{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034218,0.001810727,0.0006592815,0.0009175739,0.0003116945,0.0006425927,0.003125562,0.002093901,0.009358732],"category_scores_gemma":[0.004443407,0.000543414,0.0009685344,0.0007211441,0.0004514565,0.002229864,0.001431358,0.00204746,0.003482118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008919911,"about_ca_system_score_gemma":0.0008858881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008829944,"about_ca_topic_score_gemma":0.01214432,"domain_scores_codex":[0.999474,0.0001098604,0.00002773793,0.0002581083,0.00007515154,0.00005515756],"domain_scores_gemma":[0.9987314,0.0006753813,0.00006996153,0.0002024282,0.0002560075,0.00006480313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005485996,0.0007270277,0.001882584,0.0003451631,0.00013426,0.0002313284,0.0002907655,0.06280142,0.04353371,0.002355225,0.02681316,0.8603369],"study_design_scores_gemma":[0.00006486184,0.0002131091,0.0008146496,0.00001952847,0.0000402605,0.00008923499,0.0001245681,0.9577263,0.032214,0.00260594,0.006062259,0.00002532982],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05245527,0.0005138357,0.8837852,0.0003346389,0.0002475095,0.0005493059,0.001507862,0.05582072,0.004785618],"genre_scores_gemma":[0.2920625,0.0003013067,0.6847343,0.0008578394,0.0001391908,0.0008496786,0.008260912,0.001323786,0.01147054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009358732,"threshold_uncertainty_score":0.03130805,"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."}}