{"id":"W4251040078","doi":"10.1109/icpr.2004.1334481","title":"Shape retrieval using concavity trees","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Silhouette; Pattern recognition (psychology); Computer science; Tree (set theory); Matching (statistics); Artificial intelligence; Image retrieval; Feature extraction; Feature (linguistics); Feature vector; Tree structure; Mathematics; Image (mathematics); Algorithm; Combinatorics; Binary tree; Statistics","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":[0.0004685183,0.0004689369,0.0007411824,0.002938378,0.0006133029,0.001321847,0.0009969876,0.0007555996,0.002183472],"category_scores_gemma":[0.003165463,0.000468462,0.0007187709,0.00289517,0.0006125747,0.002777724,0.001041097,0.0007511395,0.002006874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005994427,"about_ca_system_score_gemma":0.0005542104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002490578,"about_ca_topic_score_gemma":0.002991924,"domain_scores_codex":[0.9992217,0.00009067161,0.00004652851,0.0001521113,0.0004184341,0.00007043481],"domain_scores_gemma":[0.9985216,0.0004441432,0.0002117025,0.0003600535,0.0004146519,0.00004772953],"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":[0.0003940067,0.00008249143,0.001870082,0.0002002651,0.00006040454,0.0002676554,0.0003284346,0.02841156,0.1338615,0.02340956,0.005648231,0.8054658],"study_design_scores_gemma":[0.00004537041,0.0002503422,0.003572201,0.0000413655,0.00006094297,0.001494039,0.0001459839,0.8248778,0.1225311,0.02683892,0.02004793,0.00009401998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04700053,0.0007286696,0.9464513,0.0001128973,0.00002730309,0.0001041021,0.0001987264,0.00189137,0.003485176],"genre_scores_gemma":[0.3531262,0.0008961156,0.63797,0.0001845548,0.00008751622,0.000108477,0.001322527,0.0004320194,0.005872558],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002938378,"threshold_uncertainty_score":0.00730443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07459041303220466,"score_gpt":0.2986094031659968,"score_spread":0.2240189901337922,"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."}}