{"id":"W1947746128","doi":"10.1109/cvpr.2015.7298875","title":"Visual recognition by counting instances: A multi-instance cardinality potential kernel","year":2015,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"ENCODE; Computer science; Cardinality (data modeling); Automatic summarization; Event (particle physics); Ambiguity; Kernel (algebra); Artificial intelligence; Activity recognition; Clutter; Internet video; Pattern recognition (psychology); Relation (database); Machine learning; The Internet; Data mining; 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":[0.0004280735,0.000139535,0.0001498168,0.00006452136,0.0001523433,0.0002702015,0.0002560122,0.0000727818,0.00004544709],"category_scores_gemma":[0.00004429666,0.000135006,0.000067268,0.0002519604,0.00003797144,0.001411327,0.0000751163,0.0001369886,0.0004006643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009467102,"about_ca_system_score_gemma":0.00007921056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001383412,"about_ca_topic_score_gemma":0.00005304901,"domain_scores_codex":[0.9986067,0.00008747041,0.0002630703,0.0003994458,0.0003811141,0.0002621946],"domain_scores_gemma":[0.9992076,0.00001893572,0.0001250562,0.0001879474,0.0003100992,0.0001503623],"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":[0.0001567382,0.001784344,0.002476126,0.0001253378,0.0001954905,0.0001988043,0.003044795,0.0001335233,0.01692362,0.004176504,0.09216879,0.8786159],"study_design_scores_gemma":[0.01615633,0.001012365,0.005596497,0.0004266966,0.0001374202,0.0003403231,0.004437129,0.7197637,0.0926083,0.02834217,0.1270451,0.004133937],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830994,0.00008849795,0.8065682,0.0001633863,0.0005953996,0.0001379664,0.00001272868,0.0003474597,0.008986997],"genre_scores_gemma":[0.9809759,0.00002048467,0.01742329,0.0006580661,0.0001462141,0.00001901275,0.00004096028,0.000009082026,0.0007069891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.874482,"threshold_uncertainty_score":0.5505385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05171560923527599,"score_gpt":0.2858088036242283,"score_spread":0.2340931943889523,"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."}}