{"id":"W4385687748","doi":"10.1016/j.cviu.2023.103803","title":"Improving sparse graph attention for feature matching by informative keypoints exploration","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pooling; Artificial intelligence; Pattern recognition (psychology); Matching (statistics); Feature (linguistics); Graph; Focus (optics); Mathematics; Theoretical computer science","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":[0.0004150664,0.0001930242,0.0001909096,0.0003045657,0.0004796504,0.0007270387,0.0002547901,0.0000731713,9.528675e-7],"category_scores_gemma":[0.00002713359,0.0001717021,0.00008132029,0.0005557471,0.00005105653,0.004765032,0.0003318416,0.0001511629,0.000008807798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009690004,"about_ca_system_score_gemma":0.00001367605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002831368,"about_ca_topic_score_gemma":6.027518e-7,"domain_scores_codex":[0.9988165,0.00003882267,0.0002451348,0.0003818013,0.000209979,0.0003077415],"domain_scores_gemma":[0.9992949,0.0001439134,0.0001607777,0.0002266038,0.00008337657,0.00009043543],"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":[0.0001220805,0.00009217984,0.00005733797,0.0004708112,0.00006873118,0.00003840353,0.006579378,0.00006030744,0.1316269,0.07932163,0.1308618,0.6507005],"study_design_scores_gemma":[0.001915682,0.0008613361,0.0002810384,0.0004064846,0.00001931657,0.00003245616,0.001855716,0.6858785,0.02385702,0.2815206,0.002529534,0.0008422857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001228128,0.00005619298,0.9964278,0.0008389486,0.0002683934,0.0004085491,0.00001100378,0.0006796051,0.00008133979],"genre_scores_gemma":[0.2332299,0.0003700697,0.7649968,0.0007697896,0.0001527396,0.00003930287,0.0001723207,0.00004151982,0.0002275993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6858182,"threshold_uncertainty_score":0.7010851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04132610778898841,"score_gpt":0.3054216512712523,"score_spread":0.2640955434822639,"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."}}