{"id":"W4390873290","doi":"10.1109/iccv51070.2023.01282","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"HORIZON EUROPE Health; Tsinghua Shenzhen International Graduate School; National Natural Science Foundation of China","keywords":"Computer science; Adapter (computing); Leverage (statistics); Transformer; Artificial intelligence; Natural language processing; Event (particle physics); Semantics (computer science); Feature learning; Task (project management); Speech recognition; Programming language","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":[0.0008012564,0.0001253539,0.0001190055,0.0001509444,0.0002634525,0.0002129462,0.0005938376,0.00004615666,0.00002822672],"category_scores_gemma":[0.0003624546,0.0001202458,0.00006633212,0.0005753289,0.00002651004,0.0004606992,0.0001908913,0.0001492223,0.0004116369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003245018,"about_ca_system_score_gemma":0.0000399034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000277136,"about_ca_topic_score_gemma":0.00001675272,"domain_scores_codex":[0.9987202,0.00005702877,0.0002284665,0.000461253,0.0001981547,0.0003349388],"domain_scores_gemma":[0.9987794,0.0004372892,0.00008777653,0.000501411,0.0001116163,0.00008253466],"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":[0.0000109368,0.00005976713,0.003186003,0.00006641473,0.00003252289,0.000005976389,0.002518555,0.006886462,0.02260879,0.4637499,0.009284813,0.4915899],"study_design_scores_gemma":[0.0002086591,0.0000457122,0.009347602,0.00002126481,0.00000360849,0.00000479526,0.00006575998,0.9783,0.0006308981,0.003647129,0.00755985,0.0001646993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01869597,0.000009736284,0.968509,0.004136206,0.0001665441,0.0003902173,0.000002715322,0.001701703,0.006387883],"genre_scores_gemma":[0.587,0.000001011837,0.4116172,0.0002379232,0.00009520441,0.0001609826,0.000008564337,0.00001559987,0.0008634885],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714136,"threshold_uncertainty_score":0.5290896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0256250179558844,"score_gpt":0.319102130015953,"score_spread":0.2934771120600686,"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."}}