{"id":"W2104670258","doi":"10.1109/tpami.2008.283","title":"Using Language to Learn Structured Appearance Models for Image Annotation","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Object (grammar); Feature (linguistics); Image retrieval; Computer vision; Annotation; Graph; Set (abstract data type); Natural language processing; Image (mathematics)","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":[0.001786248,0.001606517,0.001301472,0.001944452,0.0005960827,0.001434621,0.002945653,0.001886005,0.001538353],"category_scores_gemma":[0.007394267,0.0009080817,0.00189294,0.001425093,0.001432166,0.002947439,0.001416146,0.002280823,0.00142372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001487918,"about_ca_system_score_gemma":0.0009320909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006169492,"about_ca_topic_score_gemma":0.007651057,"domain_scores_codex":[0.9985941,0.0004627445,0.00005922581,0.000592407,0.0001906462,0.0001007261],"domain_scores_gemma":[0.9967307,0.001550447,0.0003626514,0.0006657339,0.000552183,0.0001383311],"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":[0.000607012,0.0004199167,0.003919857,0.0003196459,0.0002081426,0.0004210299,0.0006516279,0.4077462,0.03891319,0.00997034,0.006655942,0.5301671],"study_design_scores_gemma":[0.00001301484,0.00003784868,0.0002130476,0.000008237506,0.00001193654,0.00004674023,0.00002567509,0.9906758,0.003240957,0.005203906,0.0005079971,0.0000148494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03073782,0.0002262157,0.9640427,0.0001647719,0.00004490026,0.00008675112,0.0002068755,0.003642812,0.0008471524],"genre_scores_gemma":[0.4070011,0.0002746382,0.5860758,0.0003685702,0.00009544216,0.0003962609,0.002209154,0.0005915182,0.00298742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006169492,"threshold_uncertainty_score":0.01226717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04243375087321095,"score_gpt":0.3300145318790926,"score_spread":0.2875807810058817,"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."}}