{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007414395,0.0010046,0.0009278759,0.001073798,0.000263656,0.001018643,0.001730201,0.0009868259,0.002808043],"category_scores_gemma":[0.002457796,0.0004276792,0.0008470567,0.001433027,0.0007003355,0.00199139,0.001743476,0.001857718,0.001491293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040276,"about_ca_system_score_gemma":0.001415584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005914732,"about_ca_topic_score_gemma":0.00614446,"domain_scores_codex":[0.9995252,0.00006327911,0.0000283463,0.0001587481,0.0001524399,0.00007208996],"domain_scores_gemma":[0.9992821,0.0001451635,0.0000935953,0.0002954591,0.0001433303,0.00004039698],"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":[0.0001583664,0.0001214377,0.001626593,0.0002092887,0.0001358649,0.0001373163,0.00009107403,0.2637685,0.03416453,0.03081005,0.007066828,0.6617102],"study_design_scores_gemma":[0.000008337157,0.0000434369,0.0002169607,0.000008632559,0.00001892287,0.00006558344,0.00001598322,0.9708279,0.01512201,0.01050617,0.003152605,0.00001364047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006086998,0.0002842027,0.9913387,0.00007715738,0.00002941008,0.00002374108,0.00008933665,0.00146082,0.0006095979],"genre_scores_gemma":[0.509442,0.0009080148,0.4817649,0.000269586,0.00007656663,0.0001777678,0.001396116,0.0003863988,0.005578565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005914732,"threshold_uncertainty_score":0.01176059,"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."}}