{"id":"W4394625702","doi":"10.1109/wacv57701.2024.00073","title":"Learning to Recognize Occluded and Small Objects with Partial Inputs","year":2024,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision","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":[0.001093902,0.001713954,0.00127875,0.0006414736,0.0005835874,0.001333272,0.002650182,0.001780488,0.003716906],"category_scores_gemma":[0.003500899,0.0005630213,0.001524905,0.0005612719,0.001042107,0.002718457,0.002229262,0.002092536,0.002329156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007317321,"about_ca_system_score_gemma":0.0012031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003087087,"about_ca_topic_score_gemma":0.006365356,"domain_scores_codex":[0.9990038,0.0001370634,0.00003371944,0.0005131249,0.0001721098,0.0001402552],"domain_scores_gemma":[0.998187,0.0005209923,0.0001847142,0.0007488097,0.0002288185,0.0001296575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007432904,0.0005214352,0.005539007,0.0004646637,0.000165,0.0002968949,0.0002647149,0.09473269,0.0752634,0.004124492,0.01424981,0.8036346],"study_design_scores_gemma":[0.00002097549,0.0001637306,0.001100842,0.00002683368,0.00003288974,0.0001440318,0.00007307457,0.9607241,0.02617266,0.009381122,0.002140739,0.0000189561],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1052864,0.0006239427,0.8780248,0.0003944885,0.0001691888,0.0001909622,0.000716067,0.01093628,0.003657853],"genre_scores_gemma":[0.5829886,0.0002592028,0.406847,0.0005805138,0.0001116229,0.0002444377,0.00326756,0.0005867741,0.005114347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003716906,"threshold_uncertainty_score":0.0124343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01483884989225203,"score_gpt":0.2338113485746017,"score_spread":0.2189724986823496,"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."}}