{"id":"W2166070055","doi":"10.1109/iccv.2007.4408849","title":"Action Recognition from Arbitrary Views using 3D Exemplars","year":2007,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":449,"is_retracted":false,"has_abstract":true,"ca_institutions":"Espace pour la vie","funders":"","keywords":"Computer science; Artificial intelligence; Novelty; Hidden Markov model; Viewpoints; Novelty detection; Process (computing); Action recognition; Computer vision; Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Image (mathematics); Action (physics); Machine learning; Feature extraction","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":[0.0002695125,0.0001040581,0.00009772227,0.0001549853,0.0001892649,0.0001215784,0.0001577781,0.00008100979,0.0005360433],"category_scores_gemma":[0.000009813567,0.0001014506,0.00005838738,0.0002329167,0.00001356159,0.001220258,0.0000393771,0.0001344021,0.0006338453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007193722,"about_ca_system_score_gemma":0.00002332493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001592527,"about_ca_topic_score_gemma":0.0001392979,"domain_scores_codex":[0.9990472,0.00003888206,0.0002431873,0.000288183,0.0001794406,0.0002031549],"domain_scores_gemma":[0.9994949,0.00006621293,0.00009524354,0.0002042253,0.00005851345,0.00008092145],"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":[0.00001285972,0.00008214261,0.0001311663,0.000005446254,0.00001615391,0.00001967352,0.0002338423,0.000003055976,0.02689047,0.0003001569,0.0006611765,0.9716439],"study_design_scores_gemma":[0.001943032,0.0002285301,0.01903873,0.0002351392,0.00008957294,0.0001750022,0.0005106187,0.09323621,0.7186268,0.1167038,0.04758311,0.001629451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3989111,0.00001509376,0.5915995,0.00006649062,0.0004642815,0.0000731223,0.00000230653,0.0001812927,0.008686823],"genre_scores_gemma":[0.6686764,0.00004234024,0.3276982,0.002457195,0.0006539552,0.000005776929,0.00008614378,0.00001725416,0.0003626562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9700144,"threshold_uncertainty_score":0.8147011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1627106786740674,"score_gpt":0.3315150419728595,"score_spread":0.1688043632987921,"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."}}