{"id":"W4253829576","doi":"10.1109/cvpr.2009.5204333","title":"Beyond one-to-one feature correspondence: The need for many-to-many matching and image abstraction","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Abstraction; Computer science; Feature (linguistics); Search engine indexing; Matching (statistics); Artificial intelligence; Set (abstract data type); Feature matching; Object (grammar); Pattern recognition (psychology); Image (mathematics); Space (punctuation); Correspondence problem; Theoretical computer science; Mathematics; Programming language","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005678301,0.0004968005,0.0004715701,0.0001819601,0.0006187056,0.001528989,0.0007527748,0.0002596084,0.00001385287],"category_scores_gemma":[0.00001253929,0.0004172831,0.0002080323,0.0005043494,0.00007879159,0.0009774974,0.0002857713,0.0006647681,0.00004343834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000581918,"about_ca_system_score_gemma":0.00004105485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004925274,"about_ca_topic_score_gemma":0.00000200365,"domain_scores_codex":[0.9972159,0.0001361155,0.0004623882,0.00111986,0.000495769,0.0005699538],"domain_scores_gemma":[0.9979002,0.000467124,0.0002295475,0.000600589,0.0004437888,0.0003587057],"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":[0.00007673646,0.0001381067,0.000007982158,0.00003225003,0.00002772195,0.000007000872,0.001119316,0.00005263665,0.002036599,0.0004743043,0.02305955,0.9729678],"study_design_scores_gemma":[0.004454213,0.007668945,0.03294921,0.003927763,0.0001314143,0.0002418231,0.0002679373,0.8122001,0.01241899,0.1147017,0.007670231,0.003367665],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01690634,0.00005484398,0.9666752,0.01379578,0.0008284177,0.001224533,0.00004637026,0.0003820945,0.0000863968],"genre_scores_gemma":[0.2858979,0.0003819168,0.6714859,0.04096429,0.0009618852,0.00006722624,0.00005909718,0.000037346,0.0001444821],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9696001,"threshold_uncertainty_score":0.9998279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0351146685024474,"score_gpt":0.3076011160489306,"score_spread":0.2724864475464832,"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."}}