{"id":"W2995439012","doi":"10.1007/978-3-030-58565-5_13","title":"ScanRefer: 3D Object Localization in RGB-D Scans Using Natural Language","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Object (grammar); Computer science; Artificial intelligence; Point cloud; Minimum bounding box; Task (project management); Computer vision; Natural language; Point (geometry); RGB color model; Bounding overwatch; Pattern recognition (psychology); Sentence; Natural language processing; Image (mathematics); Mathematics; Geometry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004911129,0.002120322,0.001279387,0.002250928,0.0006146609,0.001552505,0.00230632,0.001434767,0.03590202],"category_scores_gemma":[0.00198274,0.001025171,0.001455674,0.002011352,0.0007585309,0.002254322,0.003928049,0.0007850448,0.01576053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00050992,"about_ca_system_score_gemma":0.0009028388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005951275,"about_ca_topic_score_gemma":0.01350995,"domain_scores_codex":[0.9992756,0.00008693347,0.00003395282,0.0002173495,0.0003085571,0.00007757378],"domain_scores_gemma":[0.9994825,0.0001397413,0.00003269542,0.0001924988,0.0001157931,0.00003675649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001224476,0.0002335881,0.001759467,0.001252457,0.0002037689,0.0009414098,0.0006726037,0.01035769,0.1450244,0.008242202,0.09240744,0.7376805],"study_design_scores_gemma":[0.0005565146,0.0007248607,0.00829329,0.0003107551,0.0002202813,0.002865895,0.001338533,0.5110391,0.2201676,0.04022578,0.2139008,0.0003566243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01197917,0.0004168267,0.8531488,0.0001953499,0.0001845418,0.0003556912,0.008800361,0.1193433,0.00557613],"genre_scores_gemma":[0.1301532,0.0007297,0.8169141,0.0004564067,0.00009859832,0.0008928526,0.02649827,0.01071806,0.01353869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03590202,"threshold_uncertainty_score":0.1201043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818035576378425,"score_gpt":0.3058155811202975,"score_spread":0.2876352253565133,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}