{"id":"W1479686495","doi":"10.1109/crv.2015.33","title":"Latent SVM for Object Localization in Weakly Labeled Videos","year":2015,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba; Nvidia","keywords":"Computer science; Object (grammar); Artificial intelligence; Support vector machine; The Internet; Computer vision; Class (philosophy); Pattern recognition (psychology); Information retrieval; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003377418,0.00007323828,0.0000897091,0.00008969987,0.00004066613,0.00006455214,0.0003779018,0.00003983391,0.000006765078],"category_scores_gemma":[0.0001585485,0.00006529202,0.0000229151,0.0003764819,0.00001040618,0.0001785453,0.00008975205,0.00006464397,0.0001037917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006549902,"about_ca_system_score_gemma":0.00007303886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008607797,"about_ca_topic_score_gemma":0.0001725475,"domain_scores_codex":[0.9992405,0.00004270146,0.0001663944,0.0002514439,0.000136443,0.0001625559],"domain_scores_gemma":[0.9993652,0.00008094522,0.00004505315,0.0003233212,0.0001073758,0.00007808569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003397643,0.0004426891,0.08843295,0.00004191389,0.00002090884,0.000003473381,0.003051212,0.1971255,0.002377469,0.6325072,0.01320338,0.06275927],"study_design_scores_gemma":[0.0005179725,0.0000473119,0.007353975,0.000005296481,0.000001420239,0.000001318769,0.000009914116,0.9802842,0.0005945592,0.006063374,0.005026675,0.00009403514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01746062,0.00001669338,0.9767153,0.003160059,0.00008023136,0.0004040076,7.282898e-7,0.000221642,0.001940733],"genre_scores_gemma":[0.8919969,8.757071e-7,0.1069658,0.0005130284,0.00002462089,0.0001324948,0.000007063467,0.000007239827,0.0003520425],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8745362,"threshold_uncertainty_score":0.2662531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03551878154791596,"score_gpt":0.3047090166105915,"score_spread":0.2691902350626756,"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."}}