{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001659868,0.0001958068,0.0003050698,0.0002659519,0.000546873,0.0001734566,0.001767055,0.00005363315,0.0001314898],"category_scores_gemma":[0.001687451,0.0001777715,0.0002494529,0.0005802332,0.0001724577,0.0004104888,0.0003706756,0.0003785896,0.000007150381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001340404,"about_ca_system_score_gemma":0.0001073554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001196749,"about_ca_topic_score_gemma":0.00001755504,"domain_scores_codex":[0.9974495,0.00008417091,0.000803027,0.0005623948,0.0008412879,0.0002596215],"domain_scores_gemma":[0.9967917,0.0005049416,0.0009710741,0.0002684129,0.001409977,0.00005393609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002683243,0.0003225008,0.001911363,0.00007158666,0.0001067356,6.050467e-7,0.006602368,0.008990317,0.1029924,0.8479318,0.0002317947,0.03057022],"study_design_scores_gemma":[0.0001807494,0.0004368144,0.004976959,0.0001292844,0.00002771393,0.000006701303,0.008589813,0.3691194,0.4695635,0.1460433,0.0006131024,0.0003127214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2747368,0.00003434821,0.6957059,0.01805371,0.002283046,0.001708799,0.0001281698,0.0002057141,0.007143528],"genre_scores_gemma":[0.9940506,0.00001922594,0.005262029,0.0001069114,0.00007595932,0.0001764393,0.00001376923,0.00001605418,0.000279078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7193137,"threshold_uncertainty_score":0.724931,"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."}}