{"id":"W3092681294","doi":"10.1109/icpr48806.2021.9413136","title":"A Grid-based Representation for Human Action Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Discriminative model; Computer science; Artificial intelligence; Benchmark (surveying); Representation (politics); Action recognition; Action (physics); Grid; Task (project management); Machine learning; Pattern recognition (psychology); Class (philosophy); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002445835,0.0002166109,0.0002355449,0.0002734151,0.0002571754,0.0007386236,0.0003297774,0.0002773836,0.0002692626],"category_scores_gemma":[0.0000593869,0.0002395571,0.00028767,0.0001923599,0.00001751552,0.0005627633,0.0001934954,0.0003047744,0.00005104647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001162075,"about_ca_system_score_gemma":0.0001668674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001345663,"about_ca_topic_score_gemma":0.0001694719,"domain_scores_codex":[0.9981994,0.0001204841,0.0003850618,0.0008197378,0.0002681831,0.000207123],"domain_scores_gemma":[0.9984193,0.0001038333,0.0003066924,0.0005993461,0.0004973728,0.00007347105],"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":[0.00007770475,0.001174264,0.0001375366,0.001541404,0.0003100055,0.00003579013,0.0009826551,0.00194196,0.03524833,0.00478557,0.03143433,0.9223304],"study_design_scores_gemma":[0.002885087,0.0003466719,0.002029873,0.0007990914,0.0002121316,0.00002547038,0.0004365315,0.1887833,0.6278887,0.16932,0.005472851,0.001800268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07043182,0.00001579136,0.9228184,0.0007424733,0.002142189,0.0007552654,0.00002822258,0.0005188838,0.002546924],"genre_scores_gemma":[0.8250942,0.00004009961,0.1601538,0.001696568,0.00175731,0.001477429,0.008429637,0.0000514069,0.001299498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9205302,"threshold_uncertainty_score":0.9768856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.193186320797441,"score_gpt":0.3785370716505352,"score_spread":0.1853507508530942,"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."}}