{"id":"W4309869330","doi":"10.48550/arxiv.2211.11925","title":"Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Modality (human–computer interaction); Computer science; Modalities; Artificial intelligence; Generalization; Task (project management); Machine learning; Exploit; Deep learning; Sensor fusion; RGB color model; Identification (biology); Mathematics; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001958903,0.001378887,0.001260334,0.0007887501,0.0004904433,0.0006925546,0.002540456,0.001556,0.002016711],"category_scores_gemma":[0.005105836,0.0004890526,0.001749782,0.000899245,0.0009745391,0.00191062,0.002580592,0.002232399,0.001442597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006507025,"about_ca_system_score_gemma":0.0007269862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004195648,"about_ca_topic_score_gemma":0.004552705,"domain_scores_codex":[0.9991473,0.0002464432,0.00003465119,0.0002903379,0.0001570222,0.0001242916],"domain_scores_gemma":[0.998674,0.0003266391,0.0001833358,0.0005595974,0.0002083401,0.00004808407],"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":[0.0009548213,0.0004745208,0.01180328,0.0002630931,0.0004078335,0.0007468201,0.0004465397,0.5206056,0.01848251,0.004278011,0.01437367,0.4271633],"study_design_scores_gemma":[0.00001150612,0.0001777025,0.002645943,0.00003371511,0.00005391077,0.0002998474,0.000111451,0.9698935,0.01835451,0.004763195,0.003611966,0.0000426706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1813226,0.001426599,0.8041986,0.0008058529,0.0003547356,0.0001410521,0.001796279,0.006379972,0.003574304],"genre_scores_gemma":[0.8410634,0.0004289093,0.1481833,0.0004794956,0.0001025283,0.0001354664,0.004363641,0.0002257255,0.005017493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004195648,"threshold_uncertainty_score":0.01035982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2768497228349971,"score_gpt":0.2953464896219919,"score_spread":0.01849676678699486,"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."}}