{"id":"W4390873348","doi":"10.1109/iccv51070.2023.02150","title":"One-shot recognition of any material anywhere using contrastive learning with physics-based rendering","year":2023,"lang":"en","type":"article","venue":"","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Rendering (computer graphics); Artificial intelligence; Computer graphics (images)","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":[0.0004873991,0.001828502,0.00126752,0.001676034,0.0004075881,0.001687885,0.002246018,0.001320774,0.00465228],"category_scores_gemma":[0.001451684,0.0006205604,0.002188085,0.0008907838,0.0007038825,0.00186209,0.001406244,0.002137741,0.002878095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011786,"about_ca_system_score_gemma":0.0008879679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009123431,"about_ca_topic_score_gemma":0.01651117,"domain_scores_codex":[0.9994845,0.00003746709,0.00001883609,0.000235767,0.0001418515,0.00008143469],"domain_scores_gemma":[0.9995874,0.00008856527,0.00002894317,0.0001440147,0.00009535198,0.00005580311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007297239,0.0006516342,0.00303954,0.0004421819,0.0002133862,0.000386197,0.0001156244,0.1513704,0.08207785,0.003166836,0.02779473,0.7300119],"study_design_scores_gemma":[0.00002653329,0.0001435775,0.001113573,0.0000213521,0.00002566579,0.0001763598,0.00005043814,0.9715292,0.02043217,0.003015272,0.003436962,0.00002880991],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1612436,0.002302846,0.7765759,0.0006811468,0.0007796602,0.0005627704,0.005054292,0.0368938,0.01590595],"genre_scores_gemma":[0.5327165,0.0009904623,0.4366947,0.0008662461,0.0001855424,0.0002500195,0.01491376,0.001417227,0.01196547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009123431,"threshold_uncertainty_score":0.01814067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1080466910034163,"score_gpt":0.3164128650952332,"score_spread":0.2083661740918169,"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."}}