{"id":"W2766520430","doi":"10.1145/3123266.3123327","title":"Catching the Temporal Regions-of-Interest for Video Captioning","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Closed captioning; Computer science; Focus (optics); Representation (politics); Frame (networking); Artificial intelligence; Region of interest; Image (mathematics); Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003744293,0.0000656692,0.00008046762,0.00002802435,0.0009009818,0.0002600389,0.001615726,0.00002022406,0.000004360403],"category_scores_gemma":[0.0002856451,0.0000442639,0.00006180679,0.00003776593,0.00007204304,0.0002648079,0.0002771536,0.0001071551,0.00001601034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001246815,"about_ca_system_score_gemma":0.00003592113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003708315,"about_ca_topic_score_gemma":0.0003734181,"domain_scores_codex":[0.9994282,0.0000255641,0.0001535565,0.0001994646,0.00006780204,0.000125404],"domain_scores_gemma":[0.9982496,0.0002276908,0.0002219286,0.001197805,0.00006975943,0.0000332247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002219208,0.0000186323,0.01357456,0.000008156625,0.000009831423,2.933557e-7,0.0004610635,0.0003034215,0.0005751383,0.9693827,0.0009176383,0.01474637],"study_design_scores_gemma":[0.0004952208,0.00006078444,0.1360507,0.00005463753,0.00001200019,0.00001844004,0.0001048496,0.7720634,0.001491864,0.07114102,0.01826028,0.0002468245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06062602,0.00001040651,0.9189081,0.01705117,0.000119237,0.0002278382,0.000001036679,0.00008518566,0.002971032],"genre_scores_gemma":[0.8784928,4.508827e-7,0.1208906,0.0001579074,0.00005252926,0.00005498311,0.000001025634,0.000005333683,0.0003444495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8982416,"threshold_uncertainty_score":0.6929714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1113495865189584,"score_gpt":0.3552552529180734,"score_spread":0.243905666399115,"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."}}