{"id":"W4406518305","doi":"10.1016/j.patcog.2025.111358","title":"CoLo-CAM: Class activation mapping for object co-localization in weakly-labeled unconstrained videos","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Class (philosophy); Object (grammar); Artificial intelligence; Computer science; Computer vision; Pattern recognition (psychology)","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":[0.0001955631,0.0001670828,0.0001919254,0.0003794942,0.00008174342,0.00006071735,0.00005840247,0.0001669736,0.00004241196],"category_scores_gemma":[0.0001042611,0.0001987179,0.00005097988,0.0004297055,0.00001896749,0.0001732253,0.000006650932,0.0001141839,0.00002068477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002294033,"about_ca_system_score_gemma":0.00003503458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003411769,"about_ca_topic_score_gemma":0.0001161938,"domain_scores_codex":[0.9989783,0.00005523057,0.0003950046,0.0002241483,0.0001134996,0.0002337861],"domain_scores_gemma":[0.9994993,0.0001674536,0.00006322407,0.0001103087,0.0001270978,0.00003260922],"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":[0.0001478814,0.0002409,0.02003822,0.001857675,0.0001921502,0.000004619387,0.0008192884,0.3962873,0.1141804,0.0002973957,0.004783494,0.4611507],"study_design_scores_gemma":[0.001516529,0.00003895469,0.001874051,0.0004631262,0.00002491685,9.178055e-7,0.0001984031,0.9342495,0.05913697,0.001312709,0.000923132,0.0002608265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893445,0.0000137791,0.8076916,0.0001739051,0.0003098088,0.0007356687,0.00003896363,0.000195397,0.001496462],"genre_scores_gemma":[0.997049,0.00002960213,0.0007024942,0.000455512,0.00007426823,0.0001803998,0.001442684,0.00003243706,0.00003358192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8077046,"threshold_uncertainty_score":0.8103479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02192782903744666,"score_gpt":0.2482923283764304,"score_spread":0.2263644993389837,"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."}}