{"id":"W2097089830","doi":"10.1109/cvpr.2006.297","title":"Successive Convex Matching for Action Detection","year":2006,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Matching (statistics); Sequence (biology); Computer science; Computer vision; Artificial intelligence; Template matching; Regular polygon; Point set registration; Point (geometry); Scheme (mathematics); Pattern recognition (psychology); Algorithm; Mathematics; Image (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":[0.00006805778,0.00005186115,0.00004956903,0.00006799999,0.0001664086,0.0001314499,0.00008996351,0.00003414142,0.00004095267],"category_scores_gemma":[0.000004763037,0.00004813066,0.00003974677,0.00008622355,0.000006089252,0.0006688237,0.00001410996,0.00003941662,0.00006953033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002612734,"about_ca_system_score_gemma":0.00000898571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001097757,"about_ca_topic_score_gemma":0.0001591926,"domain_scores_codex":[0.9995585,0.0000124985,0.0001004582,0.0001519863,0.00007382205,0.0001027131],"domain_scores_gemma":[0.9997265,0.00005258319,0.00005406502,0.00008722105,0.00006201122,0.00001764376],"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":[0.00002509057,0.0001471596,0.00007286209,0.00005746451,0.00002219084,0.000003454729,0.0002267094,0.0004077321,0.1896956,0.1632121,0.003289987,0.6428396],"study_design_scores_gemma":[0.0007509601,0.0001111359,0.001956149,0.00001334907,0.0000104876,0.00002067929,0.0001274533,0.08747071,0.7438378,0.1524585,0.01295535,0.0002874757],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06366266,0.000003609315,0.930612,0.0001840773,0.0003928599,0.0001150982,6.39035e-7,0.0002192399,0.004809821],"genre_scores_gemma":[0.9922327,8.667916e-7,0.006036408,0.0001708922,0.0002121712,0.00003120987,0.000005460292,0.000003810466,0.001306487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.92857,"threshold_uncertainty_score":0.1962711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.020688137702149,"score_gpt":0.2683504547072547,"score_spread":0.2476623170051057,"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."}}