{"id":"W4380990286","doi":"10.1007/s11042-023-15565-w","title":"AutoTag: automated metadata tagging for film post-production","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tamkeen; Swiss Re; York University; New York University Abu Dhabi; National Science Foundation","keywords":"Computer science; Metadata; Shot (pellet); Task (project management); Production (economics); Process (computing); Information retrieval; Multimedia; Human–computer interaction; Artificial intelligence; World Wide Web; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002505056,0.00133405,0.000719243,0.005208765,0.001281344,0.002545914,0.001612301,0.001123319,0.01151717],"category_scores_gemma":[0.00871374,0.0006340678,0.0006125672,0.002655359,0.0006128796,0.003859743,0.002930625,0.001031682,0.0129018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008784839,"about_ca_system_score_gemma":0.001036369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005126119,"about_ca_topic_score_gemma":0.007105052,"domain_scores_codex":[0.9980106,0.0004723445,0.0002111082,0.0004614243,0.0006912407,0.0001534366],"domain_scores_gemma":[0.9911579,0.002560677,0.0006954429,0.002621156,0.002593811,0.0003708419],"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":[0.0007680717,0.0002971608,0.005368928,0.0008300891,0.00008800189,0.0007298142,0.002018482,0.002596414,0.09204414,0.0038964,0.1016854,0.7896772],"study_design_scores_gemma":[0.0002589611,0.0006971195,0.02001885,0.0004020625,0.000181161,0.001401855,0.003950641,0.2583362,0.3685695,0.01637785,0.329412,0.0003936728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03980075,0.0006655071,0.6594859,0.0005292963,0.0005947946,0.00103676,0.01207567,0.2762415,0.009569854],"genre_scores_gemma":[0.1620734,0.0003927143,0.771299,0.0002728495,0.0002599807,0.0006229479,0.03846819,0.009330079,0.01728086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01151717,"threshold_uncertainty_score":0.03852874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03347354137478025,"score_gpt":0.2864682672559888,"score_spread":0.2529947258812086,"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."}}