{"id":"W2123234527","doi":"10.1109/ism.2008.53","title":"Tiny Videos: Non-parametric Content-Based Video Retrieval and Recognition","year":2008,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Parametric statistics; Sampling (signal processing); Video retrieval; Similarity (geometry); Dimension (graph theory); Artificial intelligence; Scope (computer science); Computer vision; Range (aeronautics); Pattern recognition (psychology); Information retrieval; Image (mathematics); 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":[0.0003129156,0.0001162375,0.0001858121,0.0003278624,0.0001826024,0.0001218118,0.0002260425,0.00006963419,0.00005228227],"category_scores_gemma":[0.0002640804,0.00009904153,0.00007509261,0.001274317,0.00004558526,0.0005156289,0.00006535568,0.0000821785,0.00009612283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002722773,"about_ca_system_score_gemma":0.00005676292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001183565,"about_ca_topic_score_gemma":0.00001245525,"domain_scores_codex":[0.9988007,0.00006093179,0.0002789938,0.0003738976,0.0002984854,0.0001869751],"domain_scores_gemma":[0.9991274,0.0001536395,0.00009772534,0.0003051437,0.0002078608,0.0001082718],"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":[0.0006257616,0.001882992,0.17778,0.0002066079,0.0005250633,0.0004665338,0.002144438,0.001067837,0.05659304,0.009581926,0.02877395,0.7203519],"study_design_scores_gemma":[0.002004948,0.0003905209,0.06892926,0.00004053282,0.00005077466,0.00005188466,0.00006326033,0.880819,0.04468536,0.001335136,0.001036819,0.000592511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3025393,0.00006676249,0.6952357,0.0005112427,0.00009353465,0.00010735,0.000001383303,0.0001018356,0.001342973],"genre_scores_gemma":[0.9643774,0.00006880098,0.03366026,0.0011429,0.00003783774,0.000003940914,0.00001800231,0.000006472963,0.0006844021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8797511,"threshold_uncertainty_score":0.4038796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05421736019771699,"score_gpt":0.2261857836904432,"score_spread":0.1719684234927262,"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."}}