{"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/open-vocabulary-object-detection/papers/2","list_of":"/task/open-vocabulary-object-detection","task":"Open Vocabulary Object Detection","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":[101,145],"of":145,"counts":{"archive_papers_tagged":145,"with_a_code_link":92,"where_syntology_ran_a_sample":36,"not_listed_spam_title":0,"listed":145,"listed_where_code_ran":36,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/open-vocabulary-object-detection","prev":"/task/open-vocabulary-object-detection","next":null,"papers":[{"url":null,"slug":"learning-the-ropes-better-2d-and-3d-position","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","date":"2025-02-04","arxiv_id":"2502.02562","repositories_listed":0,"syntology":null},{"url":null,"slug":"modulating-cnn-features-with-pre-trained-vit","title":"Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection","date":"2025-01-28","arxiv_id":"2501.16981","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-objectness-modeling-unifies-novel","title":"Open-World Objectness Modeling Unifies Novel Object Detection","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-bag-of-views-for-open-vocabulary","title":"Sampling Bag of Views for Open-Vocabulary Object Detection","date":"2024-12-24","arxiv_id":"2412.18273","repositories_listed":0,"syntology":null},{"url":null,"slug":"densevlm-a-retrieval-and-decoupled-alignment","title":"DenseVLM: A Retrieval and Decoupled Alignment Framework for Open-Vocabulary Dense Prediction","date":"2024-12-09","arxiv_id":"2412.06244","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-open-vocabulary-object","title":"Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation","date":"2024-11-23","arxiv_id":"2411.15620","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-application-agnostic-automatic-target","title":"An Application-Agnostic Automatic Target Recognition System Using Vision Language Models","date":"2024-11-05","arxiv_id":"2411.03491","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via-language","title":"Open-Vocabulary Object Detection via Language Hierarchy","date":"2024-10-27","arxiv_id":"2410.20371","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-target-driven-instance-detection","title":"Few-shot target-driven instance detection based on open-vocabulary object detection models","date":"2024-10-21","arxiv_id":"2410.16028","repositories_listed":0,"syntology":null},{"url":null,"slug":"ludvig-learning-free-uplifting-of-2d-visual","title":"LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes","date":"2024-10-18","arxiv_id":"2410.14462","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-open-vocabulary-object-detection-by","title":"Boosting Open-Vocabulary Object Detection by Handling Background Samples","date":"2024-10-11","arxiv_id":"2410.08645","repositories_listed":0,"syntology":null},{"url":null,"slug":"vovtrack-exploring-the-potentiality-in-videos","title":"VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking","date":"2024-10-11","arxiv_id":"2410.08529","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-and-detect-training-free-long-tail","title":"Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval","date":"2024-09-26","arxiv_id":"2409.18733","repositories_listed":0,"syntology":null},{"url":null,"slug":"ha-fgovd-highlighting-fine-grained-attributes","title":"HA-FGOVD: Highlighting Fine-grained Attributes via Explicit Linear Composition for Open-Vocabulary Object Detection","date":"2024-09-24","arxiv_id":"2409.16136","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-open-vocabulary-video-visual","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","date":"2024-09-19","arxiv_id":"2409.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-potential-of-open-vocabulary-models","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","date":"2024-08-20","arxiv_id":"2408.11221","repositories_listed":0,"syntology":null},{"url":null,"slug":"bacon-supercharge-your-vlm-with-bag-of","title":"BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs","date":"2024-07-03","arxiv_id":"2407.03314","repositories_listed":0,"syntology":null},{"url":null,"slug":"v3det-challenge-2024-on-vast-vocabulary-and","title":"V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results","date":"2024-06-17","arxiv_id":"2406.11739","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-x-ray-prohibited-item","title":"Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP","date":"2024-06-16","arxiv_id":"2406.10961","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-object-detection-a-study-on-vast","title":"Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024","date":"2024-06-13","arxiv_id":"2406.09201","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-background-prompts-to-discover","title":"Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection","date":"2024-06-01","arxiv_id":"2406.00510","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via","title":"Open-Vocabulary Object Detection via Neighboring Region Attention Alignment","date":"2024-05-14","arxiv_id":"2405.08593","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-your-step-optimal-retrieval-for","title":"Watch Your Step: Optimal Retrieval for Continual Learning at Scale","date":"2024-04-16","arxiv_id":"2404.10758","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":"investigating-robustness-of-open-vocabulary","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","date":"2024-04-01","arxiv_id":"2405.14874","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-with-meta","title":"Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization","date":"2024-03-14","arxiv_id":"2403.09433","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-meet-vlms-boost-open-vocabulary-object","title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors","date":"2024-02-07","arxiv_id":"2402.04630","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcvo-an-efficient-pretraining-free-framework","title":"LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering","date":"2024-01-29","arxiv_id":"2401.15842","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-region-word-alignment-in-built-in","title":"Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-adaptive-and-region-aware-multi-modal","title":"Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-open-vocabulary-object","title":"Weakly Supervised Open-Vocabulary Object Detection","date":"2023-12-19","arxiv_id":"2312.12437","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":"spuriosity-rankings-for-free-a-simple","title":"Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection","date":"2023-10-31","arxiv_id":"2311.00079","repositories_listed":0,"syntology":null},{"url":"/paper/yolov8-based-visual-detection-of-road-hazards","slug":"yolov8-based-visual-detection-of-road-hazards","title":"YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes","date":"2023-10-31","arxiv_id":"2311.00073","repositories_listed":0,"syntology":null},{"url":null,"slug":"edadet-open-vocabulary-object-detection-using","title":"EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment","date":"2023-09-03","arxiv_id":"2309.01151","repositories_listed":0,"syntology":null},{"url":"/paper/contrastive-feature-masking-open-vocabulary","slug":"contrastive-feature-masking-open-vocabulary","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","date":"2023-09-02","arxiv_id":"2309.00775","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-multi-modal-contextual-knowledge","title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","date":"2023-08-30","arxiv_id":"2308.15846","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via-scene","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","date":"2023-07-07","arxiv_id":"2307.03339","repositories_listed":0,"syntology":null},{"url":"/paper/detclipv2-scalable-open-vocabulary-object","slug":"detclipv2-scalable-open-vocabulary-object","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","date":"2023-04-10","arxiv_id":"2304.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-guided-transformers-for-end-to-end","title":"Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection","date":"2023-03-25","arxiv_id":"2303.14386","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-using-pseudo","title":"Open-Vocabulary Object Detection using Pseudo Caption Labels","date":"2023-03-23","arxiv_id":"2303.13040","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-role-of-context-in-region-word","title":"Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection","date":"2023-03-17","arxiv_id":"2303.10093","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-with-an-open","title":"Open-Vocabulary Object Detection With an Open Corpus","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-detect-and-segment-for-open","title":"Learning to Detect and Segment for Open Vocabulary Object Detection","date":"2022-12-23","arxiv_id":"2212.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-3-ovd-fine-grained-visual-text-prompt","title":"Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection","date":"2022-11-02","arxiv_id":"2211.00849","repositories_listed":0,"syntology":null}],"record_sha256":"3dd815ab736ef72d6ec5a6462a85a221d11cb53605678017ce291c0796baeb0b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}