{"id":"W7085164132","doi":"10.1109/tmm.2025.3618564","title":"Learning Efficient and Adaptive Cross-Channel Dependencies for Weakly-Supervised Object Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Infections and bacterial resistance","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Taishan Scholar Project of Shandong Province; Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Object detection; Convolution (computer science); Feature (linguistics); Focus (optics); Object (grammar); Pattern recognition (psychology); Code (set theory); Feature extraction","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":[0.0001103346,0.0001423121,0.0001146016,0.00009545414,0.0004199468,0.00004619751,0.00005393066,0.0001562875,0.000009147628],"category_scores_gemma":[0.00003974384,0.0001405605,0.0001003787,0.0001078716,0.00008885664,0.000005597882,0.00000207723,0.0001306888,0.000004033197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003244592,"about_ca_system_score_gemma":0.00005218617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003733013,"about_ca_topic_score_gemma":0.0002217934,"domain_scores_codex":[0.9992394,0.00003715946,0.0001485584,0.0003136952,0.0000690164,0.0001921235],"domain_scores_gemma":[0.9995932,0.00006430504,0.00003626783,0.0001291922,0.0001318926,0.00004516595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007732409,0.0001036055,0.0000239426,0.00002978551,0.00007904746,4.597342e-7,0.0001096579,0.0236399,0.9352658,0.00000524691,0.00001334016,0.03995592],"study_design_scores_gemma":[0.001059646,0.0005130957,0.0009129599,0.00002794407,0.00004281705,0.000003493144,0.0001782369,0.03951785,0.9563516,0.00001587614,0.001202427,0.0001740799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5172077,0.00005584855,0.4817218,0.00001335169,0.000560692,0.0002417657,0.00002769355,0.0000233195,0.0001477382],"genre_scores_gemma":[0.9971603,0.00008248221,0.0009733695,0.00003780872,0.00007495362,0.0001671584,0.00000890655,0.00001497622,0.001480016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4807485,"threshold_uncertainty_score":0.5731893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008559026826373104,"score_gpt":0.2574732485536368,"score_spread":0.2489142217272637,"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."}}