{"id":"W3215163807","doi":"10.24963/ijcai.2022/180","title":"SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"Nanyang Technological University","keywords":"Skeleton (computer programming); Computer science; Artificial intelligence; Discriminative model; Sequence (biology); Feature learning; Pattern recognition (psychology); Consistency (knowledge bases); Similarity (geometry); Representation (politics); Identification (biology); Deep learning; Natural language processing; Image (mathematics)","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":[0.001058948,0.001179202,0.001094492,0.001064898,0.0004142409,0.0006230013,0.002746972,0.001298364,0.003645752],"category_scores_gemma":[0.002831908,0.0005742167,0.001074073,0.0008400084,0.0008687708,0.001452933,0.001957057,0.0017498,0.002636478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006715764,"about_ca_system_score_gemma":0.001007833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004486412,"about_ca_topic_score_gemma":0.008806055,"domain_scores_codex":[0.9991373,0.0001346708,0.00002583799,0.0003906177,0.0002184319,0.00009316801],"domain_scores_gemma":[0.9990824,0.0002198389,0.00008708086,0.0003482849,0.0001895585,0.00007271702],"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":[0.0003765126,0.0002696878,0.002339812,0.0001301171,0.0001516265,0.0001572334,0.0001342073,0.1266,0.02714526,0.005812268,0.009791343,0.8270919],"study_design_scores_gemma":[0.00001489617,0.0001123585,0.0007300325,0.00001316831,0.00001900977,0.0001634268,0.00001594586,0.9832394,0.008895691,0.003983922,0.002793629,0.00001856914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01777092,0.0003865549,0.9765452,0.0001007648,0.00008088464,0.00009155279,0.0002159865,0.003432708,0.001375511],"genre_scores_gemma":[0.2906624,0.0004288678,0.6960837,0.0004035359,0.0001233385,0.0002317503,0.002257055,0.0006401162,0.009169308],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004486412,"threshold_uncertainty_score":0.01219624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1077185773896893,"score_gpt":0.3326002944640817,"score_spread":0.2248817170743923,"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."}}