{"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/improving-one-stage-visual-grounding-by","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","arxiv_id":"2008.01059","date":"2020-08-03","proceeding":"ECCV 2020 8","authors":["Zhengyuan Yang","Tianlang Chen","Li-Wei Wang","Jiebo Luo"],"abstract":"We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. Existing one-stage methods encode the entire language query as a single sentence embedding vector, e.g., taking the embedding from BERT or the hidden state from LSTM. This single vector representation is prone to overlooking the detailed descriptions in the query. To address this query modeling deficiency, we propose a recursive sub-query construction framework, which reasons between image and query for multiple rounds and reduces the referring ambiguity step by step. We show our new one-stage method obtains 5.0%, 4.5%, 7.5%, 12.8% absolute improvements over the state-of-the-art one-stage baseline on ReferItGame, RefCOCO, RefCOCO+, and RefCOCOg, respectively. In particular, superior performances on longer and more complex queries validates the effectiveness of our query modeling.","url_abs":"https://arxiv.org/abs/2008.01059v1","url_pdf":"https://arxiv.org/pdf/2008.01059v1.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":"improving-one-stage-visual-grounding-by","repo_url":"https://github.com/zyang-ur/ReSC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.01059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01059"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ReSC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":20},"by_repo_kind":{"official":{"samples":22,"ran":2,"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":"8d23fbe2b99b840b","entry":"gelu","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/modulation.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/modulation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/loss.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/ReSC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/utils.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":"ec48fe4bebce9e11"}},{"code_sha256_prefix":"419a432ce9a6b3ad","entry":"body_region_confusion_matrix","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/parsing_metrics.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":"419a432ce9a6b3ad"}},{"code_sha256_prefix":"94ef5f8ebf328450","entry":"build_object_targets","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/darknet.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":"94ef5f8ebf328450"}},{"code_sha256_prefix":"694e413f977737ba","entry":"convert_examples_to_features","repo":"zyang-ur/ReSC","repo_kind":"official","path":"dataset/data_loader.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/dataset/data_loader.py","link_basis":"plan_row","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/ReSC","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/darknet.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":"a57e101603c7a691"}},{"code_sha256_prefix":"0336cb59d505cda3","entry":"generate_coord","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/grounding_model.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/grounding_model.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":"0336cb59d505cda3"}},{"code_sha256_prefix":"47314d0f58b9e44b","entry":"label_accuracy_score","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/parsing_metrics.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":"47314d0f58b9e44b"}},{"code_sha256_prefix":"c7ccdc37dfee61f7","entry":"label_confusion_matrix","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/parsing_metrics.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/parsing_metrics.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":"c7ccdc37dfee61f7"}},{"code_sha256_prefix":"7d95e42ef6cbd96a","entry":"letterbox","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/transforms.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":"7d95e42ef6cbd96a"}},{"code_sha256_prefix":"8dc1056f0f6f5443","entry":"load_pretrain","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/checkpoint.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/checkpoint.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":"8dc1056f0f6f5443"}},{"code_sha256_prefix":"44ac945d7427e3cc","entry":"load_resume","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/checkpoint.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/checkpoint.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":"44ac945d7427e3cc"}},{"code_sha256_prefix":"1d7c6e0cc5b3dcf9","entry":"lr_cos","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/loss.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":"1d7c6e0cc5b3dcf9"}},{"code_sha256_prefix":"ff4a9912ba457edd","entry":"mask_softmax","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/modulation.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/modulation.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":"ff4a9912ba457edd"}},{"code_sha256_prefix":"7541c25367bf48c2","entry":"parse_model_config","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/darknet.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/darknet.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":"7541c25367bf48c2"}},{"code_sha256_prefix":"408bfee1417b817e","entry":"random_affine","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/transforms.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":"408bfee1417b817e"}},{"code_sha256_prefix":"e4f50d4eeb6144e9","entry":"read_examples","repo":"zyang-ur/ReSC","repo_kind":"official","path":"dataset/data_loader.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/dataset/data_loader.py","link_basis":"plan_row","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/ReSC","repo_kind":"official","path":"utils/transforms.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/transforms.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":"cb5d2317201b6913"}},{"code_sha256_prefix":"39509f649c31ad13","entry":"xywh2xyxy","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/utils.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":"39509f649c31ad13"}},{"code_sha256_prefix":"a43bd5ac31eb7191","entry":"xyxy2xywh","repo":"zyang-ur/ReSC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/utils/utils.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":"a43bd5ac31eb7191"}},{"code_sha256_prefix":"659cdef76298b02f","entry":"yolo_loss","repo":"zyang-ur/ReSC","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/loss.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":"659cdef76298b02f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}