{"id":"W3106697459","doi":"10.18653/v1/2020.aacl-main.48","title":"Multimodal Pretraining for Dense Video Captioning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Closed captioning; Timeline; Computer science; Leverage (statistics); Variety (cybernetics); Multimedia; Construct (python library); Artificial intelligence; Human–computer interaction; Natural language processing; Image (mathematics)","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":[0.001134099,0.002233889,0.0011191,0.001721854,0.0007745802,0.001216447,0.001773328,0.002160603,0.01996415],"category_scores_gemma":[0.004475249,0.0009216667,0.001102547,0.001498825,0.0006259218,0.002275871,0.001966077,0.00242386,0.01016659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000975673,"about_ca_system_score_gemma":0.001018779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008827565,"about_ca_topic_score_gemma":0.01872846,"domain_scores_codex":[0.9992892,0.0001806871,0.00003155975,0.0002396434,0.0001268906,0.0001320604],"domain_scores_gemma":[0.9986402,0.0005464065,0.00005688603,0.000248154,0.0004262772,0.00008204098],"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":[0.0005320791,0.0002328751,0.0005369796,0.0003269749,0.0001150193,0.0002004234,0.0001199496,0.05287604,0.02940219,0.004235663,0.07843085,0.8329909],"study_design_scores_gemma":[0.00004615558,0.0001595267,0.0009985931,0.00008406571,0.00006148572,0.0001463487,0.00009172151,0.9516342,0.02381822,0.008850602,0.01407283,0.0000361296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02166558,0.003230365,0.9353442,0.0007079695,0.0008449496,0.0002972557,0.003099591,0.02236307,0.01244702],"genre_scores_gemma":[0.3486871,0.002124134,0.5935608,0.000994274,0.0009834132,0.0008242443,0.02265137,0.002533858,0.02764082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01996415,"threshold_uncertainty_score":0.06678677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04438772172069969,"score_gpt":0.3200176612216676,"score_spread":0.2756299395009679,"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."}}