{"id":"W1514208555","doi":"10.1109/ijcnn.2005.1556162","title":"Using knowledge of the region of interest (ROI) in automatic image retrieval learning","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Naresuan University; Canada Research Chairs","keywords":"Computer science; Relevance feedback; Artificial intelligence; Relevance (law); Process (computing); Artificial neural network; Set (abstract data type); Region of interest; Image retrieval; Machine learning; Computer vision; Data mining; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001861355,0.0006659726,0.0008467113,0.001030315,0.0003779958,0.0006985632,0.001537777,0.001084808,0.001249033],"category_scores_gemma":[0.007873625,0.0004393886,0.0005228369,0.0007629204,0.0006716881,0.002551626,0.0009047407,0.0007587185,0.001009352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003931074,"about_ca_system_score_gemma":0.0005995567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001581643,"about_ca_topic_score_gemma":0.001811975,"domain_scores_codex":[0.9989309,0.0003161643,0.0000489263,0.0003516045,0.0002858399,0.00006662371],"domain_scores_gemma":[0.9974329,0.0012728,0.0003111464,0.000446795,0.0004757165,0.00006057737],"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":[0.0003407619,0.0002138775,0.001268468,0.0003097371,0.00006264329,0.0002018358,0.00034646,0.03710926,0.1389055,0.00334538,0.002186132,0.8157099],"study_design_scores_gemma":[0.00008100755,0.0006780144,0.005969077,0.0000605615,0.0001176806,0.000792723,0.0001438685,0.8496235,0.1202221,0.01465337,0.007537465,0.0001206118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02249166,0.0005694071,0.9742383,0.00008785373,0.000025925,0.00008027632,0.00003575105,0.00174149,0.0007292988],"genre_scores_gemma":[0.4180684,0.000532241,0.5788295,0.0002053547,0.00009581732,0.0002241998,0.0001972662,0.0002520178,0.001595182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001861355,"threshold_uncertainty_score":0.009843886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09929148277385846,"score_gpt":0.3075985863804036,"score_spread":0.2083071036065451,"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."}}