{"id":"W2905564365","doi":"10.1609/aaai.v33i01.33018505","title":"DeepCCFV: Camera Constraint-Free Multi-View Convolutional Neural Network for 3D Object Retrieval","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Constraint (computer-aided design); Dropout (neural networks); Computer vision; Point cloud; Object (grammar); Feature (linguistics); Modal; Field (mathematics); Machine learning; Mathematics","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":[0.0004956335,0.001179193,0.001054546,0.000681452,0.0003156947,0.0006878246,0.002624147,0.001401133,0.002303104],"category_scores_gemma":[0.001096087,0.0005842535,0.0008362342,0.0007718928,0.000441871,0.001533632,0.001368214,0.001372135,0.0009797945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232425,"about_ca_system_score_gemma":0.001355288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02332783,"about_ca_topic_score_gemma":0.02902183,"domain_scores_codex":[0.9996653,0.00002916775,0.00001244269,0.0001029894,0.0001187842,0.0000714397],"domain_scores_gemma":[0.999775,0.00004889578,0.00002775636,0.00006506452,0.00006275529,0.00002053273],"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":[0.0002755683,0.0001469651,0.001421252,0.0001945383,0.0001842092,0.0002292449,0.00007315328,0.2313132,0.03844276,0.005019856,0.01511409,0.7075852],"study_design_scores_gemma":[0.00001131963,0.0000419043,0.0003292773,0.000009846731,0.00002073043,0.0001069555,0.000007008864,0.9884504,0.007405308,0.001624505,0.001978134,0.0000145382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.021596,0.001580086,0.9693406,0.0001698703,0.0001168933,0.00007421878,0.0003875121,0.00496827,0.001766465],"genre_scores_gemma":[0.5748498,0.001513872,0.4050269,0.0008666865,0.0001317612,0.0001843913,0.004004465,0.0004724435,0.0129498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02332783,"threshold_uncertainty_score":0.0463841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05343436733982881,"score_gpt":0.2656915329047693,"score_spread":0.2122571655649405,"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."}}