{"id":"W2560645892","doi":"10.1109/iccv.2017.140","title":"Areas of Attention for Image Captioning","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":218,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Agence Nationale de la Recherche","keywords":"Closed captioning; Computer science; Pairwise comparison; Transformer; Artificial intelligence; Convolutional neural network; Image (mathematics); Language model; Pattern recognition (psychology); Computer vision","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":[0.0003059074,0.0001214165,0.0001870597,0.00008671702,0.0001665792,0.0002139759,0.001368323,0.0001096593,0.00001136339],"category_scores_gemma":[0.0001580651,0.000120053,0.0001484276,0.00002931367,0.00004137576,0.0001399677,0.0009683971,0.0002164257,0.00002584392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000292669,"about_ca_system_score_gemma":0.00007789709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00100949,"about_ca_topic_score_gemma":0.00001475656,"domain_scores_codex":[0.9990524,0.00002509878,0.000225501,0.0004270556,0.0001423595,0.0001275608],"domain_scores_gemma":[0.9978032,0.00007690203,0.0004517857,0.0013894,0.0002390256,0.00003967511],"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":[0.00001295694,0.0003235655,0.01967358,0.001203472,0.0001950079,0.0000021925,0.0008385649,0.01069447,0.01766307,0.7724034,0.003404959,0.1735848],"study_design_scores_gemma":[0.000243254,0.00002056824,0.1406588,0.0001197209,0.00002120667,0.000002924102,0.00000510322,0.804517,0.0007646256,0.05286277,0.0005458796,0.0002380618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01778905,0.00001917225,0.9722703,0.001693464,0.0002338651,0.0004761588,0.0000111671,0.0001634473,0.007343364],"genre_scores_gemma":[0.5884904,0.000002587861,0.4106475,0.00001279622,0.00005162035,0.0001541202,0.00003254537,0.000007499466,0.0006009349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7938226,"threshold_uncertainty_score":0.4895618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048174510081268,"score_gpt":0.3389131894072359,"score_spread":0.3084314443064232,"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."}}