{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000368538,0.001418572,0.002483763,0.002330368,0.0006139217,0.0007570988,0.002238832,0.00174573,0.006470435],"category_scores_gemma":[0.002842565,0.0006412306,0.001018255,0.002901622,0.0005863009,0.002277893,0.002118588,0.001481652,0.0018334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005442195,"about_ca_system_score_gemma":0.001065555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00905008,"about_ca_topic_score_gemma":0.01322988,"domain_scores_codex":[0.9993561,0.00009245246,0.00002536115,0.0002285459,0.0001888595,0.0001087258],"domain_scores_gemma":[0.9989806,0.0004928769,0.00007243436,0.0002264851,0.0001597507,0.00006794559],"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":[0.0007962467,0.000433037,0.00126667,0.0002526051,0.0001539818,0.0002296959,0.000130742,0.09942496,0.05333538,0.007278778,0.0156591,0.8210388],"study_design_scores_gemma":[0.00003517484,0.0001078314,0.0004070385,0.000007493119,0.00003418932,0.0001111555,0.00003173387,0.9818859,0.007073647,0.008891696,0.001402641,0.00001151796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03568132,0.0008781656,0.9575053,0.0002016242,0.0001136172,0.00007561093,0.0002234251,0.003745864,0.001575239],"genre_scores_gemma":[0.6482001,0.0007259776,0.3403928,0.0005887158,0.0002250492,0.0001312275,0.001665681,0.000797654,0.007272845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00905008,"threshold_uncertainty_score":0.02164578,"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."}}