{"id":"W4385899901","doi":"10.1109/iscas46773.2023.10182225","title":"Improving Deep Features for Image Retrieval Using Multi-Source Spatial Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Residual; Feature (linguistics); Convolutional neural network; Pattern recognition (psychology); Feature extraction; Block (permutation group theory); Convolution (computer science); Deep learning; Spatial analysis; Abstraction; Artificial neural network; Algorithm; Remote sensing; Mathematics","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":[0.0003230896,0.0001371923,0.0001322984,0.0002098119,0.0002156498,0.0003178062,0.0004546325,0.00007930573,0.000003974939],"category_scores_gemma":[0.0004988736,0.0001222461,0.0000838131,0.0006159774,0.00002970898,0.002811316,0.0003060205,0.000113463,0.00002998595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005707911,"about_ca_system_score_gemma":0.0000438217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001477776,"about_ca_topic_score_gemma":0.000008655671,"domain_scores_codex":[0.9989659,0.00001873113,0.0002460468,0.0002210582,0.0002134874,0.0003348219],"domain_scores_gemma":[0.999171,0.0001080539,0.0001252434,0.0003265812,0.0002034219,0.00006567169],"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":[0.0000704404,0.00002670217,0.00005927527,0.0001173741,0.00001490181,0.000007864654,0.0009713229,0.0002119256,0.1594825,0.001779517,0.0006983869,0.8365598],"study_design_scores_gemma":[0.0003533305,0.0000697018,0.0002701558,0.00000950305,0.000004322221,0.00001024085,0.00005845488,0.6212873,0.3743242,0.0006198386,0.002815405,0.0001774755],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001420425,0.00002011511,0.9963396,0.0001189156,0.0001827988,0.0004233178,0.000004069661,0.001389332,0.0001014359],"genre_scores_gemma":[0.03522482,0.00001058684,0.9638541,0.0003611932,0.00009968896,0.000006616106,0.00001899118,0.00001451139,0.000409498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8363823,"threshold_uncertainty_score":0.4985053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02305549250836249,"score_gpt":0.3068681358403355,"score_spread":0.283812643331973,"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."}}