{"id":"W3197746894","doi":"10.1109/tmm.2021.3066118","title":"A Discriminative Vectorial Framework for Multi-Modal Feature Representation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Discriminative model; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Modal; Feature learning; Representation (politics); Feature extraction; 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":[0.00007137961,0.0001807297,0.0001979748,0.0001005648,0.000217478,0.0001043896,0.0003055021,0.0001726271,0.00001907585],"category_scores_gemma":[0.0001819198,0.0001746482,0.0001873251,0.000497353,0.00005333797,0.0006051594,0.000004279763,0.000384212,0.00001804571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007952858,"about_ca_system_score_gemma":0.00008679595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008480394,"about_ca_topic_score_gemma":0.00001178986,"domain_scores_codex":[0.9986917,0.00007598099,0.0001798476,0.0005382988,0.0002527386,0.0002613869],"domain_scores_gemma":[0.9984511,0.0005945999,0.00007446393,0.0004976203,0.0002790133,0.0001031875],"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":[0.0002378579,0.0009260616,0.00001003948,0.00004633681,0.0001152514,0.00006803168,0.004656995,0.0006398195,0.03307114,0.00433895,0.001135622,0.9547539],"study_design_scores_gemma":[0.001022674,0.0001806139,0.0001764013,0.0000624707,0.00003150771,0.00001123265,0.0001322668,0.07258365,0.9169207,0.007207364,0.001391963,0.0002791672],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001948341,0.00006558278,0.9958653,0.0007360739,0.002271102,0.0004300966,0.00005475768,0.0003458203,0.00003644269],"genre_scores_gemma":[0.09307202,0.00007716423,0.9055761,0.0001924731,0.0002304632,0.0001907888,0.00001072022,0.00002049241,0.0006298273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9544747,"threshold_uncertainty_score":0.7121945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06014157342650117,"score_gpt":0.3740701604246917,"score_spread":0.3139285869981905,"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."}}