{"id":"W4321368497","doi":"10.1016/j.asoc.2023.110136","title":"End-to-end learning of representations for instance-level document image retrieval","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Image retrieval; Automatic image annotation; Artificial intelligence; Image (mathematics); Visual Word; Pattern recognition (psychology); Ranking (information retrieval); Feature detection (computer vision); Matching (statistics); Representation (politics); Document retrieval; Learning to rank; Image processing; 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":[0.00090791,0.0001431256,0.0002229025,0.0002292309,0.0003171007,0.0001346154,0.000651873,0.00005593535,0.000007935814],"category_scores_gemma":[0.0002626477,0.0001503534,0.00008811292,0.00147818,0.0000584764,0.0001762428,0.0004189757,0.0001625341,0.00004272673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005707111,"about_ca_system_score_gemma":0.00007938268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001002607,"about_ca_topic_score_gemma":5.583022e-7,"domain_scores_codex":[0.9982863,0.00003792075,0.000454978,0.0004846647,0.0003821925,0.0003539624],"domain_scores_gemma":[0.9984452,0.0005947101,0.0002360436,0.0004261198,0.000212999,0.00008491174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005448862,0.00006339955,0.0002224161,0.0001179121,0.00004941989,0.000004639497,0.003777718,0.001082675,0.3157264,0.3974018,0.001423854,0.2800752],"study_design_scores_gemma":[0.001029004,0.0001967376,0.01003676,0.0000998791,0.00002265765,0.000005968155,0.0009549535,0.1659545,0.784777,0.02655066,0.0097276,0.0006441767],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0101954,0.00001145328,0.9859329,0.000610431,0.0001261806,0.0005379533,0.000005615098,0.0008068357,0.001773249],"genre_scores_gemma":[0.7049283,0.000005379672,0.2944807,0.0001110573,0.00005302713,0.00002557991,0.00001746849,0.00001513111,0.000363342],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.694733,"threshold_uncertainty_score":0.6131235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03666415697909401,"score_gpt":0.3139962661019693,"score_spread":0.2773321091228753,"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."}}