{"id":"W1998959036","doi":"10.5244/c.28.46","title":"Unlabelled 3D Motion Examples Improve Cross-View Action Recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Hallucinating; Feature (linguistics); Artificial intelligence; Transformation (genetics); Motion (physics); Viewpoints; Pattern recognition (psychology); Action (physics); Action recognition; Feature learning; Computer vision; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004234766,0.0001412504,0.0001346184,0.0001307105,0.0002610532,0.0003551239,0.000219076,0.0000976566,0.000562917],"category_scores_gemma":[0.00006774805,0.0001297159,0.00006999804,0.0002241438,0.00002866443,0.001417254,0.00006137184,0.0001272671,0.001765115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004585369,"about_ca_system_score_gemma":0.00001742612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005309979,"about_ca_topic_score_gemma":0.00003236955,"domain_scores_codex":[0.9987547,0.0001195575,0.0002723962,0.0004129117,0.0002151975,0.0002252668],"domain_scores_gemma":[0.9991844,0.00008536178,0.000133602,0.0003214352,0.0001919411,0.00008329805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004975777,0.00006240844,0.00006122079,0.00002503426,0.00000837582,4.633416e-7,0.0000546353,0.000006505948,0.006087991,0.00381283,0.0003362012,0.9895394],"study_design_scores_gemma":[0.005030046,0.001024513,0.01816609,0.0002066625,0.00008648526,0.0001034867,0.0001021397,0.2824031,0.3552264,0.1741564,0.1614675,0.002027267],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1190216,0.00001567138,0.8603241,0.0002371017,0.0009470189,0.0002073548,0.000002554518,0.0005277822,0.01871679],"genre_scores_gemma":[0.9707565,0.00008449797,0.02483689,0.001008899,0.0004708445,0.00005441572,0.00007250853,0.00001668621,0.002698759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9875121,"threshold_uncertainty_score":0.9990121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05302742208085452,"score_gpt":0.2913688229776417,"score_spread":0.2383414008967872,"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."}}