{"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/referring-expression-comprehension/papers/2","list_of":"/task/referring-expression-comprehension","task":"Referring Expression Comprehension","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,167],"of":167,"counts":{"archive_papers_tagged":167,"with_a_code_link":98,"where_syntology_ran_a_sample":50,"not_listed_spam_title":0,"listed":167,"listed_where_code_ran":50,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":47,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":47,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"first_page":"/task/referring-expression-comprehension","prev":"/task/referring-expression-comprehension","next":null,"papers":[{"url":"/paper/weakmcn-multi-task-collaborative-network-for","slug":"weakmcn-multi-task-collaborative-network-for","title":"WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation","date":"2025-05-24","arxiv_id":"2505.18686","repositories_listed":0,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":24,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/weakmcn-multi-task-collaborative-network-for#ran","syntology_url":"https://syntology.ai/paper/2505.18686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18686"}},"official":null}},{"url":null,"slug":"beyond-object-categories-multi-attribute","title":"Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding","date":"2025-03-25","arxiv_id":"2503.19240","repositories_listed":0,"syntology":null},{"url":null,"slug":"georsmllm-a-multimodal-large-language-model","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","date":"2025-03-16","arxiv_id":"2503.12490","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spatial-language-grounding-through","title":"Exploring Spatial Language Grounding Through Referring Expressions","date":"2025-02-04","arxiv_id":"2502.04359","repositories_listed":0,"syntology":null},{"url":null,"slug":"flora-formal-language-model-enables-robust","title":"FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis","date":"2025-01-17","arxiv_id":"2501.09887","repositories_listed":0,"syntology":null},{"url":null,"slug":"omni-rgpt-unifying-image-and-video-region","title":"Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks","date":"2025-01-14","arxiv_id":"2501.08326","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-alignment-enhanced-adaptive","title":"Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension","date":"2025-01-02","arxiv_id":"2501.01416","repositories_listed":0,"syntology":null},{"url":null,"slug":"dvin-dynamic-visual-routing-network-for","title":"DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-aware-cross-modal-feature-refinement","title":"Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"harlequin-color-driven-generation-of","title":"Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension","date":"2024-11-22","arxiv_id":"2411.14807","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-graph-based-referring-expression","title":"Make Graph-based Referring Expression Comprehension Great Again through Expression-guided Dynamic Gating and Regression","date":"2024-09-05","arxiv_id":"2409.03385","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-multi-modal-llm-evaluation","title":"Revisiting Multi-Modal LLM Evaluation","date":"2024-08-09","arxiv_id":"2408.05334","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskinversion-localized-embeddings-via","title":"MaskInversion: Localized Embeddings via Optimization of Explainability Maps","date":"2024-07-29","arxiv_id":"2407.20034","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-grounding-from-generative","title":"Learning Visual Grounding from Generative Vision and Language Model","date":"2024-07-18","arxiv_id":"2407.14563","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-solution-for-the-5th-gcaiac-zero-shot","title":"The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge","date":"2024-07-06","arxiv_id":"2407.04998","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-2-ist-multi-modal-interactive-side-tuning","title":"M$^2$IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension","date":"2024-07-01","arxiv_id":"2407.01131","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-anything-model-for-automated-image","title":"Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO","date":"2024-06-27","arxiv_id":"2406.19057","repositories_listed":0,"syntology":null},{"url":null,"slug":"scanformer-referring-expression-comprehension-1","title":"ScanFormer: Referring Expression Comprehension by Iteratively Scanning","date":"2024-06-26","arxiv_id":"2406.18048","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-driven-affordance-learning-from","title":"Text-driven Affordance Learning from Egocentric Vision","date":"2024-04-03","arxiv_id":"2404.02523","repositories_listed":0,"syntology":null},{"url":null,"slug":"proptest-automatic-property-testing-for","title":"PropTest: Automatic Property Testing for Improved Visual Programming","date":"2024-03-25","arxiv_id":"2403.16921","repositories_listed":0,"syntology":null},{"url":null,"slug":"watervg-waterway-visual-grounding-based-on","title":"WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar","date":"2024-03-19","arxiv_id":"2403.12686","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-region-guidance-improving","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","date":"2024-03-04","arxiv_id":"2403.02325","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-zero-shot-learning-for","title":"Compositional Zero-Shot Learning for Attribute-Based Object Reference in Human-Robot Interaction","date":"2023-12-21","arxiv_id":"2312.13655","repositories_listed":0,"syntology":null},{"url":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-pseudo-labeler-beyond-noun-concepts","title":"Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection","date":"2023-12-04","arxiv_id":"2312.02103","repositories_listed":0,"syntology":null},{"url":null,"slug":"vilam-a-vision-language-model-with-enhanced","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","date":"2023-11-21","arxiv_id":"2311.12327","repositories_listed":0,"syntology":null},{"url":null,"slug":"covlm-composing-visual-entities-and","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","date":"2023-11-06","arxiv_id":"2311.03354","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-referring-expression-comprehension-via-1","title":"Video Referring Expression Comprehension via Transformer with Content-conditioned Query","date":"2023-10-25","arxiv_id":"2310.16402","repositories_listed":0,"syntology":null},{"url":null,"slug":"switching-head-tail-funnel-uniter-for-dual","title":"Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks","date":"2023-07-14","arxiv_id":"2307.07166","repositories_listed":0,"syntology":null},{"url":null,"slug":"switch-bert-learning-to-model-multimodal","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","date":"2023-06-25","arxiv_id":"2306.14182","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-3d-object-detection-in-point","title":"Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving","date":"2023-05-25","arxiv_id":"2305.15765","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"refclip-a-universal-teacher-for-weakly","title":"RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"refteacher-a-strong-baseline-for-semi","title":"RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-referring-expression-comprehension-via","title":"Video