{"id":"W2952541350","doi":"10.1109/crv.2018.00049","title":"An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-identification","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Senstar (Canada)","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Baseline (sea); Software deployment; Identification (biology); Deep learning; Domain (mathematical analysis); Range (aeronautics); Deep neural networks; Machine learning; Pattern recognition (psychology)","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":[0.01176927,0.0002260903,0.0003310205,0.0002282024,0.0001083322,0.0002466025,0.001273549,0.0002633405,0.00007040844],"category_scores_gemma":[0.0005423428,0.0002118714,0.0001814686,0.0001766808,0.00004391692,0.000358911,0.0002013216,0.0001516875,0.00001537402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001077224,"about_ca_system_score_gemma":0.0002861558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000139062,"about_ca_topic_score_gemma":0.0003100423,"domain_scores_codex":[0.9965578,0.0007439555,0.0005444778,0.0009387976,0.0009875784,0.0002273373],"domain_scores_gemma":[0.9950895,0.0001956217,0.0005676206,0.001705579,0.002367791,0.00007388328],"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":[0.00004733308,0.0003586423,0.003352221,0.0004723647,0.0001413119,7.631112e-7,0.003142791,0.01592001,0.005634516,0.002854449,0.0007490676,0.9673265],"study_design_scores_gemma":[0.000358004,0.00008762708,0.0166786,0.00005562025,0.00006991689,0.000001290787,0.0001113451,0.9390144,0.02658178,0.01672849,0.00005930553,0.0002536418],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0358374,0.0001930047,0.9599105,0.0003323932,0.00204192,0.0009488108,0.00001241857,0.0001483135,0.0005752946],"genre_scores_gemma":[0.6989214,0.00001345529,0.3003785,0.00004640574,0.0003344466,0.0001424836,0.00008955433,0.00001461514,0.00005912504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9670729,"threshold_uncertainty_score":0.8639864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442352014096874,"score_gpt":0.4077124556246107,"score_spread":0.2634772542149233,"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."}}