{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/a-fast-and-accurate-one-stage-approach-to","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","arxiv_id":"1908.06354","date":"2019-08-18","proceeding":"ICCV 2019 10","authors":["Zhengyuan Yang","Boqing Gong","Li-Wei Wang","Wenbing Huang","Dong Yu","Jiebo Luo"],"abstract":"We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank two-stage methods are capped by the quality of the region candidates they propose in the first stage --- if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query's embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.","url_abs":"https://arxiv.org/abs/1908.06354v1","url_pdf":"https://arxiv.org/pdf/1908.06354v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-fast-and-accurate-one-stage-approach-to","repo_url":"https://github.com/zyang-ur/onestage_grounding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-fast-and-accurate-one-stage-approach-to","repo_url":"https://github.com/zyang-ur/ReSC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"yolov3","method_name":"YOLOv3"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.06354","atlas_url":"https://app.syntology.ai/?focus=1908.06354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06354"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zyang-ur/onestage_grounding","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zyang-ur/ReSC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":18},"by_repo_kind":{"official":{"samples":19,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"train_yolo.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/train_yolo.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"ec48fe4bebce9e11","entry":"bbox_iou_numpy","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec48fe4bebce9e11"}},{"code_sha256_prefix":"9811fc4335a757ba","entry":"bbox_randscale","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"dataset/referit_loader.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/dataset/referit_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9811fc4335a757ba"}},{"code_sha256_prefix":"419a432ce9a6b3ad","entry":"body_region_confusion_matrix","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/parsing_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"419a432ce9a6b3ad"}},{"code_sha256_prefix":"94ef5f8ebf328450","entry":"build_object_targets","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/model/darknet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94ef5f8ebf328450"}},{"code_sha256_prefix":"df36ec87b420dbdf","entry":"build_target","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"train_yolo.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/train_yolo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df36ec87b420dbdf"}},{"code_sha256_prefix":"694e413f977737ba","entry":"convert_examples_to_features","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"dataset/referit_loader.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/dataset/referit_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"694e413f977737ba"}},{"code_sha256_prefix":"a57e101603c7a691","entry":"create_modules","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/model/darknet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a57e101603c7a691"}},{"code_sha256_prefix":"0336cb59d505cda3","entry":"generate_coord","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"model/grounding_model.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/model/grounding_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0336cb59d505cda3"}},{"code_sha256_prefix":"47314d0f58b9e44b","entry":"label_accuracy_score","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/parsing_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47314d0f58b9e44b"}},{"code_sha256_prefix":"c7ccdc37dfee61f7","entry":"label_confusion_matrix","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/parsing_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7ccdc37dfee61f7"}},{"code_sha256_prefix":"7d95e42ef6cbd96a","entry":"letterbox","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d95e42ef6cbd96a"}},{"code_sha256_prefix":"7541c25367bf48c2","entry":"parse_model_config","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/model/darknet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7541c25367bf48c2"}},{"code_sha256_prefix":"408bfee1417b817e","entry":"random_affine","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"408bfee1417b817e"}},{"code_sha256_prefix":"e4f50d4eeb6144e9","entry":"read_examples","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"dataset/referit_loader.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/dataset/referit_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4f50d4eeb6144e9"}},{"code_sha256_prefix":"cb5d2317201b6913","entry":"wrap_points","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb5d2317201b6913"}},{"code_sha256_prefix":"39509f649c31ad13","entry":"xywh2xyxy","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39509f649c31ad13"}},{"code_sha256_prefix":"a43bd5ac31eb7191","entry":"xyxy2xywh","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a43bd5ac31eb7191"}},{"code_sha256_prefix":"13969771dccff2bc","entry":"yolo_loss","repo":"zyang-ur/onestage_grounding","repo_kind":"official","path":"train_yolo.py","file_url":"https://github.com/zyang-ur/onestage_grounding/blob/HEAD/train_yolo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13969771dccff2bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}