{"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":"/method/mdetr","slug":"mdetr","name":"MDETR","full_name":"MDETR","full_name_withheld":false,"description_markdown":"**MDETR** is an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. It utilizes a [transformer](https://paperswithcode.com/method/transformer)-based architecture to reason jointly over text and image by fusing the two modalities at an early stage of the model. The network is pre-trained on 1.3M text-image pairs, mined from pre-existing multi-modal datasets having explicit alignment between phrases in text and objects in the image. The network is then fine-tuned on several downstream tasks such as phrase grounding, referring expression comprehension and segmentation.","description_state":"present","introduced_year":null,"introduced_by":{"title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","paper":"/paper/mdetr-modulated-detection-for-end-to-end","first_author":"Aishwarya Kamath","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mdetr-modulated-detection-for-end-to-end"},"source":{"url":"https://arxiv.org/abs/2104.12763v2","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Object Detection Models","url":"/methods/category/object-detection-models","pwc_aliases":[]}],"n_papers_tagged":13,"archive_num_papers":13,"papers_newest_first":[{"paper":"/paper/disambiguating-reference-in-visually-grounded","slug":"disambiguating-reference-in-visually-grounded","title":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","date":"2025-05-16","arxiv_id":"2505.11726","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sinadumi/mmrr"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"seeing-more-with-less-human-like","title":"Seeing More with Less: Human-like Representations in Vision Models","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/lightmdetr-a-lightweight-approach-for-low","slug":"lightmdetr-a-lightweight-approach-for-low","title":"A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training","date":"2024-08-20","arxiv_id":"2408.10787","n_code_links":1,"syntology":null},{"paper":null,"slug":"elsa-evaluating-localization-of-social","title":"ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection","date":"2024-06-03","arxiv_id":"2406.01551","n_code_links":0,"syntology":null},{"paper":"/paper/augment-the-pairs-semantics-preserving-image","slug":"augment-the-pairs-semantics-preserving-image","title":"Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models","date":"2023-11-05","arxiv_id":"2311.02536","n_code_links":1,"syntology":null},{"paper":"/paper/3d-aware-visual-question-answering-about-1","slug":"3d-aware-visual-question-answering-about-1","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","date":"2023-10-27","arxiv_id":"2310.17914","n_code_links":2,"syntology":{"ran":22,"of":28,"n_ran_checked":21,"n_instrument":1,"unverified":6,"pointer_only":14,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["xingruiwang/3d-aware-vqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"dynamic-inference-with-grounding-based-vision","title":"Dynamic Inference With Grounding Based Vision and Language Models","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-mdetr-a-dynamic-multimodal","title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding","date":"2022-09-28","arxiv_id":"2209.13959","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-modulated-detection-transformer-as","slug":"exploring-modulated-detection-transformer-as","title":"Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos","date":"2022-09-21","arxiv_id":"2209.10126","n_code_links":1,"syntology":null},{"paper":"/paper/looking-outside-the-box-to-ground-language-in","slug":"looking-outside-the-box-to-ground-language-in","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","date":"2021-12-16","arxiv_id":"2112.08879","n_code_links":1,"syntology":null},{"paper":null,"slug":"augmented-2d-tan-a-two-stage-approach-for","title":"Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding","date":"2021-06-20","arxiv_id":"2106.10634","n_code_links":0,"syntology":null},{"paper":"/paper/team-ruc-aim3-technical-report-at-activitynet-1","slug":"team-ruc-aim3-technical-report-at-activitynet-1","title":"Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object Localization","date":"2021-06-11","arxiv_id":"2106.06138","n_code_links":1,"syntology":null},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"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","n_code_links":5,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ashkamath/mdetr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":13,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":13,"with_a_code_link":8,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/mdetr/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/mdetr/papers/ran/1","json":"/method/mdetr/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/referring-expression-comprehension","name":"Referring Expression Comprehension","papers":5},{"task":"/task/phrase-grounding","name":"Phrase Grounding","papers":4},{"task":"/task/question-answering","name":"Question Answering","papers":4},{"task":"/task/referring-expression","name":"Referring Expression","papers":4},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":4},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/visual-grounding","name":"Visual Grounding","papers":3},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/referring-expression-segmentation","name":"Referring Expression Segmentation","papers":2},{"task":"/task/action-detection","name":"Action Detection","papers":1},{"task":"/task/action-recognition-in-videos-2","name":"Action Recognition In Videos","papers":1},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/caption-generation","name":"Caption Generation","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/coreference-resolution","name":"Coreference Resolution","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1}],"tasks_shown":20,"n_tasks":34,"usage_by_year":[{"year":"2021","papers":4},{"year":"2022","papers":2},{"year":"2023","papers":3},{"year":"2024","papers":2},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mdetr"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=MDETR","read_at":"2026-10-05T00:59:01+00:00","query":"MDETR","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"MDETR","origin_arxiv_id":"2104.12763"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2104.12763","repositories":{"listed":5,"in_graph":5,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2104.12763","citations":1204},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'MDETR'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2104.12763","page":"/paper/mdetr-modulated-detection-for-end-to-end","syntology_url":"https://syntology.ai/paper/2104.12763","in_graph_layer":true,"samples":11,"ran":7,"n_ran_checked":6,"n_instrument":1,"unverified":4,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 5 in the graph, strongest link: official). This answer is about arXiv:2104.12763, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"d11cb9cdbe183c6e7cf6db3398e14bf6cad7e136c02d478aabd43d1f5ed9371c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}