{"id":"W4402632374","doi":"10.1007/978-3-031-71602-7_17","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ericsson (Canada); École de Technologie Supérieure; Concordia University","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Computer vision; Object (grammar); Electrical engineering; Voltage","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":[0.000569563,0.0005172914,0.0004817164,0.0009990551,0.0002206233,0.0003858597,0.001779076,0.0002616525,0.00000788438],"category_scores_gemma":[0.00004313182,0.0005050046,0.0001604053,0.00140295,0.000447553,0.0006715289,0.0003379557,0.0006734555,0.00001889125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004776552,"about_ca_system_score_gemma":0.0005214466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000146189,"about_ca_topic_score_gemma":0.0001844175,"domain_scores_codex":[0.9963018,0.0000188336,0.0006476706,0.001724426,0.0005814801,0.0007257831],"domain_scores_gemma":[0.9982598,0.0006369193,0.0001352147,0.0006708928,0.00015592,0.0001412334],"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":[0.000008653525,0.00001883892,0.00001815247,0.0001081986,0.000009246601,0.00003197574,0.001011572,0.300603,0.0003489889,0.03916504,0.00002184281,0.6586545],"study_design_scores_gemma":[0.0002483556,0.00006661083,0.000007249601,0.0003673988,0.000006687592,0.00002399771,4.97676e-7,0.7443005,0.0009636328,0.2520694,0.001515331,0.00043032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003045634,0.0003937918,0.9934317,0.001980596,0.001027449,0.001265428,0.00001003034,0.0002577061,0.00160277],"genre_scores_gemma":[0.4553593,0.0001098145,0.5399998,0.003138046,0.0005578179,0.0002078838,0.00004017645,0.0001130952,0.0004741058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6582242,"threshold_uncertainty_score":0.9997402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02028710733145838,"score_gpt":0.2601601459871975,"score_spread":0.2398730386557391,"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."}}