{"id":"W4402754275","doi":"10.1109/cvpr52733.2024.00131","title":"SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Landmark; Autoencoder; Artificial intelligence; Computer science; Pattern recognition (psychology); Estimation; Computer vision; Artificial neural network; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002958962,0.0001773518,0.0001583064,0.00009218467,0.0001636935,0.0004159396,0.000325682,0.00004550883,0.00007980788],"category_scores_gemma":[0.00003180662,0.0001252202,0.0000575039,0.0004937403,0.00002462118,0.0007615459,0.00006645294,0.00008166342,0.00006792414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008992727,"about_ca_system_score_gemma":0.0001778184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001991091,"about_ca_topic_score_gemma":0.000019634,"domain_scores_codex":[0.9987083,0.00006490199,0.0001728888,0.00051843,0.0002446261,0.0002908516],"domain_scores_gemma":[0.9991879,0.0002735618,0.00003460121,0.0002687373,0.0001637253,0.0000714146],"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":[0.0005899197,0.0006265164,0.0002238388,0.00050111,0.001029718,0.0000917437,0.01216874,0.1627897,0.01969504,0.08961406,0.108565,0.6041046],"study_design_scores_gemma":[0.0002849537,0.0002788644,0.0000909525,0.00006000041,0.0000255689,0.000006778776,0.00002480998,0.9792274,0.01553073,0.001077049,0.003192661,0.0002002001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006905646,0.0001198956,0.9943532,0.001002219,0.0004182828,0.0005465659,0.000002946517,0.0003645202,0.002501829],"genre_scores_gemma":[0.3838428,0.000009558652,0.6132753,0.000208136,0.00007885655,0.0001320798,0.000005222831,0.00001127233,0.002436831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8164377,"threshold_uncertainty_score":0.5106332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008781674077387029,"score_gpt":0.2391022957727829,"score_spread":0.2303206216953958,"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."}}