{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002085587,0.0001628085,0.0002041813,0.0001867588,0.0001182629,0.00004494415,0.001119393,0.0001426409,0.0000125733],"category_scores_gemma":[0.00006274775,0.0001727449,0.0002003256,0.0002091779,0.00007663613,0.0002264095,0.000816871,0.0002044564,0.0000458065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001086296,"about_ca_system_score_gemma":0.00009096106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779382,"about_ca_topic_score_gemma":0.000007747568,"domain_scores_codex":[0.9988246,0.00006538667,0.0001716207,0.0006895528,0.00005802907,0.0001908387],"domain_scores_gemma":[0.9982199,0.0001484942,0.0003584866,0.0009380392,0.000262053,0.00007303515],"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":[0.00002331289,0.0001157814,0.01597266,0.00019693,0.0001026433,0.00001081343,0.0001434728,0.03791137,0.003690324,0.9387003,0.0002163458,0.002916018],"study_design_scores_gemma":[0.0006350199,0.00003846923,0.03914961,0.0001742949,0.00006275593,0.000002399708,0.000015783,0.7945886,0.0004000695,0.1643583,0.000225973,0.0003487411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2007094,0.000008022538,0.797076,0.0002375651,0.0001444347,0.0003098006,0.00002334689,0.0001423139,0.001349189],"genre_scores_gemma":[0.9789581,0.0000104007,0.02019511,0.000013474,0.00005161402,0.00000530819,0.00002066146,0.00001318449,0.0007321006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7782488,"threshold_uncertainty_score":0.7044333,"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."}}