{"id":"W2404253817","doi":"10.1109/wacv.2016.7477588","title":"Efficient video-based retrieval of human motion with flexible alignment","year":2016,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Motion capture; Dynamic time warping; Motion compensation; Set (abstract data type); Motion (physics); Image warping; Feature (linguistics); Benchmark (surveying); Feature extraction; Matching (statistics); Scalability; Pattern recognition (psychology); Database","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":[0.0001589114,0.00006815379,0.00007889566,0.00009539827,0.0000661649,0.00002380812,0.0001550568,0.00002483285,0.0002317026],"category_scores_gemma":[0.000005389857,0.0000389484,0.00003286447,0.000157702,0.00003376004,0.00009226146,0.00002602949,0.00002210674,0.00007369836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004058558,"about_ca_system_score_gemma":0.00002590255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007848283,"about_ca_topic_score_gemma":0.000001987765,"domain_scores_codex":[0.9992331,0.00002804538,0.0001490039,0.0001971202,0.0002723275,0.0001203522],"domain_scores_gemma":[0.9995099,0.00003002405,0.00007993694,0.0002460566,0.00008775182,0.00004631852],"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":[0.0001420848,0.001129549,0.001526499,0.00006864407,0.00005756582,0.00001165294,0.0003194785,0.001777688,0.7793615,0.1362162,0.001770169,0.07761903],"study_design_scores_gemma":[0.000977476,0.0004024041,0.002306472,0.00007414744,0.000005811427,0.00000224268,0.000009141913,0.006231401,0.9887052,0.0009020559,0.0002691099,0.0001145798],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3064304,0.000002077796,0.6890031,0.0003987749,0.00005053201,0.0000877348,0.000001070215,0.0001004223,0.003925914],"genre_scores_gemma":[0.9956253,3.805795e-7,0.003383655,0.0001296,0.00002119024,0.000003241888,0.000001209441,0.000003824076,0.0008315939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6891949,"threshold_uncertainty_score":0.2536981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191510690302947,"score_gpt":0.2463953147962465,"score_spread":0.2272442457659518,"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."}}