{"id":"W4400338820","doi":"10.1016/j.cviu.2024.104064","title":"Implicit and explicit commonsense for multi-sentence video captioning","year":2024,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"Alliance de recherche numérique du Canada; Vector Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Closed captioning; Computer science; Commonsense knowledge; Sentence; Paragraph; Natural language processing; Artificial intelligence; Task (project management); Object (grammar); Isolation (microbiology); Commonsense reasoning; Knowledge base; Transformer; Image (mathematics); World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003236919,0.0001860029,0.0001761113,0.0002068204,0.0004883666,0.001268006,0.0002456483,0.00005219496,0.000002890101],"category_scores_gemma":[0.00002703727,0.0001681552,0.0000566351,0.000241268,0.00007767029,0.0005925259,0.0003761018,0.0001882102,0.00000991445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008752615,"about_ca_system_score_gemma":0.00002083896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005392424,"about_ca_topic_score_gemma":0.000005777039,"domain_scores_codex":[0.9987079,0.00004920284,0.0002245947,0.0006267597,0.0001262906,0.0002652858],"domain_scores_gemma":[0.9989784,0.0004890857,0.00004820885,0.0003003037,0.00004216752,0.0001418727],"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":[0.00002500091,0.00009091294,0.0008173416,0.0003993031,0.00006980126,0.0000473165,0.004858207,0.000177484,0.05317953,0.7821314,0.005540929,0.1526628],"study_design_scores_gemma":[0.000412209,0.00009757619,0.001448012,0.0001850468,0.000009162768,0.0001132723,0.0001325837,0.9892436,0.0001554888,0.006860015,0.001135171,0.0002078766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01704715,0.0005504735,0.9790273,0.002349699,0.0002185522,0.000325043,0.000005186093,0.0004057598,0.00007077803],"genre_scores_gemma":[0.6276053,0.00006223261,0.3719692,0.0002459388,0.00005754102,0.00001862926,0.000003540543,0.00001520408,0.00002245529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9890661,"threshold_uncertainty_score":0.9997688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07097240444014455,"score_gpt":0.3486225845864008,"score_spread":0.2776501801462563,"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."}}