{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002318571,0.0001401952,0.0001225906,0.0002263744,0.0002909671,0.0002497386,0.0001777016,0.00009421381,0.0001626779],"category_scores_gemma":[0.00002796292,0.0001372146,0.0001141804,0.0002053109,0.00001288483,0.001263462,0.0000223936,0.0001190982,0.0001131918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001033606,"about_ca_system_score_gemma":0.00002332166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006910173,"about_ca_topic_score_gemma":0.0007485723,"domain_scores_codex":[0.9989856,0.00004398837,0.0002773922,0.0003523951,0.000133288,0.0002072598],"domain_scores_gemma":[0.9993699,0.00001970432,0.0001346736,0.0002061284,0.0001925501,0.0000770226],"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":[0.00003037611,0.0001302819,0.000006772305,0.00001250421,0.000009555541,0.00000142078,0.0001134596,0.000007412713,0.007692695,0.003303383,0.0011318,0.9875603],"study_design_scores_gemma":[0.002651803,0.003039601,0.007837514,0.0001232878,0.00005036944,0.0001089192,0.000269101,0.04696206,0.5730616,0.3536315,0.01125352,0.001010681],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1628963,0.000002995475,0.8317634,0.0009117725,0.000408284,0.0003384094,0.000003404534,0.0004264931,0.003248886],"genre_scores_gemma":[0.9813486,0.000004113208,0.01720777,0.000639202,0.0003052156,0.00004830138,0.0001078713,0.000008010568,0.0003309623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9865497,"threshold_uncertainty_score":0.5595449,"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."}}