{"id":"W2100968369","doi":"10.1109/tpami.2005.220","title":"Efficient shape matching using shape contexts","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":458,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Shape analysis (program analysis); Heat kernel signature; Active shape model; Artificial intelligence; Shape context; Computer science; Matching (statistics); Computer vision; Pattern recognition (psychology); Vector quantization; Mathematics; Image (mathematics); Segmentation","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002775828,0.000214243,0.0002747345,0.0004701398,0.0002866655,0.0002038369,0.0004571763,0.00006426649,0.0002828734],"category_scores_gemma":[0.000002741944,0.0001849959,0.000235383,0.001016196,0.00006381582,0.0001787457,0.000008340083,0.0002445867,0.00004650895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006199566,"about_ca_system_score_gemma":0.0000206279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002857237,"about_ca_topic_score_gemma":0.0001147109,"domain_scores_codex":[0.9984543,0.00007104855,0.0004056235,0.0005172673,0.0003068368,0.0002448686],"domain_scores_gemma":[0.9991316,0.00008710696,0.0001240448,0.0004398349,0.00009331409,0.000124149],"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":[0.000004702828,0.0001427519,0.00003985491,0.00000733531,0.000129957,0.000003956052,0.0003154767,0.0231822,0.002585582,0.0001787427,9.880819e-7,0.9734085],"study_design_scores_gemma":[0.00004195952,0.00003412076,0.0002007886,0.00001705241,0.0001313868,0.00001457997,0.00002073495,0.8262615,0.1729492,0.00008682755,0.00005652327,0.0001853655],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01887364,0.0001538044,0.9799778,0.0005347125,0.0000808031,0.0001163079,0.00001436343,0.0001853417,0.00006324245],"genre_scores_gemma":[0.9890748,0.0001135977,0.01004573,0.000602908,0.00002378707,0.0000104411,0.000001362582,0.00001028664,0.0001171401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9732231,"threshold_uncertainty_score":0.7543916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02776617728988811,"score_gpt":0.2924933018035573,"score_spread":0.2647271245136691,"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."}}