{"id":"W2007060009","doi":"10.1109/crv.2010.54","title":"Human Action Recognition Using Salient Opponent-Based Motion Features","year":2010,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Salient; Artificial intelligence; Computer science; Motion (physics); Pattern recognition (psychology); Feature extraction; Set (abstract data type); Computer vision; Action (physics); Feature (linguistics); Energy (signal processing); Biological motion; 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":[0.0001924991,0.0001180932,0.00008363963,0.0002151622,0.0003326878,0.0002383734,0.0001758657,0.0001090255,0.000445199],"category_scores_gemma":[0.00001485449,0.0001135252,0.00007200285,0.0001867891,0.00002422133,0.0007773401,0.00003034346,0.0002463908,0.0002413234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003911927,"about_ca_system_score_gemma":0.00002707208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001385302,"about_ca_topic_score_gemma":0.0001933087,"domain_scores_codex":[0.999061,0.00005279631,0.0001741431,0.0003067608,0.0002237954,0.0001814613],"domain_scores_gemma":[0.9994095,0.00001708599,0.0001049683,0.0002617531,0.0001222869,0.00008440336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007389229,0.0002903835,0.0001833034,0.00002196044,0.00001333804,0.00000602436,0.00008874381,0.00008824524,0.7273114,0.00321753,0.002999626,0.265772],"study_design_scores_gemma":[0.00140149,0.0001734835,0.02015785,0.00005258921,0.00004094095,0.00006233286,0.00008626631,0.06819212,0.8877692,0.01919332,0.002118967,0.0007514199],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7360817,0.00000173631,0.2600711,0.000395663,0.0009311897,0.0001381239,0.000002051464,0.0003351604,0.002043226],"genre_scores_gemma":[0.9789359,8.171622e-7,0.01984116,0.000777723,0.0002103387,0.00001163293,0.00005749773,0.000007418473,0.0001575217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2650206,"threshold_uncertainty_score":0.4874617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07520099848527821,"score_gpt":0.3130402947991104,"score_spread":0.2378392963138322,"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."}}