{"id":"W2546190447","doi":"10.1109/tpami.2017.2753232","title":"Cross-Modal Scene Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Modalities; Computer science; Modality (human–computer interaction); Modal; Representation (politics); Convolutional neural network; Categorization; Artificial intelligence; Transfer of learning; Machine learning","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":[0.0002393409,0.0002162821,0.0002963184,0.0002547564,0.000810881,0.0007403744,0.001041829,0.00007885963,0.00009488993],"category_scores_gemma":[0.00001021789,0.0001857747,0.0002524807,0.0003634866,0.0001668553,0.0007813343,0.00001812285,0.0003119395,0.00001764074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002335244,"about_ca_system_score_gemma":0.00001151039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006541167,"about_ca_topic_score_gemma":0.000319018,"domain_scores_codex":[0.9986029,0.00003717603,0.0003032378,0.0005613476,0.0002203171,0.000275037],"domain_scores_gemma":[0.9983216,0.00007320665,0.0001717453,0.001198501,0.0000966783,0.0001382643],"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":[0.00000826635,0.00006210236,0.002018455,0.000004261367,0.0001518912,0.00001488724,0.00003451659,0.006940168,0.00007537163,0.00008257071,0.000003452116,0.990604],"study_design_scores_gemma":[0.0001194123,0.0001781554,0.01241559,0.00002923775,0.0002196313,0.00001567261,0.000004903559,0.5647153,0.4204685,0.001176516,0.0002259045,0.0004311891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008675825,0.0001383056,0.9980817,0.0002614403,0.0002016393,0.00009393277,0.00001314129,0.0001497817,0.0001924955],"genre_scores_gemma":[0.9919434,0.0009458172,0.006233258,0.0003450215,0.0000344723,0.00001403597,0.00000158234,0.00001038263,0.0004720704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9918484,"threshold_uncertainty_score":0.7575671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02595754722131622,"score_gpt":0.3300448087055881,"score_spread":0.3040872614842719,"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."}}