{"id":"W1588326449","doi":"10.1007/978-3-540-27814-6_51","title":"Extraction of Salient Features for Image Retrieval Using Multi-scale Image Relevance Function","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Image retrieval; Computer science; Salient; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Feature detection (computer vision); Scale space; Automatic image annotation; Computer vision; Visual Word; Image (mathematics); Relevance (law); Image processing","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":[0.0005247291,0.0007142723,0.001672117,0.002918127,0.0003592601,0.0007949114,0.0007796286,0.0007729436,0.002468294],"category_scores_gemma":[0.001774786,0.0004464021,0.001006234,0.002113161,0.0002668175,0.001347985,0.0006753136,0.0006414537,0.001902315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002848314,"about_ca_system_score_gemma":0.0004868423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007771479,"about_ca_topic_score_gemma":0.001265198,"domain_scores_codex":[0.9997235,0.00002909225,0.00002180137,0.00005057604,0.0001338824,0.00004118561],"domain_scores_gemma":[0.9994777,0.0001349214,0.00006236523,0.00007498595,0.0002201388,0.00002999001],"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":[0.0003230977,0.0001351926,0.0004422795,0.0003951707,0.00005458077,0.0002132083,0.00005442515,0.004862858,0.4018932,0.001784415,0.003443652,0.5863979],"study_design_scores_gemma":[0.0001291757,0.0006750294,0.01469982,0.00006638426,0.0004164117,0.001663815,0.0001321458,0.6481983,0.3143887,0.006981968,0.01253191,0.0001163093],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03738472,0.001725163,0.9580014,0.0001120647,0.0001187271,0.0001404498,0.0001751743,0.001366945,0.0009753085],"genre_scores_gemma":[0.2225217,0.001476194,0.7717133,0.00008231186,0.000189217,0.0001736603,0.0007608694,0.0002676592,0.002815143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002918127,"threshold_uncertainty_score":0.00825727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02540452358785483,"score_gpt":0.2942470428648285,"score_spread":0.2688425192769737,"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."}}