{"id":"W2081934843","doi":"10.1109/icip.2012.6467136","title":"Non-negative sparse coding for human action recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Neural coding; Computer science; Sparse approximation; Pattern recognition (psychology); Artificial intelligence; Action recognition; Support vector machine; Representation (politics); Feature (linguistics); Coding (social sciences); Feature vector; Feature extraction; 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":[0.0002202949,0.00008330807,0.00007821948,0.0001021859,0.0002705327,0.00008937758,0.0001091443,0.00004926072,0.0001742216],"category_scores_gemma":[0.00001931291,0.00007952478,0.00005803654,0.0001184364,0.0000126866,0.001540513,0.00002804956,0.00006555179,0.0003767963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004302251,"about_ca_system_score_gemma":0.000009228782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000187873,"about_ca_topic_score_gemma":0.00001638571,"domain_scores_codex":[0.9993562,0.00001936038,0.0001386542,0.0001621766,0.00009806629,0.0002255214],"domain_scores_gemma":[0.9995605,0.00006392186,0.00007894787,0.0001230986,0.00009558641,0.00007791129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004251905,0.0007814867,0.0009501218,0.0001308588,0.0001085117,0.000001631065,0.004311034,0.000005322599,0.1120383,0.07936313,0.02958427,0.7726828],"study_design_scores_gemma":[0.001596437,0.0002821269,0.007822612,0.00007378693,0.00003921808,0.00002575817,0.0005568801,0.009334887,0.8915886,0.07853696,0.00950793,0.0006347953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1862953,0.000002887616,0.7943839,0.0001526489,0.0006597493,0.0003070153,0.000003530781,0.0002001989,0.01799468],"genre_scores_gemma":[0.9783701,0.000004294794,0.01988081,0.0003312382,0.000428042,0.00007364029,0.00002466848,0.000006885266,0.0008802639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7920748,"threshold_uncertainty_score":0.4843079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1365592667280948,"score_gpt":0.3340452274806414,"score_spread":0.1974859607525466,"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."}}