{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004355062,0.001284775,0.0005635819,0.0007884371,0.00026121,0.0009166669,0.001629865,0.001227428,0.002928798],"category_scores_gemma":[0.001891561,0.0003182816,0.001061662,0.0006924612,0.0003164511,0.00227921,0.0009170928,0.001973986,0.001572717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001020611,"about_ca_system_score_gemma":0.0008627241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01443951,"about_ca_topic_score_gemma":0.01726297,"domain_scores_codex":[0.9996868,0.00005315152,0.00001265989,0.0001542683,0.00005032535,0.0000428848],"domain_scores_gemma":[0.9996196,0.0001581996,0.00003894057,0.00007154021,0.00008422537,0.00002739341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002070149,0.0002992256,0.00139878,0.0001955983,0.0001629342,0.0002585024,0.0001964414,0.349184,0.02328329,0.009696514,0.01783406,0.5972836],"study_design_scores_gemma":[0.00000583078,0.00003178403,0.0001288978,0.000007346831,0.00001275016,0.00002661842,0.00002629045,0.9907174,0.002984663,0.004892698,0.001159631,0.000006140433],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03715958,0.0009220447,0.9449278,0.0006040392,0.0001050916,0.000135801,0.001149381,0.01186742,0.00312869],"genre_scores_gemma":[0.6587274,0.0006525003,0.3229084,0.0007566627,0.0001129141,0.0002580042,0.006394503,0.0005194838,0.009670133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01443951,"threshold_uncertainty_score":0.02871096,"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."}}