{"id":"W4387676203","doi":"10.1016/j.patcog.2023.110045","title":"A Novel Attention-Driven Framework for Unsupervised Pedestrian Re-identification with Clustering Optimization","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada","funders":"National Natural Science Foundation of China-Shandong Joint Fund for Marine Science Research Centers; Natural Science Foundation of Shandong Province","keywords":"Computer science; Artificial intelligence; Cluster analysis; Pedestrian; Pattern recognition (psychology); Identification (biology); Machine learning; Field (mathematics); Unsupervised learning; Convolutional neural network; Task (project management); Pedestrian detection","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":[0.001269156,0.001420871,0.002394004,0.001590881,0.0008916699,0.001321324,0.004910935,0.002337653,0.004230707],"category_scores_gemma":[0.002554739,0.001047389,0.001818468,0.001863216,0.0008700904,0.001518789,0.002903682,0.001953713,0.00192633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001369603,"about_ca_system_score_gemma":0.002202132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02204808,"about_ca_topic_score_gemma":0.0265505,"domain_scores_codex":[0.9988546,0.0002476958,0.0000480565,0.0004064324,0.0002675491,0.0001755858],"domain_scores_gemma":[0.9990678,0.00026842,0.00007230409,0.0001529402,0.0003562399,0.00008235688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003219284,0.0002776089,0.0008163788,0.0001453422,0.0002246073,0.0001391798,0.0001257312,0.5590631,0.01479486,0.02331609,0.01204775,0.3887275],"study_design_scores_gemma":[0.000003307807,0.00000976789,0.00006089319,0.000002687792,0.00000580753,0.00001249118,0.000003600782,0.9964523,0.00060702,0.002442703,0.0003940498,0.000005337951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00240365,0.0001453615,0.9959351,0.00007397399,0.00003787121,0.00003309546,0.00006628109,0.0006644532,0.0006401975],"genre_scores_gemma":[0.20462,0.0003541313,0.7804083,0.0005051285,0.0002528829,0.0003225244,0.00121402,0.0009089283,0.0114141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02204808,"threshold_uncertainty_score":0.04383951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09206838056496137,"score_gpt":0.3193227789167085,"score_spread":0.2272543983517472,"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."}}