{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001121897,0.001958558,0.001000283,0.002376531,0.0006940772,0.000765211,0.00191944,0.001654853,0.004047051],"category_scores_gemma":[0.003361014,0.0004003341,0.000961724,0.002086348,0.0007031387,0.002439293,0.00119342,0.001284818,0.001578483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001544623,"about_ca_system_score_gemma":0.0007665287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006617524,"about_ca_topic_score_gemma":0.006104105,"domain_scores_codex":[0.9993431,0.0001833009,0.00003164765,0.0002179059,0.0001409278,0.00008310292],"domain_scores_gemma":[0.9992931,0.0002443895,0.00009670693,0.0001135746,0.0001968001,0.00005538766],"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":[0.0007675423,0.0002528631,0.001528351,0.0003721284,0.0001311074,0.0003899258,0.0003210711,0.2122558,0.0243815,0.009351962,0.01816092,0.7320869],"study_design_scores_gemma":[0.00001970563,0.0001406319,0.00052651,0.00003374656,0.00006076972,0.0001245733,0.00008453285,0.9708188,0.01065936,0.01062937,0.006874202,0.0000279488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0480603,0.002906495,0.9294325,0.0006551074,0.0003993935,0.0003880754,0.001331578,0.007967032,0.008859577],"genre_scores_gemma":[0.5720103,0.001760056,0.405378,0.0005890199,0.0003995185,0.0004551654,0.006051729,0.0004967193,0.01285944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006617524,"threshold_uncertainty_score":0.01353878,"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."}}