{"id":"W2900626451","doi":"10.1109/cvprw.2018.00260","title":"Image Caption Generation with Hierarchical Contextual Visual Spatial Attention","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Grid; Word (group theory); Context (archaeology); Spatial contextual awareness; Layer (electronics); Context model; Image (mathematics); Object (grammar); Pattern recognition (psychology); Computer vision; Natural language processing; Linguistics; Geography","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":[0.0001698932,0.0001050199,0.00008261977,0.00007582853,0.0002357451,0.0001778936,0.0002548016,0.00004683496,0.00009708163],"category_scores_gemma":[0.00002180669,0.00008377201,0.00002649188,0.0001956346,0.0001204643,0.0003842361,0.0000863719,0.0001329264,0.0005036636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003507382,"about_ca_system_score_gemma":0.00004235216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009659691,"about_ca_topic_score_gemma":0.0003428404,"domain_scores_codex":[0.9989572,0.00008719231,0.0001558819,0.0003737244,0.0002502569,0.0001758005],"domain_scores_gemma":[0.9993544,0.00002935559,0.00006403554,0.0002965102,0.0001779338,0.0000777753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006287966,0.0004088853,0.01086007,0.000009477723,0.00004025614,0.000007816746,0.0009611401,0.0001274372,0.4941874,0.1870816,0.001175202,0.3050779],"study_design_scores_gemma":[0.0003877399,0.0003367224,0.07980654,0.000003481737,0.000004269463,0.00002260864,0.000006757854,0.9164748,0.002356583,0.0002608037,0.0002091841,0.0001304731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.361023,9.270647e-7,0.6357005,0.001078302,0.00006665953,0.000127943,5.240126e-7,0.0001874651,0.001814728],"genre_scores_gemma":[0.8358912,3.149229e-7,0.1632416,0.000190071,0.0004429474,0.00002954991,0.00002288613,0.00000773046,0.0001735977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9163474,"threshold_uncertainty_score":0.6473744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01382938427846726,"score_gpt":0.2899706842396153,"score_spread":0.276141299961148,"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."}}