{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004923487,0.0002323478,0.0002359527,0.0001562491,0.0001719834,0.00008811591,0.0005187702,0.0001330523,0.00000108695],"category_scores_gemma":[0.0005884777,0.0002001273,0.0002340005,0.0003477364,0.0001619079,0.00120757,0.00009703996,0.0002466332,8.879177e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001437278,"about_ca_system_score_gemma":0.00001913472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004374726,"about_ca_topic_score_gemma":4.639458e-8,"domain_scores_codex":[0.9983586,2.796974e-8,0.0004040271,0.0004395118,0.0005477304,0.0002500806],"domain_scores_gemma":[0.998486,0.00008687609,0.0002928813,0.00006645574,0.0009935884,0.00007412993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006930099,0.00009627563,0.0001820305,0.0001865101,0.00005689354,1.259428e-7,0.0001854388,0.0003550603,0.9111995,0.07906818,0.0003273321,0.008273398],"study_design_scores_gemma":[0.0004050775,0.000426144,0.001599487,0.0001804364,0.00002840934,0.00003143572,0.0001398196,0.1274429,0.8670428,0.001998538,0.0004681537,0.0002367695],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8849235,0.00005191311,0.1129174,0.0009557579,0.0001510828,0.0004532833,0.000004485166,0.0002046259,0.0003378885],"genre_scores_gemma":[0.6630307,0.0001086638,0.3364634,0.00005997086,0.0001713965,0.00008085287,0.000002257125,0.00002402338,0.00005874429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.223546,"threshold_uncertainty_score":0.8160954,"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."}}