{"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":3,"n_unverified":1,"n_pointer_only":4}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":34,"tagged_in_all":69,"items":[{"url":"/paper/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":5,"n_unverified":5,"n_pointer_only":10}},{"url":"/paper/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","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":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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","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":7,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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":9,"n_unverified":8,"n_pointer_only":17}},{"url":"/paper/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_unverified":2,"n_pointer_only":2}},{"url":"/paper/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","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":10,"n_unverified":6,"n_pointer_only":16}},{"url":"/paper/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":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/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","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":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","date":"2021-10-21","arxiv_id":"2110.10834","repositories_listed":1,"syntology":null}],"syntology_records":14,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}