{"id":"W2968104955","doi":"10.1109/cvpr.2019.00675","title":"Streamlined Dense Video Captioning","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Parks and Wilderness Society","funders":"","keywords":"Closed captioning; Computer science; Event (particle physics); Context (archaeology); Dependency (UML); Task (project management); Artificial intelligence; Storytelling; Sequence (biology); Natural language processing; Image (mathematics); Narrative; Linguistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001139236,0.00006365353,0.00006520495,0.00005004354,0.00005995167,0.00008846414,0.0004379412,0.00002639751,0.0002301032],"category_scores_gemma":[0.00003002766,0.00005682588,0.00002848067,0.0001957186,0.000007739642,0.0001918922,0.0001311156,0.00009698366,0.003221887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001993836,"about_ca_system_score_gemma":0.00002482774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000473485,"about_ca_topic_score_gemma":0.00001104481,"domain_scores_codex":[0.9993631,0.000024736,0.0001025213,0.0002517932,0.0001219739,0.0001358585],"domain_scores_gemma":[0.9992315,0.00008986589,0.00003664234,0.000549151,0.00004074727,0.00005209167],"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":[0.000003050367,0.00007791683,0.119528,0.00001104085,0.00001736489,0.000002610351,0.0005393172,0.01295349,0.01307644,0.7853515,0.0009416072,0.06749777],"study_design_scores_gemma":[0.0002846242,0.00003079301,0.1273171,0.000006482419,0.000001952875,0.000009771913,0.00001436133,0.8645836,0.00090239,0.002710887,0.00397612,0.0001618629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4485532,0.00000764057,0.5285959,0.001727882,0.00008513165,0.0001203927,2.420581e-7,0.0003946368,0.02051498],"genre_scores_gemma":[0.8618779,5.109484e-7,0.1354336,0.0002977483,0.00002140912,0.0000106997,0.000001627779,0.000004656339,0.002351843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8516302,"threshold_uncertainty_score":0.9975542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006586964800575043,"score_gpt":0.2454334821047727,"score_spread":0.2388465173041977,"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."}}