{"id":"W3176425931","doi":"10.1609/aaai.v35i3.16353","title":"Semantic Grouping Network for Video Captioning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Interpretability; Closed captioning; Margin (machine learning); Word (group theory); Redundancy (engineering); Phrase; Artificial intelligence; Natural language processing; Speech recognition; Image (mathematics); Machine learning","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":[0.0005272002,0.0001714128,0.0002208156,0.00005674926,0.0004268131,0.0003203001,0.001383534,0.00006003985,0.00002882635],"category_scores_gemma":[0.000799697,0.0001471762,0.0001383776,0.0007704102,0.0001098653,0.0002679992,0.0003746224,0.0002748625,0.00005053754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003957254,"about_ca_system_score_gemma":0.0001167643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007888712,"about_ca_topic_score_gemma":0.00001915699,"domain_scores_codex":[0.9983254,0.00001965627,0.0004549139,0.0005324559,0.0003056232,0.0003619149],"domain_scores_gemma":[0.9981371,0.0002416546,0.0003456316,0.000360653,0.0008440656,0.00007086856],"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":[0.000009515898,0.00005393675,0.000608468,0.00003891681,0.00001207639,2.253762e-7,0.0004266479,0.001670928,0.02226585,0.9482062,0.0001172778,0.02658995],"study_design_scores_gemma":[0.00002904377,0.00006025186,0.001198987,0.0002655203,0.00001541216,0.000009451949,0.000175054,0.5208595,0.1272972,0.3495454,0.0003327804,0.0002113836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1138726,0.00005744657,0.8662571,0.01183012,0.0006104794,0.0006800652,0.0000041546,0.0002191642,0.0064689],"genre_scores_gemma":[0.9385877,0.000008178519,0.06062012,0.0004062097,0.0001445403,0.00008765005,0.000001003471,0.00001337016,0.0001312894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8247151,"threshold_uncertainty_score":0.6001673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06834906582068068,"score_gpt":0.3139618964753935,"score_spread":0.2456128306547128,"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."}}