{"id":"W4387969760","doi":"10.1145/3581783.3612863","title":"Deep Video Understanding with Video-Language Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Process (computing); Artificial intelligence; Selection (genetic algorithm); Matching (statistics); Modal; Graph; Dual (grammatical number); Multimedia; Machine learning; Human–computer interaction; Natural language processing; Theoretical computer science; 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":[0.0001920451,0.0001067427,0.00009241733,0.000150073,0.0001847904,0.0001405878,0.0005962066,0.00003246382,0.00002591051],"category_scores_gemma":[0.00002854368,0.00008445275,0.00002824314,0.0008648836,0.00002971499,0.0002517453,0.0002061882,0.0001393372,0.0004329352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007802131,"about_ca_system_score_gemma":0.00003880589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002184631,"about_ca_topic_score_gemma":0.00009582222,"domain_scores_codex":[0.9989976,0.00002442469,0.0001124524,0.0003585916,0.0002406746,0.0002662008],"domain_scores_gemma":[0.9991187,0.0001243315,0.00004022647,0.0006033135,0.00002190481,0.00009151128],"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":[0.000003330664,0.00002028715,0.001018318,0.00000953229,0.00001455625,0.00001318159,0.002715692,0.3742514,0.001177662,0.6153219,0.0008590276,0.004595075],"study_design_scores_gemma":[0.0001769982,0.00001801457,0.001307299,0.000006418519,0.000002737498,0.000005384144,0.0002472464,0.9881188,0.0001238801,0.009816114,0.00004668882,0.0001304424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01341822,0.000007657529,0.9636896,0.00322458,0.00002391288,0.0001325048,4.846032e-7,0.001360908,0.01814216],"genre_scores_gemma":[0.8627461,0.000001670259,0.1358302,0.0003460958,0.00001678187,0.00003363221,0.000003620261,0.00001338816,0.001008546],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493279,"threshold_uncertainty_score":0.556465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519577788868931,"score_gpt":0.2896068538903968,"score_spread":0.2544110760017075,"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."}}