{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004317343,0.0002295274,0.0001962174,0.0002556982,0.0002220551,0.0005262686,0.0006775793,0.0000804306,0.0001060987],"category_scores_gemma":[0.00008190128,0.0001819375,0.00005839759,0.0009189211,0.00004779414,0.0007753054,0.0002067285,0.000794669,0.000444906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001131424,"about_ca_system_score_gemma":0.0001404993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143375,"about_ca_topic_score_gemma":0.00104725,"domain_scores_codex":[0.9981604,0.00008358784,0.0003166626,0.0007022942,0.0003177637,0.0004192975],"domain_scores_gemma":[0.9990116,0.0002556252,0.00006146919,0.0004873381,0.0000611205,0.0001228596],"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":[0.00001787461,0.000141979,0.222899,0.00012673,0.00006969966,0.0001997453,0.02438021,0.03446629,0.002591099,0.08443977,0.0003133744,0.6303543],"study_design_scores_gemma":[0.0003153892,0.0001062117,0.03669563,0.0001279988,0.000003064335,0.00005697879,0.0004790351,0.9589215,0.0003862333,0.0003008173,0.002292064,0.0003151124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4274574,0.0001950739,0.5568953,0.002721435,0.0001604674,0.0003584863,5.771464e-7,0.001377543,0.0108337],"genre_scores_gemma":[0.9541733,0.000002485855,0.04416027,0.0002298606,0.00007715524,0.0001054302,0.000003911033,0.00003075846,0.001216785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9244552,"threshold_uncertainty_score":0.7419198,"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."}}