{"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":"/paper/rel3d-a-minimally-contrastive-benchmark-for-1","title":"Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D","arxiv_id":"2012.01634","date":"2020-12-03","proceeding":"NeurIPS 2020 12","authors":["Ankit Goyal","Kaiyu Yang","Dawei Yang","Jia Deng"],"abstract":"Understanding spatial relations (e.g., \"laptop on table\") in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, which is critical for learning spatial relations. In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. Rel3D enables quantifying the effectiveness of 3D information in predicting spatial relations on large-scale human data. Moreover, we propose minimally contrastive data collection -- a novel crowdsourcing method for reducing dataset bias. The 3D scenes in our dataset come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other. We empirically validate that minimally contrastive examples can diagnose issues with current relation detection models as well as lead to sample-efficient training. Code and data are available at https://github.com/princeton-vl/Rel3D.","url_abs":"https://arxiv.org/abs/2012.01634v1","url_pdf":"https://arxiv.org/pdf/2012.01634v1.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":"rel3d-a-minimally-contrastive-benchmark-for-1","repo_url":"https://github.com/princeton-vl/Rel3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rel3d-a-minimally-contrastive-benchmark-for-1","repo_url":"https://github.com/princeton-vl/SpatialSense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"spatial-relation-recognition","task_name":"Spatial Relation Recognition"}],"methods":[],"datasets_introduced":[{"slug":"rel3d","name":"Rel3D","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"Human","rank_in_archive_order":1,"of":9,"metrics":{"Acc":"94.25"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"MLP-Aligned Features","rank_in_archive_order":2,"of":9,"metrics":{"Acc":"85.03"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"MLP-Raw Features","rank_in_archive_order":3,"of":9,"metrics":{"Acc":"81.24"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"BBox Only","rank_in_archive_order":4,"of":9,"metrics":{"Acc":"74.14"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"PPR-FCN","rank_in_archive_order":5,"of":9,"metrics":{"Acc":"73.3"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"DRNet","rank_in_archive_order":6,"of":9,"metrics":{"Acc":"73.25"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"VipCNN","rank_in_archive_order":7,"of":9,"metrics":{"Acc":"72.32"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"VTransE","rank_in_archive_order":8,"of":9,"metrics":{"Acc":"72.27"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-relation-recognition-on-rel3d","task":"Spatial Relation Recognition","dataset":"Rel3D","model":"Random","rank_in_archive_order":9,"of":9,"metrics":{"Acc":"50"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.01634","atlas_url":"https://app.syntology.ai/?focus=2012.01634","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.01634"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.01634\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.01634"},"call":"get_concepts_for_paper(arxiv_id=\"2012.01634\")"}],"by_repo":[{"repo":"princeton-vl/Rel3D","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"princeton-vl/SpatialSense","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1908.02660"],"harvested_for_calls":[{"arxiv_id":"1908.02660","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1908.02660"},"call":"get_harvested_code_for_paper(arxiv_id=\"1908.02660\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51b289d4eea0c1b43bd88b38ba0e0452163c231ad9eb2a54c21423f3f8326754","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}