{"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/zero-shot-grounding-of-objects-from-natural","title":"Zero-Shot Grounding of Objects from Natural Language Queries","arxiv_id":"1908.07129","date":"2019-08-20","proceeding":"ICCV 2019 10","authors":["Arka Sadhu","Kan Chen","Ram Nevatia"],"abstract":"A phrase grounding system localizes a particular object in an image referred to by a natural language query. In previous work, the phrases were restricted to have nouns that were encountered in training, we extend the task to Zero-Shot Grounding(ZSG) which can include novel, \"unseen\" nouns. Current phrase grounding systems use an explicit object detection network in a 2-stage framework where one stage generates sparse proposals and the other stage evaluates them. In the ZSG setting, generating appropriate proposals itself becomes an obstacle as the proposal generator is trained on the entities common in the detection and grounding datasets. We propose a new single-stage model called ZSGNet which combines the detector network and the grounding system and predicts classification scores and regression parameters. Evaluation of ZSG system brings additional subtleties due to the influence of the relationship between the query and learned categories; we define four distinct conditions that incorporate different levels of difficulty. We also introduce new datasets, sub-sampled from Flickr30k Entities and Visual Genome, that enable evaluations for the four conditions. Our experiments show that ZSGNet achieves state-of-the-art performance on Flickr30k and ReferIt under the usual \"seen\" settings and performs significantly better than baseline in the zero-shot setting.","url_abs":"https://arxiv.org/abs/1908.07129v1","url_pdf":"https://arxiv.org/pdf/1908.07129v1.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":"zero-shot-grounding-of-objects-from-natural","repo_url":"https://github.com/TheShadow29/zsgnet-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.07129","atlas_url":"https://app.syntology.ai/?focus=1908.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07129"}},"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/TheShadow29/zsgnet-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"unverified":14},"by_repo_kind":{"official":{"samples":18,"ran":4,"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":"2a8545e480332b47","entry":"add_extras","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/ssd_vgg.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/ssd_vgg.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a8545e480332b47"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/fpn_resnet.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/fpn_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"b490ac8699f5a7ad","entry":"multibox","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/ssd_vgg.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/ssd_vgg.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b490ac8699f5a7ad"}},{"code_sha256_prefix":"6921f7ed00595a4f","entry":"vgg","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/ssd_vgg.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/ssd_vgg.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6921f7ed00595a4f"}},{"code_sha256_prefix":"13ae5809344e4f05","entry":"collater","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/dat_loader.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/dat_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":"13ae5809344e4f05"}},{"code_sha256_prefix":"4b907a406f06ace0","entry":"conv2d","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/mdl.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/mdl.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":"4b907a406f06ace0"}},{"code_sha256_prefix":"7af4e486b4c60709","entry":"conv2d_relu","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/mdl.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/mdl.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":"7af4e486b4c60709"}},{"code_sha256_prefix":"a7dcff4207ca66bf","entry":"cthw2tlbr","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/anchors.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/anchors.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":"a7dcff4207ca66bf"}},{"code_sha256_prefix":"609205821f10988e","entry":"exec_func_if_main_proc","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/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":"609205821f10988e"}},{"code_sha256_prefix":"daf082e9921b6a03","entry":"make_data_sampler","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/dat_loader.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/dat_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":"daf082e9921b6a03"}},{"code_sha256_prefix":"ad11ef6d39eb2ff3","entry":"pad_out","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/fpn_resnet.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/fpn_resnet.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":"ad11ef6d39eb2ff3"}},{"code_sha256_prefix":"dfeaf11b09c7a0bc","entry":"pil2tensor","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/dat_loader.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/dat_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":"dfeaf11b09c7a0bc"}},{"code_sha256_prefix":"b7654b7006fe061d","entry":"reduce_dict","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/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":"b7654b7006fe061d"}},{"code_sha256_prefix":"75e6e3f3c795ee43","entry":"reduce_dict_corr","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/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":"75e6e3f3c795ee43"}},{"code_sha256_prefix":"fdb481756a08ea1e","entry":"reshape","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/evaluator.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/evaluator.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":"fdb481756a08ea1e"}},{"code_sha256_prefix":"fe0212a6c494a57f","entry":"resnet50","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/fpn_resnet.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/fpn_resnet.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":"fe0212a6c494a57f"}},{"code_sha256_prefix":"345cb82041ecd304","entry":"tlbr2cthw","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/anchors.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/anchors.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":"345cb82041ecd304"}},{"code_sha256_prefix":"6206186edff240f5","entry":"tlbr2tlhw","repo":"TheShadow29/zsgnet-pytorch","repo_kind":"official","path":"code/anchors.py","file_url":"https://github.com/TheShadow29/zsgnet-pytorch/blob/HEAD/code/anchors.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":"6206186edff240f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}