{"id":"W4402703105","doi":"10.1109/cvpr52733.2024.01295","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Artificial intelligence; Human–computer interaction; Multimedia; History; Archaeology","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":[0.0009369169,0.001350332,0.0005547514,0.0004777964,0.000298094,0.0008153699,0.002248556,0.001156528,0.01245899],"category_scores_gemma":[0.004605961,0.0003342295,0.0005883104,0.0002218401,0.0003373708,0.001872816,0.002018095,0.00104559,0.003539302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000354829,"about_ca_system_score_gemma":0.0003953239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00107272,"about_ca_topic_score_gemma":0.002000976,"domain_scores_codex":[0.9994847,0.000156334,0.00002678109,0.0002021875,0.00009114228,0.0000388778],"domain_scores_gemma":[0.9993371,0.0002934913,0.00003748629,0.0001742604,0.00009351685,0.00006406066],"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":[0.001035902,0.0005313728,0.002400985,0.001240038,0.0001945323,0.001095838,0.0009905261,0.02548042,0.06610407,0.004396525,0.05443955,0.8420902],"study_design_scores_gemma":[0.0002533816,0.001067141,0.00227761,0.0001525967,0.0001451442,0.001407754,0.000592152,0.8216229,0.09423789,0.008880176,0.06924021,0.0001230678],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06899493,0.001552119,0.8139687,0.0004782763,0.0005334139,0.001124652,0.003565446,0.0984881,0.01129428],"genre_scores_gemma":[0.2872095,0.0004072051,0.6914251,0.0006113468,0.0001245662,0.0007957953,0.006857214,0.00130158,0.01126782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01245899,"threshold_uncertainty_score":0.04167944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008162838442675452,"score_gpt":0.2595758568692203,"score_spread":0.2514130184265448,"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."}}