{"id":"W2953060102","doi":"10.48550/arxiv.1502.02063","title":"Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"ENCODE; Cardinality (data modeling); Computer science; Automatic summarization; Event (particle physics); Ambiguity; Kernel (algebra); Artificial intelligence; Activity recognition; Internet video; Clutter; Pattern recognition (psychology); Machine learning; The Internet; Data mining; Mathematics; Combinatorics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005051755,0.0003853986,0.0004028161,0.0002131183,0.0002868731,0.0003193249,0.0009421281,0.0003733953,0.0000400743],"category_scores_gemma":[0.00004295815,0.000480258,0.0002472209,0.0004726902,0.0001169031,0.001155053,0.0007856474,0.000726142,0.0002694859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004659263,"about_ca_system_score_gemma":0.0002919308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002849378,"about_ca_topic_score_gemma":0.00009417626,"domain_scores_codex":[0.9974514,0.000249755,0.0003261175,0.001323341,0.0002200967,0.0004292463],"domain_scores_gemma":[0.998,0.00003781692,0.0004960243,0.0006156843,0.0006216976,0.0002288039],"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":[0.003051274,0.01571587,0.02411142,0.00624767,0.006734245,0.01748051,0.01362052,0.3249394,0.01149641,0.06790859,0.1353476,0.3733464],"study_design_scores_gemma":[0.002945968,0.0001355046,0.0007705255,0.0004976987,0.0002345634,0.00002727029,0.0005159195,0.9478866,0.001074948,0.04017851,0.003950937,0.001781593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4088986,0.00009641294,0.5875567,0.00002957882,0.00088709,0.0002561044,0.0001046839,0.0003342976,0.001836502],"genre_scores_gemma":[0.9967487,0.0002217447,0.001600991,0.0001511406,0.0001833104,0.000003160865,0.0002171748,0.00002265107,0.0008510817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6229472,"threshold_uncertainty_score":0.9997649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1035648681886287,"score_gpt":0.2200513824284257,"score_spread":0.116486514239797,"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."}}