{"id":"W1993238398","doi":"10.1117/12.766841","title":"Designing caption production rules based on face, text, and motion detection","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Computer vision; Optical flow; Classifier (UML); Motion (physics); Production line; Speech recognition; Image (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":[0.001701469,0.00161336,0.00111933,0.001831744,0.0007285266,0.001622334,0.001707563,0.001047967,0.004495564],"category_scores_gemma":[0.009307964,0.0006208399,0.0006799016,0.0006537436,0.0005925179,0.001250288,0.0005416979,0.0008110176,0.003110359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005587081,"about_ca_system_score_gemma":0.0007157449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00314975,"about_ca_topic_score_gemma":0.003871439,"domain_scores_codex":[0.9990829,0.0001901095,0.0001111754,0.0002743873,0.000271271,0.00007009383],"domain_scores_gemma":[0.9944476,0.002218266,0.0003738329,0.0004244639,0.002356703,0.0001792019],"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":[0.0007167619,0.0004067131,0.005064867,0.0007507783,0.0001217371,0.001003739,0.0008529525,0.02675931,0.1502079,0.00213841,0.01426192,0.797715],"study_design_scores_gemma":[0.00007780223,0.0003964833,0.007518049,0.0001155819,0.0002039668,0.001107529,0.0004834946,0.7306392,0.2360426,0.002583195,0.02070295,0.0001291612],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04901896,0.0003030532,0.924278,0.0001079516,0.000130711,0.001064105,0.0004348002,0.01864424,0.006018218],"genre_scores_gemma":[0.1872585,0.0003189984,0.8054844,0.0001061273,0.00006293898,0.0006959125,0.001491312,0.0009855742,0.003596287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004495564,"threshold_uncertainty_score":0.01503915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01506345324739933,"score_gpt":0.2333204339744658,"score_spread":0.2182569807270664,"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."}}