{"id":"W3110876735","doi":"10.1186/s13640-021-00562-6","title":"Exploiting prunability for person re-identification","year":2021,"lang":"en","type":"article","venue":"EURASIP Journal on Image and Video Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Pruning; Convolutional neural network; Artificial intelligence; Deep learning; Identification (biology); Feature (linguistics); FLOPS; Machine learning; Computational complexity theory; Pattern recognition (psychology); Feature extraction; Domain (mathematical analysis); Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002198222,0.0001411934,0.0001999101,0.00008877616,0.0007215184,0.001639144,0.0002555812,0.00004707691,0.00000617806],"category_scores_gemma":[0.001267747,0.0001264852,0.000094353,0.0002820863,0.00004030302,0.00158497,0.00004580498,0.000276924,0.00000376517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004441074,"about_ca_system_score_gemma":0.0001622678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.946078e-7,"about_ca_topic_score_gemma":0.000001461972,"domain_scores_codex":[0.9984539,0.000222112,0.0003545381,0.0004290371,0.0002553422,0.0002851156],"domain_scores_gemma":[0.9984995,0.000310702,0.0002884777,0.0002503204,0.0005352575,0.0001157368],"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":[0.00002616605,0.00007879221,0.002555919,0.0002079224,0.00001620159,0.00008405275,0.002157242,0.00001781913,0.03944531,0.0004843843,0.0003876495,0.9545385],"study_design_scores_gemma":[0.005216518,0.0008355335,0.1915299,0.002583635,0.0001337957,0.003877019,0.00716333,0.08296696,0.6152766,0.06877649,0.01938825,0.002251919],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09058652,0.00114157,0.9030091,0.004245921,0.0003291226,0.00009263965,0.000001233938,0.00007625165,0.0005176211],"genre_scores_gemma":[0.8280218,0.00006898648,0.1708234,0.000580756,0.0003210179,0.00001004648,0.000001761314,0.00001514243,0.0001571441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9522866,"threshold_uncertainty_score":0.9993973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06440125554445895,"score_gpt":0.3486757450711406,"score_spread":0.2842744895266817,"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."}}