"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"]}}},{"url":"/paper/pllava-parameter-free-llava-extension-from-1","slug":"pllava-parameter-free-llava-extension-from-1","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","date":"2024-04-25","arxiv_id":"2404.16994","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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/pllava-parameter-free-llava-extension-from-1#ran","syntology_url":"https://syntology.ai/paper/2404.16994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16994"}},"official":{"repos":["magic-research/PLLaVA"],"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/rethinking-3d-dense-caption-and-visual","slug":"rethinking-3d-dense-caption-and-visual","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","date":"2024-04-17","arxiv_id":"2404.11064","repositories_listed":1,"syntology":null},{"url":"/paper/tod3cap-towards-3d-dense-captioning-in","slug":"tod3cap-towards-3d-dense-captioning-in","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","date":"2024-03-28","arxiv_id":"2403.19589","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":4,"n_violates":1,"n_no_contract":1,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/tod3cap-towards-3d-dense-captioning-in#ran","syntology_url":"https://syntology.ai/paper/2403.19589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19589"}},"official":{"repos":["jxbbb/tod3cap"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-dense-captioner-with-multimodal","slug":"controllable-dense-captioner-with-multimodal","title":"ControlCap: Controllable Region-level Captioning","date":"2024-01-31","arxiv_id":"2401.17910","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controllable-dense-captioner-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2401.17910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17910"}},"official":{"repos":["callsys/controlcap"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ll3da-visual-interactive-instruction-tuning-1","slug":"ll3da-visual-interactive-instruction-tuning-1","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ll3da-visual-interactive-instruction-tuning","slug":"ll3da-visual-interactive-instruction-tuning","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","date":"2023-11-30","arxiv_id":"2311.18651","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ll3da-visual-interactive-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2311.18651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18651"}},"official":{"repos":["open3da/ll3da"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/3d-vista-pre-trained-transformer-for-3d","slug":"3d-vista-pre-trained-transformer-for-3d","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","date":"2023-08-08","arxiv_id":"2308.04352","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/3d-vista-pre-trained-transformer-for-3d#ran","syntology_url":"https://syntology.ai/paper/2308.04352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04352"}},"official":null}},{"url":"/paper/enhancing-vision-language-pre-training-with","slug":"enhancing-vision-language-pre-training-with","title":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","date":"2023-05-19","arxiv_id":"2305.11769","repositories_listed":1,"syntology":null},{"url":"/paper/iiitd-20k-dense-captioning-for-text-image","slug":"iiitd-20k-dense-captioning-for-text-image","title":"IIITD-20K: Dense captioning for Text-Image ReID","date":"2023-05-08","arxiv_id":"2305.04497","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","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"}},"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"]}}},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/grit-a-generative-region-to-text-transformer","slug":"grit-a-generative-region-to-text-transformer","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","date":"2022-12-01","arxiv_id":"2212.00280","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/grit-a-generative-region-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.00280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00280"}},"official":{"repos":["JialianW/GRiT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-visuospatial-linguistic-and-1","slug":"integrating-visuospatial-linguistic-and-1","title":"Integrating Visuospatial, Linguistic, and Commonsense Structure into Story Visualization","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/integrating-visuospatial-linguistic-and","slug":"integrating-visuospatial-linguistic-and","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","date":"2021-10-21","arxiv_id":"2110.10834","repositories_listed":1,"syntology":null},{"url":"/paper/dense-captioning-events-in-videos-sysu","slug":"dense-captioning-events-in-videos-sysu","title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","date":"2020-06-21","arxiv_id":"2006.11693","repositories_listed":1,"syntology":null},{"url":"/paper/joint-event-detection-and-description-in","slug":"joint-event-detection-and-description-in","title":"Joint Event Detection and Description in Continuous Video Streams","date":"2018-02-28","arxiv_id":"1802.10250","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/joint-event-detection-and-description-in#ran","syntology_url":"https://syntology.ai/paper/1802.10250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10250"}},"official":{"repos":["VisionLearningGroup/JEDDi-Net"],"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/dense-captioning-with-joint-inference-and","slug":"dense-captioning-with-joint-inference-and","title":"Dense Captioning with Joint Inference and Visual Context","date":"2016-11-21","arxiv_id":"1611.06949","repositories_listed":1,"syntology":null},{"url":"/paper/densecap-fully-convolutional-localization","slug":"densecap-fully-convolutional-localization","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","date":"2015-11-24","arxiv_id":"1511.07571","repositories_listed":1,"syntology":null},{"url":null,"slug":"does-your-3d-encoder-really-work-when","title":"Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs","date":"2025-06-05","arxiv_id":"2506.05318","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-spatial-understanding-in-mllms","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","date":"2024-12-09","arxiv_id":"2412.06613","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-scene-graph-guided-vision-language-pre","title":"3D