{"id":"W2770305773","doi":"10.1145/3130800.3130811","title":"Learning to predict part mobility from a single static snapshot","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Carleton University","funders":"Science and Technology Planning Project of Guangdong Province; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Snapshot (computer storage); Computer science; Artificial intelligence; Motion (physics); Computer vision; Object (grammar)","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":[0.000204876,0.0001439095,0.0001439854,0.0001633976,0.001162259,0.0004353898,0.0009151047,0.00007979941,0.0002577098],"category_scores_gemma":[0.0001283846,0.0001477586,0.0001156,0.0001796105,0.00007039296,0.000689189,0.00002265454,0.000363811,0.0001241237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003238398,"about_ca_system_score_gemma":0.00003383807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001336953,"about_ca_topic_score_gemma":0.000234735,"domain_scores_codex":[0.9987554,0.00008102032,0.0002156144,0.000436359,0.0002798887,0.0002317078],"domain_scores_gemma":[0.998081,0.0001980586,0.0001065724,0.001360993,0.00009212714,0.000161295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001481283,0.00305021,0.003261673,0.00006666837,0.000388159,0.0000517474,0.006904942,0.004925234,0.005015287,0.001603613,0.003129625,0.9714547],"study_design_scores_gemma":[0.007226318,0.008881012,0.1739296,0.001313964,0.0005921021,0.00005922228,0.001862855,0.135989,0.1208377,0.3174331,0.227228,0.004647124],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3278942,0.000006219484,0.6678049,0.002361711,0.0006842591,0.0002222579,0.00004148151,0.0002206547,0.000764271],"genre_scores_gemma":[0.9907916,0.00003128915,0.008226974,0.0006652434,0.0000597059,0.00005697785,0.00001765813,0.00001084845,0.0001397576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9668076,"threshold_uncertainty_score":0.8939271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04716985089233217,"score_gpt":0.2761866867057783,"score_spread":0.2290168358134462,"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."}}