{"id":"W2155292833","doi":"10.48550/arxiv.1511.02793","title":"Generating Images from Captions with Attention","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Artificial intelligence; Generative model; Baseline (sea); Image (mathematics); Natural language processing; Training set; Natural (archaeology); Natural language generation; Machine learning; Natural language; Geography","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":[0.0008551939,0.001620203,0.0008777476,0.001102973,0.0004199749,0.001520359,0.002007437,0.001855022,0.007350286],"category_scores_gemma":[0.004877069,0.0008504032,0.001546579,0.0008809328,0.0009918096,0.001714842,0.00124084,0.001974232,0.002568982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001322486,"about_ca_system_score_gemma":0.000680993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005442805,"about_ca_topic_score_gemma":0.007964741,"domain_scores_codex":[0.9993879,0.0001801995,0.00002080622,0.0002344615,0.0001134144,0.00006321612],"domain_scores_gemma":[0.9985307,0.0008035674,0.00007936668,0.0003247025,0.0001885055,0.00007300133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005438644,0.0003059361,0.00194874,0.0006642641,0.0001837024,0.000775437,0.0005881962,0.4984543,0.03407443,0.03621093,0.05496244,0.3712878],"study_design_scores_gemma":[0.00003633535,0.0000458284,0.000208933,0.00002332752,0.00002026317,0.000175954,0.00003079063,0.9753677,0.007032532,0.01217546,0.00486477,0.00001806924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03654676,0.0013538,0.9371267,0.001006603,0.0003241522,0.0004299007,0.001371709,0.01154306,0.01029733],"genre_scores_gemma":[0.5303128,0.001092924,0.4418806,0.001238875,0.0003118795,0.0006369305,0.006775067,0.002306337,0.01544465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007350286,"threshold_uncertainty_score":0.02458918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06370869466700849,"score_gpt":0.2035532282945449,"score_spread":0.1398445336275364,"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."}}