Referring Expression Comprehension via Transformer with Content-aware Query","date":"2022-10-06","arxiv_id":"2210.02953","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-for-all-one-stage-referring-expression","title":"One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning","date":"2022-07-31","arxiv_id":"2208.00361","repositories_listed":0,"syntology":null},{"url":"/paper/unified-io-a-unified-model-for-vision","slug":"unified-io-a-unified-model-for-vision","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","date":"2022-06-17","arxiv_id":"2206.08916","repositories_listed":0,"syntology":null},{"url":null,"slug":"refcrowd-grounding-the-target-in-crowd-with","title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","date":"2022-06-16","arxiv_id":"2206.08172","repositories_listed":0,"syntology":null},{"url":null,"slug":"referring-expression-comprehension-via-cross","title":"Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension","date":"2022-04-21","arxiv_id":"2204.09957","repositories_listed":0,"syntology":null},{"url":null,"slug":"findit-generalized-localization-with-natural","title":"FindIt: Generalized Localization with Natural Language Queries","date":"2022-03-31","arxiv_id":"2203.17273","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiated-relevances-embedding-for-group","title":"Differentiated Relevances Embedding for Group-based Referring Expression Comprehension","date":"2022-03-12","arxiv_id":"2203.06382","repositories_listed":0,"syntology":null},{"url":"/paper/webly-supervised-concept-expansion-for","slug":"webly-supervised-concept-expansion-for","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","date":"2022-02-04","arxiv_id":"2202.02317","repositories_listed":0,"syntology":null},{"url":null,"slug":"lite-mdetr-a-lightweight-multi-modal-detector","title":"Lite-MDETR: A Lightweight Multi-Modal Detector","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reclip-a-strong-zero-shot-baseline-for","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"come-again-re-query-in-referring-expression","title":"Evaluating and Improving Interactions with Hazy Oracles","date":"2021-10-19","arxiv_id":"2110.10206","repositories_listed":0,"syntology":null},{"url":null,"slug":"proposal-free-one-stage-referring-expression","title":"Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention","date":"2021-05-05","arxiv_id":"2105.02061","repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-lottery-tickets-with-vision-and","title":"Playing Lottery Tickets with Vision and Language","date":"2021-04-23","arxiv_id":"2104.11832","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-grounding-networks-with-semantic-attention","title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","date":"2021-03-23","arxiv_id":"2103.12346","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-mediated-object-centric-1","title":"Language-Mediated, Object-Centric Representation Learning","date":"2020-12-31","arxiv_id":"2012.15814","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppgn-phrase-guided-proposal-generation","title":"PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension","date":"2020-12-20","arxiv_id":"2012.10890","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-graph-attention-network-for-complex","title":"Modular Graph Attention Network for Complex Visual Relational Reasoning","date":"2020-11-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/arramon-a-joint-navigation-assembly","slug":"arramon-a-joint-navigation-assembly","title":"ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments","date":"2020-11-15","arxiv_id":"2011.07660","repositories_listed":0,"syntology":null},{"url":null,"slug":"commands-4-autonomous-vehicles-c4av-workshop","title":"Commands 4 Autonomous Vehicles (C4AV) Workshop Summary","date":"2020-09-18","arxiv_id":"2009.08792","repositories_listed":0,"syntology":null},{"url":null,"slug":"referring-expression-comprehension-a-survey","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","date":"2020-07-19","arxiv_id":"2007.09554","repositories_listed":0,"syntology":null},{"url":"/paper/ernie-vil-knowledge-enhanced-vision-language","slug":"ernie-vil-knowledge-enhanced-vision-language","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","date":"2020-06-30","arxiv_id":"2006.16934","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-non-specialists-for-accurate-and","title":"Leveraging Non-Specialists for Accurate and Time Efficient AMR Annotation","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"giving-commands-to-a-self-driving-car-a","title":"Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding","date":"2020-03-19","arxiv_id":"2003.08717","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutatt-visual-textual-mutual-guidance-for","title":"MUTATT: Visual-Textual Mutual Guidance for Referring Expression Comprehension","date":"2020-03-18","arxiv_id":"2003.08027","repositories_listed":0,"syntology":null},{"url":"/paper/cops-ref-a-new-dataset-and-task-on","slug":"cops-ref-a-new-dataset-and-task-on","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","date":"2020-03-01","arxiv_id":"2003.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniter-learning-universal-image-text","title":"UNITER: Learning UNiversal Image-TExt Representations","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-graph-attention-for-referring","title":"Dynamic Graph Attention for Referring Expression Comprehension","date":"2019-09-18","arxiv_id":"1909.08164","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-real-time-cross-modality-correlation","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","date":"2019-09-16","arxiv_id":"1909.07072","repositories_listed":0,"syntology":null},{"url":"/paper/vqd-visual-query-detection-in-natural-scenes","slug":"vqd-visual-query-detection-in-natural-scenes","title":"VQD: Visual Query Detection in Natural Scenes","date":"2019-04-04","arxiv_id":"1904.02794","repositories_listed":0,"syntology":null},{"url":null,"slug":"neighbourhood-watch-referring-expression","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","date":"2018-12-12","arxiv_id":"1812.04794","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-referring-expression-comprehension","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","date":"2018-12-09","arxiv_id":"1812.03426","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-attention-a-unified-framework-for","title":"Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries","date":"2017-11-17","arxiv_id":"1711.06370","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-fragment-embeddings-for-bidirectional","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","date":"2014-06-22","arxiv_id":"1406.5679","repositories_listed":0,"syntology":null}],"record_sha256":"f1edaf29362f60fc77edb58ee719dca501a95e5cfd9cc9a1c19c0494ea0f5c40","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}