{"url":"/task/referring-expression","name":"Referring Expression","slug":"referring-expression","description_markdown":"Referring expressions places a bounding box around\r\nthe instance corresponding to the provided description and\r\nimage.","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":364,"papers_with_code":166,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/referring-expression-on-sqa3d-1","slug":"referring-expression-on-sqa3d-1","dataset":"SQA3D","dataset_url":"/dataset/sqa3d","rows_in_archive":1,"metrics":["Acc@0.5m","Acc@1.0m","Acc@15°","Acc@30°"],"first_row_in_archive_order":{"model":"Random","paper_title":"SQA3D: Situated Question Answering in 3D Scenes","paper_url":"/paper/sqa3d-situated-question-answering-in-3d","paper_date":"2022-10-14","arxiv_id":"2210.07474","code_links":[{"title":"SilongYong/SQA3D","url":"https://github.com/SilongYong/SQA3D"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/sqa3d","name":"SQA3D","full_name":"Situated Question Answering in 3D Scenes","num_papers_in_archive":58},{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/a-game-of-sorts","name":"A Game Of Sorts","full_name":"","num_papers_in_archive":4}],"subtasks":[],"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":166,"tagged_in_all":364,"items":[{"url":"/paper/grounding-dino-marrying-dino-with-grounded","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","date":"2023-03-09","arxiv_id":"2303.05499","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/prompt-based-multi-modal-image-segmentation","title":"Image Segmentation Using Text and Image Prompts","date":"2021-12-18","arxiv_id":"2112.10003","repositories_listed":6,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/towards-visual-grounding-a-survey","title":"Towards Visual Grounding: A Survey","date":"2024-12-28","arxiv_id":"2412.20206","repositories_listed":4,"syntology":{"n":15,"n_ran":9,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/set-of-mark-prompting-unleashes-extraordinary","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","date":"2023-10-17","arxiv_id":"2310.11441","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/modeling-context-in-referring-expressions","title":"Modeling Context in Referring Expressions","date":"2016-07-31","arxiv_id":"1608.00272","repositories_listed":4,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/seqtr-a-simple-yet-universal-network-for","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","date":"2022-03-30","arxiv_id":"2203.16265","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/3d-gres-generalized-3d-referring-expression","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","date":"2024-07-30","arxiv_id":"2407.20664","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/hdc-hierarchical-semantic-decoding-with-1","title":"CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation","date":"2024-05-24","arxiv_id":"2405.15658","repositories_listed":2,"syntology":null},{"url":"/paper/llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/an-open-and-comprehensive-pipeline-for","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","date":"2024-01-04","arxiv_id":"2401.02361","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/localized-symbolic-knowledge-distillation-for-1","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","date":"2023-12-08","arxiv_id":"2312.04837","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/kosmos-2-grounding-multimodal-large-language","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","date":"2023-06-26","arxiv_id":"2306.14824","repositories_listed":2,"syntology":null},{"url":"/paper/gres-generalized-referring-expression-1","title":"GRES: Generalized Referring Expression Segmentation","date":"2023-06-01","arxiv_id":"2306.00968","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/reclip-a-strong-zero-shot-baseline-for-1","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","date":"2022-04-12","arxiv_id":"2204.05991","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/the-project-dialogism-novel-corpus-a-dataset","title":"The Project Dialogism Novel Corpus: A Dataset for Quotation Attribution in Literary Texts","date":"2022-04-12","arxiv_id":"2204.05836","repositories_listed":2,"syntology":null},{"url":"/paper/airbert-in-domain-pretraining-for-vision-and","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","date":"2021-08-20","arxiv_id":"2108.09105","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_unverified":10,"n_pointer_only":6}},{"url":"/paper/multi-task-collaborative-network-for-joint","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","date":"2020-03-19","arxiv_id":"2003.08813","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/a-fast-and-accurate-one-stage-approach-to","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","date":"2019-08-18","arxiv_id":"1908.06354","repositories_listed":2,"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/towards-human-friendly-referring-expression","title":"Generating Easy-to-Understand Referring Expressions for Target Identifications","date":"2018-11-29","arxiv_id":"1811.12104","repositories_listed":2,"syntology":null},{"url":"/paper/a-joint-speaker-listener-reinforcer-model-for","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","date":"2016-12-30","arxiv_id":"1612.09542","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-referring-expressions-in-visually","title":"Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models","date":"2025-06-26","arxiv_id":"2506.21294","repositories_listed":1,"syntology":null},{"url":"/paper/textregion-text-aligned-region-tokens-from","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","date":"2025-05-29","arxiv_id":"2505.23769","repositories_listed":1,"syntology":null}],"syntology_records":21,"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"}}