{"id":"W2952745240","doi":"10.13016/m2dnjv-coqd","title":"Learning Aligned Cross-Modal Representations from Weakly Aligned Data","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Modalities; Modal; Modality (human–computer interaction); Representation (politics); Categorization; Convolutional neural network; Computer science; Artificial intelligence; Transfer of learning; Feature learning; Pattern recognition (psychology); Natural language processing","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":[0.001443124,0.001101423,0.0007629058,0.00140959,0.0004073507,0.001199968,0.001226756,0.00133591,0.003101833],"category_scores_gemma":[0.006089285,0.0004009784,0.001395751,0.001253957,0.000976023,0.004030364,0.002786764,0.002857637,0.001317449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006733416,"about_ca_system_score_gemma":0.0004375502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00187098,"about_ca_topic_score_gemma":0.002462652,"domain_scores_codex":[0.9991178,0.0002175072,0.00003858382,0.0004116772,0.00010534,0.0001091139],"domain_scores_gemma":[0.9980018,0.0006391469,0.0002361104,0.0007745484,0.0002404733,0.000107996],"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":[0.001464528,0.0009305725,0.0173197,0.0007958137,0.0006276101,0.0004894442,0.001039987,0.09464668,0.1201963,0.02078712,0.01852871,0.7231736],"study_design_scores_gemma":[0.00007634687,0.0005243867,0.01781819,0.0001301286,0.0002032134,0.0005834732,0.0009023024,0.8034546,0.03290328,0.1325365,0.01074148,0.0001261956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2027593,0.001316112,0.782337,0.00105284,0.0001844136,0.0001824422,0.003087904,0.003270469,0.005809532],"genre_scores_gemma":[0.8482942,0.0006184164,0.1399783,0.0005613361,0.0001457644,0.0001853426,0.006934313,0.0002104271,0.003072045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003101833,"threshold_uncertainty_score":0.01037663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1151145021947778,"score_gpt":0.2743072143804434,"score_spread":0.1591927121856656,"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."}}