{"id":"W2099083873","doi":"10.1109/crv.2009.44","title":"Towards a Robust Spatio-Temporal Interest Point Detection for Human Action Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Blob detection; Artificial intelligence; Computer science; Scale space; Feature extraction; Pattern recognition (psychology); Salient; Computer vision; Feature (linguistics); Gaussian; Representation (politics); Scale (ratio); Image (mathematics); Edge detection; Image processing; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00131565,0.0007199932,0.001029886,0.001377095,0.0002728101,0.0009341429,0.00176004,0.001568293,0.001513226],"category_scores_gemma":[0.002933855,0.0004953303,0.001040726,0.001049478,0.0007057052,0.001420374,0.0009976375,0.0009866257,0.001561124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005648063,"about_ca_system_score_gemma":0.0006012883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002663578,"about_ca_topic_score_gemma":0.002846551,"domain_scores_codex":[0.9991395,0.0001703592,0.00005079856,0.0002745238,0.000286832,0.00007800898],"domain_scores_gemma":[0.9991285,0.000257489,0.00009286958,0.0001484318,0.0003181941,0.00005439683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003601236,0.0002325378,0.0009967571,0.0001912623,0.0001158967,0.0002386858,0.0001599489,0.06092266,0.1783434,0.01191479,0.005539736,0.7409842],"study_design_scores_gemma":[0.00001185641,0.00007391562,0.0007819947,0.000007106697,0.00001677379,0.0001187973,0.00002573572,0.9746057,0.01912997,0.003800765,0.001411998,0.00001530584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004043623,0.000122744,0.9949215,0.00005145345,0.00001567617,0.00002687526,0.00004101272,0.0006060207,0.0001710825],"genre_scores_gemma":[0.1273479,0.000286418,0.8696541,0.0001287346,0.00007916205,0.0001323803,0.0002945735,0.0001122494,0.001964564],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002663578,"threshold_uncertainty_score":0.006957948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1219126969658045,"score_gpt":0.3103394603783271,"score_spread":0.1884267634125226,"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."}}