{"id":"W3203518786","doi":"10.1109/iccv48922.2021.00615","title":"COTR: Correspondence Transformer for Matching Across Images","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":272,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Prior probability; Inference; Transformer; Pattern recognition (psychology); Zoom; Computer vision; Data mining; Bayesian probability","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004428124,0.0003999787,0.0003959241,0.0001839291,0.0003838672,0.001305044,0.001757522,0.000112561,0.0006278998],"category_scores_gemma":[0.00006510532,0.000384104,0.0002886701,0.0003788909,0.00008399928,0.001524042,0.0003424228,0.0004147622,0.0003644458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001523926,"about_ca_system_score_gemma":0.0002449107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195827,"about_ca_topic_score_gemma":0.00001261065,"domain_scores_codex":[0.9965396,0.0001236219,0.0006319392,0.001189906,0.0009166608,0.000598252],"domain_scores_gemma":[0.9972584,0.000424013,0.0002166924,0.000722083,0.001154192,0.0002246459],"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":[0.0002019193,0.0004389347,0.00005810282,0.00004375719,0.00009626257,0.0002408332,0.001562081,0.001850481,0.08236258,0.08963184,0.01908134,0.8044319],"study_design_scores_gemma":[0.002078005,0.0004064129,0.0006691961,0.0006632449,0.000009725824,0.0001915822,0.0002680803,0.8696624,0.05711,0.01799062,0.05007785,0.0008729121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004485291,0.0000639124,0.9774745,0.008831725,0.005438321,0.0002693469,0.00008988761,0.0001648717,0.003182183],"genre_scores_gemma":[0.5715491,0.0003199911,0.4101698,0.006599493,0.0009715425,0.00008677212,0.0001191542,0.00006212236,0.01012209],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8678119,"threshold_uncertainty_score":0.9998611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03936874785590629,"score_gpt":0.3716827517917868,"score_spread":0.3323140039358806,"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."}}