{"id":"W2009788881","doi":"10.1117/12.478427","title":"<title>Recognition as Translating Images into Text</title>","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; National Science Foundation","keywords":"Computer science; Feature (linguistics); Segmentation; Object (grammar); Artificial intelligence; Information retrieval; Image (mathematics); Cognitive neuroscience of visual object recognition; Natural language processing; Pattern recognition (psychology); Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001008123,0.0009980287,0.001011598,0.001485185,0.0004719709,0.003267589,0.001905915,0.002085739,0.01150092],"category_scores_gemma":[0.003618342,0.0004427685,0.001195698,0.002246327,0.001606299,0.004673808,0.0008554172,0.001299087,0.01483002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009541243,"about_ca_system_score_gemma":0.0005868275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003757773,"about_ca_topic_score_gemma":0.003236577,"domain_scores_codex":[0.9991127,0.0001913278,0.00007753939,0.000289287,0.0002507486,0.00007847016],"domain_scores_gemma":[0.9986229,0.0003797974,0.0001534649,0.0004569227,0.0003267903,0.00006013807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003024949,0.0001398225,0.00101707,0.0005867815,0.00007631919,0.0004534088,0.0003524029,0.03034468,0.0600475,0.05220139,0.06034268,0.7941354],"study_design_scores_gemma":[0.0000532601,0.0002626752,0.002386278,0.0001231728,0.00009950694,0.0008282837,0.000266669,0.6537294,0.1196602,0.1258387,0.09660657,0.0001453138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008598187,0.001163608,0.9692955,0.001221586,0.0007663404,0.0001702699,0.0008958607,0.008919733,0.008968993],"genre_scores_gemma":[0.1685856,0.002600973,0.7696025,0.001556701,0.00103239,0.0004266498,0.00550925,0.002581296,0.04810465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01150092,"threshold_uncertainty_score":0.03847444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01305801403532724,"score_gpt":0.2373037049005581,"score_spread":0.2242456908652309,"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."}}