{"id":"W2949906242","doi":"10.48550/arxiv.1612.01033","title":"Areas of Attention for Image Captioning","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Closed captioning; Computer science; Pairwise comparison; Transformer; Artificial intelligence; Language model; Image (mathematics); Convolutional neural network; Natural language processing; Pattern recognition (psychology); Machine learning","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":[0.001019787,0.001382552,0.0006283021,0.00134348,0.0004783342,0.001395853,0.001850113,0.001417272,0.005637689],"category_scores_gemma":[0.003556245,0.0005125077,0.001297147,0.0009937893,0.0009821623,0.003005633,0.001903898,0.002076825,0.00204071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001244418,"about_ca_system_score_gemma":0.0007834045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004565594,"about_ca_topic_score_gemma":0.006174543,"domain_scores_codex":[0.9992136,0.0002351434,0.00003442838,0.0002926116,0.0001276083,0.00009663562],"domain_scores_gemma":[0.9988127,0.0004396123,0.0001229026,0.0003252787,0.0002261389,0.00007343013],"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":[0.0007128426,0.0002450105,0.002763045,0.0005212643,0.0001934296,0.000311164,0.0005170765,0.1663203,0.04933335,0.02872368,0.03036645,0.7199923],"study_design_scores_gemma":[0.00002134558,0.00009599297,0.0008457737,0.00002912818,0.00004485956,0.0001470305,0.00004912454,0.942407,0.02357954,0.02130451,0.01145158,0.00002417673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03720162,0.001899279,0.9354842,0.0007125598,0.0003038841,0.0002399194,0.001053834,0.01401666,0.009088133],"genre_scores_gemma":[0.6507046,0.001073651,0.3304814,0.0006175373,0.000293148,0.0003155134,0.003022109,0.001195923,0.01229606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005637689,"threshold_uncertainty_score":0.01885992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05277417207380759,"score_gpt":0.2151521324611663,"score_spread":0.1623779603873587,"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."}}