{"id":"W1730856983","doi":"10.1007/978-3-642-15696-0_66","title":"Discovering Motion Patterns for Human Action Recognition","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Discriminative model; Histogram; Artificial intelligence; Representation (politics); Histogram of oriented gradients; Coherence (philosophical gambling strategy); Action recognition; Point (geometry); Optical flow; Motion (physics); Pattern recognition (psychology); Benchmark (surveying); Computer vision; Point of interest; Detector; Image (mathematics); Mathematics; Class (philosophy)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005244216,0.0003782536,0.0003068782,0.0007682072,0.0005351048,0.0006856932,0.001025165,0.0003797342,0.00005794669],"category_scores_gemma":[0.00004132263,0.0003830149,0.0001607001,0.0002024206,0.0001750256,0.001322554,0.0003009913,0.000773264,0.00005107319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00022247,"about_ca_system_score_gemma":0.0001131645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002998048,"about_ca_topic_score_gemma":0.0004398093,"domain_scores_codex":[0.9974262,0.00001944598,0.0004282203,0.001164986,0.0005193204,0.0004418778],"domain_scores_gemma":[0.9984609,0.000170139,0.0003343449,0.0006682905,0.0002549279,0.0001114012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000394542,0.00002982777,0.00001934753,0.00006510447,0.000006843744,0.000006616924,0.0002330051,0.0004130609,0.004901467,0.002373875,0.000003958304,0.9919429],"study_design_scores_gemma":[0.0007624471,0.0003820749,0.0005422718,0.0007730813,0.00002886708,0.00008893948,6.338292e-7,0.09916324,0.08295365,0.8120937,0.001920488,0.001290616],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004969663,0.00001384701,0.9904596,0.0002311793,0.002751923,0.0005554173,0.00002383125,0.000201035,0.0007934743],"genre_scores_gemma":[0.8051804,0.00004011493,0.1906529,0.0008768286,0.002453449,0.00008067027,0.0002004455,0.00007015979,0.0004450484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906523,"threshold_uncertainty_score":0.9998622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04633297557003738,"score_gpt":0.284468027909171,"score_spread":0.2381350523391336,"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."}}