{"id":"W2114227971","doi":"","title":"Deep Representations and Codes for Image Auto-Annotation","year":2012,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Annotation; Artificial intelligence; Benchmark (surveying); Automatic image annotation; Feature (linguistics); Focus (optics); Pattern recognition (psychology); Image (mathematics); Image retrieval; Hamming distance; Task (project management); Deep learning; Feature extraction; Machine learning; Algorithm","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":[0.0004748692,0.0008019529,0.0005586983,0.001051496,0.0003677399,0.0009727112,0.001833086,0.001116315,0.004877053],"category_scores_gemma":[0.003266748,0.0003781042,0.0004829289,0.001398542,0.0008113157,0.002959243,0.001484487,0.002037962,0.003002996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001034246,"about_ca_system_score_gemma":0.0008616298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003872152,"about_ca_topic_score_gemma":0.004971466,"domain_scores_codex":[0.9995332,0.00007475854,0.00002900325,0.0001485433,0.0001538801,0.00006075033],"domain_scores_gemma":[0.9986299,0.0003410799,0.0001173867,0.0005571359,0.0003034343,0.00005109947],"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":[0.0003256649,0.0001569788,0.0009913024,0.0001772397,0.00003011508,0.00009845495,0.0001344661,0.08953665,0.03344478,0.04670322,0.0166225,0.8117785],"study_design_scores_gemma":[0.00001992722,0.00007432095,0.0004452072,0.0000353053,0.00001468945,0.00009733381,0.00003818323,0.9038666,0.0293659,0.0551057,0.01090779,0.0000290037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01896062,0.0003598718,0.9706227,0.000221314,0.00008150794,0.00004313059,0.0004734808,0.00695488,0.002282437],"genre_scores_gemma":[0.3549805,0.0005855676,0.6297845,0.0002949407,0.0001009027,0.0002521538,0.003745885,0.0008105322,0.00944514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004877053,"threshold_uncertainty_score":0.0163154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02653827360369656,"score_gpt":0.3183442060859372,"score_spread":0.2918059324822406,"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."}}