{"id":"W2962849746","doi":"10.24963/ijcai.2017/425","title":"Deep Descriptor Transforming for Image Co-Localization","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China; University of Adelaide","keywords":"Convolutional neural network; Robustness (evolution); Artificial intelligence; Computer science; Margin (machine learning); Benchmark (surveying); Pattern recognition (psychology); Feature extraction; Generalization; Deep learning; Image (mathematics); Feature (linguistics); Set (abstract data type); Object detection; Machine learning; Computer vision; 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":[0.0001521254,0.00008438721,0.00009591244,0.00003704195,0.0005127694,0.0003945171,0.0007516187,0.00003819593,0.0000108407],"category_scores_gemma":[0.0001222983,0.0000721567,0.00005785938,0.00003751338,0.00004856144,0.002285538,0.00004978292,0.00003829164,0.00001077783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002263483,"about_ca_system_score_gemma":0.00001740656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009820767,"about_ca_topic_score_gemma":0.000006212627,"domain_scores_codex":[0.9993619,0.000006797386,0.0001283804,0.0002140329,0.0001017345,0.0001871808],"domain_scores_gemma":[0.9992356,0.0000280785,0.00006550066,0.0005213313,0.00009892072,0.00005051336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001845719,0.00004511362,0.0001983586,0.00005265977,0.00001050574,0.000008468531,0.0003779791,0.000005691729,0.03132308,0.1215374,0.003572532,0.8428497],"study_design_scores_gemma":[0.0003194968,0.0001052845,0.00009273467,0.00001529491,0.000003915408,0.000005684273,0.00001389649,0.1088519,0.8081366,0.02714038,0.05513594,0.0001788272],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004862782,0.00003425349,0.9904436,0.0003249336,0.00009866979,0.0002986554,0.000001146972,0.0003050248,0.008445121],"genre_scores_gemma":[0.1426116,0.00005200479,0.8560327,0.0004397886,0.00006594708,0.00004449491,0.000003506323,0.00001191543,0.0007380078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8426709,"threshold_uncertainty_score":0.394386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03218489846885022,"score_gpt":0.3401778789690577,"score_spread":0.3079929805002075,"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."}}