{"id":"W2130820701","doi":"10.1109/crv.2012.69","title":"Evaluation of Local Spatio-temporal Salient Feature Detectors for Human Action Recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Artificial intelligence; Salient; Detector; Computer science; Pattern recognition (psychology); Computer vision; Motion (physics); Representation (politics); Feature (linguistics); Action recognition; Feature extraction; Sparse approximation; Motion detection","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":[0.001255726,0.00009708416,0.0001018109,0.00014708,0.0001360489,0.00003688064,0.000108906,0.00009122608,0.0002097787],"category_scores_gemma":[0.0000339307,0.0000900904,0.00008164588,0.0001655931,0.00002178889,0.0009393334,0.00002290223,0.00006852902,0.00004280947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001241317,"about_ca_system_score_gemma":0.00004336519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004516216,"about_ca_topic_score_gemma":0.0001748368,"domain_scores_codex":[0.9988073,0.0001306072,0.0002003595,0.0001783477,0.0005001745,0.0001832034],"domain_scores_gemma":[0.9989889,0.0000378623,0.0001689815,0.0001697757,0.0005655516,0.0000688826],"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":[0.00001783879,0.0002369184,0.0005023752,0.0000383862,0.00003643143,6.189792e-8,0.0003568362,0.00004299103,0.005677233,0.002404269,0.003293606,0.9873931],"study_design_scores_gemma":[0.002494826,0.0005758497,0.0161599,0.00007907551,0.0002759319,0.00001200221,0.0005863642,0.07258727,0.8538015,0.04774376,0.005124981,0.0005585312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4481131,0.00002208585,0.5497962,0.00008547348,0.0004705801,0.0003741355,0.000004911875,0.00008227483,0.001051257],"genre_scores_gemma":[0.9924641,0.000001736163,0.006898812,0.00008103504,0.000217571,0.00008866583,0.0001431107,0.000007532914,0.00009746387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9868345,"threshold_uncertainty_score":0.367378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1265306666725108,"score_gpt":0.3480644755262002,"score_spread":0.2215338088536894,"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."}}