{"id":"W3193285831","doi":"10.1016/j.cad.2021.103105","title":"Multi-Task Joint Learning of 3D Keypoint Saliency and Correspondence Estimation","year":2021,"lang":"en","type":"article","venue":"Computer-Aided Design","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Natural Science Foundation of China; National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization; Shandong University","keywords":"Computer science; Artificial intelligence; Point cloud; Pose; Pattern recognition (psychology); Cluster analysis; Offset (computer science); Computer vision","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":[0.0002505648,0.0001291119,0.0002432719,0.0001068136,0.00005369424,0.00004493076,0.00007016359,0.00005509134,0.00002027651],"category_scores_gemma":[0.00008282343,0.0001366963,0.00005227943,0.0002139962,0.00002679677,0.00009344277,0.00004789221,0.000145961,0.00002209353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002513695,"about_ca_system_score_gemma":0.00002766854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007021982,"about_ca_topic_score_gemma":6.273667e-7,"domain_scores_codex":[0.9991155,0.0001010024,0.0002880713,0.0002083046,0.0001336457,0.0001535139],"domain_scores_gemma":[0.999498,0.0001244348,0.00005151843,0.0001752031,0.00009056874,0.00006033637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002404359,0.00002303069,0.00007111685,0.00007861097,0.00002549175,0.00001595599,0.0004314648,0.9473678,0.01803947,0.00001181741,0.00008600251,0.03384681],"study_design_scores_gemma":[0.0002268938,0.0000400364,0.0005589246,0.0001045959,0.00003176,0.00001903712,0.00002955948,0.989788,0.008943557,0.0001000477,0.00001760101,0.0001399761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06730413,0.0008719384,0.9314392,0.00001693887,0.0001257974,0.00004937242,0.000001025351,0.0001574223,0.00003413927],"genre_scores_gemma":[0.6654548,0.00006084712,0.3343558,0.00001254202,0.00002246694,0.000002196452,0.000005355778,0.00001352728,0.00007247709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5981507,"threshold_uncertainty_score":0.5574312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03236641652319404,"score_gpt":0.2303861775850386,"score_spread":0.1980197610618445,"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."}}