{"id":"W4405812114","doi":"10.1109/tpami.2024.3522295","title":"A Review of Deep Learning for Video Captioning","year":2024,"lang":"en","type":"review","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Deep learning; Computer vision; Natural language processing; Multimedia; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006653375,0.0004872657,0.001692219,0.001039901,0.0002172915,0.0001345062,0.0008147939,0.0001303602,0.00007597768],"category_scores_gemma":[0.00003637861,0.0003910889,0.001515291,0.002343209,0.00006067754,0.0001157968,0.00001612163,0.0008875323,0.00006479816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006769127,"about_ca_system_score_gemma":0.00006072378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007138774,"about_ca_topic_score_gemma":0.0001611078,"domain_scores_codex":[0.9971661,0.0002344469,0.001105897,0.0009595639,0.0002668033,0.0002671745],"domain_scores_gemma":[0.9977887,0.0006141767,0.0005429373,0.0007850009,0.0001450654,0.0001240781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.24774e-7,0.00004553243,0.000001300611,0.03436388,0.001018437,0.000001363947,0.00005878559,0.002241147,3.382181e-7,0.0001350038,0.000006283924,0.9621273],"study_design_scores_gemma":[0.00007903553,0.0002581388,0.000003891547,0.07554998,0.02913198,0.00007194918,0.00001232147,0.5772578,0.0001093212,0.0002486154,0.3160797,0.001197212],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[4.990513e-8,0.4930765,0.5063075,0.00006086365,0.00007409517,0.0003588404,0.00002993249,0.00007456989,0.00001758682],"genre_scores_gemma":[0.003206652,0.9910859,0.004742466,0.0002059327,0.00002818963,0.0005437435,0.00004155385,0.00004345603,0.0001021145],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9609301,"threshold_uncertainty_score":0.9998541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03868040932106809,"score_gpt":0.3533350145359122,"score_spread":0.3146546052148441,"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."}}