Scene Graph Guided Vision-Language Pre-training","date":"2024-11-27","arxiv_id":"2411.18666","repositories_listed":0,"syntology":null},{"url":null,"slug":"hint-ad-holistically-aligned-interpretability","title":"Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving","date":"2024-09-10","arxiv_id":"2409.06702","repositories_listed":0,"syntology":null},{"url":null,"slug":"xgen-videosyn-1-high-fidelity-text-to-video","title":"xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations","date":"2024-08-22","arxiv_id":"2408.12590","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-captioning-enhancing-visual","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","date":"2024-07-09","arxiv_id":"2407.06723","repositories_listed":0,"syntology":null},{"url":"/paper/detclipv3-towards-versatile-generative-open","slug":"detclipv3-towards-versatile-generative-open","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","date":"2024-04-14","arxiv_id":"2404.09216","repositories_listed":0,"syntology":null},{"url":null,"slug":"entity6k-a-large-open-domain-evaluation","title":"Entity6K: A Large Open-Domain Evaluation Dataset for Real-World Entity Recognition","date":"2024-03-19","arxiv_id":"2403.12339","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcap-generating-rich-localized-and","title":"FlexCap: Describe Anything in Images in Controllable Detail","date":"2024-03-18","arxiv_id":"2403.12026","repositories_listed":0,"syntology":null},{"url":"/paper/scene-llm-extending-language-model-for-3d","slug":"scene-llm-extending-language-model-for-3d","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","date":"2024-03-18","arxiv_id":"2403.11401","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-3d-dense-captioning","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","date":"2024-03-12","arxiv_id":"2403.07469","repositories_listed":0,"syntology":null},{"url":null,"slug":"capdet-unifying-dense-captioning-and-open","title":"CapDet: Unifying Dense Captioning and Open-World Detection Pretraining","date":"2023-03-04","arxiv_id":"2303.02489","repositories_listed":0,"syntology":null},{"url":null,"slug":"unit3d-a-unified-transformer-for-3d-dense","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","date":"2022-12-01","arxiv_id":"2212.00836","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"savchoi-detecting-suspicious-activities-using","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","date":"2022-07-24","arxiv_id":"2207.11838","repositories_listed":0,"syntology":null},{"url":null,"slug":"caponimage-context-driven-dense-captioning-on","title":"CapOnImage: Context-driven Dense-Captioning on Image","date":"2022-04-27","arxiv_id":"2204.12974","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-aware-pretraining-for-dense-video","title":"Semantic-Aware Pretraining for Dense Video Captioning","date":"2022-04-13","arxiv_id":"2204.07449","repositories_listed":0,"syntology":null},{"url":null,"slug":"describing-image-focused-in-cognitive-and","title":"Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs","date":"2022-02-10","arxiv_id":"2202.05331","repositories_listed":0,"syntology":null},{"url":"/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,"repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-diversity-and-reducing-redundancy","title":"Improving Diversity and Reducing Redundancy in Paragraph Captions","date":"2020-07-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/team-ruc-aim3-technical-report-at-activitynet","slug":"team-ruc-aim3-technical-report-at-activitynet","title":"Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning","date":"2020-06-14","arxiv_id":"2006.07896","repositories_listed":0,"syntology":null},{"url":null,"slug":"activitynet-2019-task-3-exploring-contexts","title":"Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos","date":"2019-07-11","arxiv_id":"1907.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-procedure-captioning-in-narrated","title":"Dense Procedure Captioning in Narrated Instructional Videos","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"trimmed-action-recognition-dense-captioning","title":"Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019","date":"2019-06-14","arxiv_id":"1906.07016","repositories_listed":0,"syntology":null},{"url":"/paper/context-and-attribute-grounded-dense","slug":"context-and-attribute-grounded-dense","title":"Context and Attribute Grounded Dense Captioning","date":"2019-04-02","arxiv_id":"1904.01410","repositories_listed":0,"syntology":null},{"url":null,"slug":"yh-technologies-at-activitynet-challenge-2018","title":"YH Technologies at ActivityNet Challenge 2018","date":"2018-06-29","arxiv_id":"1807.00686","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-vision-technologies-submission-to","title":"Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos","date":"2018-06-25","arxiv_id":"1806.09278","repositories_listed":0,"syntology":null},{"url":null,"slug":"ruccmu-system-report-for-dense-captioning","title":"RUC+CMU: System Report for Dense Captioning Events in Videos","date":"2018-06-22","arxiv_id":"1806.08854","repositories_listed":0,"syntology":null},{"url":null,"slug":"fooling-vision-and-language-models-despite","title":"Fooling Vision and Language Models Despite Localization and Attention Mechanism","date":"2017-09-25","arxiv_id":"1709.08693","repositories_listed":0,"syntology":null},{"url":null,"slug":"visually-grounded-word-embeddings-and-richer","title":"Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation","date":"2017-07-04","arxiv_id":"1707.01009","repositories_listed":0,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"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_where_code_ran":13,"papers_where_code_ran_first_page":"/task/dense-captioning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/dense-captioning/papers/ran/1","json":"/task/dense-captioning/papers/ran/1.json","rows":13}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"1dacc7d8cd008882f6604a30b2851454b5673b5c3e6021bd8675077bbe731efa","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}