{"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/voxel-informed-language-grounding-2","title":"Voxel-informed Language Grounding","arxiv_id":"2205.09710","date":"2022-05-19","proceeding":"ACL 2022 5","authors":["Rodolfo Corona","Shizhan Zhu","Dan Klein","Trevor Darrell"],"abstract":"Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.","url_abs":"https://arxiv.org/abs/2205.09710v1","url_pdf":"https://arxiv.org/pdf/2205.09710v1.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":"voxel-informed-language-grounding-2","repo_url":"https://github.com/rcorona/voxel_informed_language_grounding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"voxel-informed-language-grounding-2","repo_url":"https://github.com/snaredataset/snare","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.09710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09710"}},"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":"deterministic:regex_extraction","url":"https://github.com/snaredataset/snare","reach":null}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"a4008621e2070d9e","entry":"MaxPool","repo":"snaredataset/snare","repo_kind":"official","path":"models/single_cls.py","file_url":"https://github.com/snaredataset/snare/blob/HEAD/models/single_cls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4008621e2070d9e"}},{"code_sha256_prefix":"ff17d659b14107d5","entry":"MeanPool","repo":"snaredataset/snare","repo_kind":"official","path":"models/single_cls.py","file_url":"https://github.com/snaredataset/snare/blob/HEAD/models/single_cls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff17d659b14107d5"}},{"code_sha256_prefix":"43cc1535fc5f711b","entry":"RandomIndex","repo":"snaredataset/snare","repo_kind":"official","path":"models/single_cls.py","file_url":"https://github.com/snaredataset/snare/blob/HEAD/models/single_cls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43cc1535fc5f711b"}},{"code_sha256_prefix":"488c45769c1e1e1c","entry":"SingleClassifier","repo":"snaredataset/snare","repo_kind":"official","path":"models/single_cls.py","file_url":"https://github.com/snaredataset/snare/blob/HEAD/models/single_cls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"488c45769c1e1e1c"}},{"code_sha256_prefix":"30b934293080d9a0","entry":"TwoRandomIndex","repo":"snaredataset/snare","repo_kind":"official","path":"models/single_cls.py","file_url":"https://github.com/snaredataset/snare/blob/HEAD/models/single_cls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30b934293080d9a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}