{"id":"W4225683910","doi":"10.24963/ijcai.2022/762","title":"A Survey of Vision-Language Pre-Trained Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Transformer; Pace; Artificial intelligence; Pointer (user interface); Deep learning; Mainstream; Focus (optics); Natural language processing; Human–computer interaction; Engineering","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":[0.001112483,0.00180739,0.001107363,0.0009548017,0.0003706911,0.001361325,0.002836398,0.001513078,0.00615347],"category_scores_gemma":[0.00495107,0.0007291263,0.001216061,0.001214283,0.0005826692,0.002801838,0.001192425,0.002779372,0.004400886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270409,"about_ca_system_score_gemma":0.00178525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009325035,"about_ca_topic_score_gemma":0.01037677,"domain_scores_codex":[0.9994023,0.000159916,0.00004790814,0.00020034,0.000125356,0.00006427346],"domain_scores_gemma":[0.9988536,0.0005908572,0.00003728526,0.0001851892,0.0002844863,0.00004861296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001654917,0.0001657319,0.001556014,0.0009282778,0.000168342,0.0001124103,0.0001432177,0.07835431,0.004425691,0.01390773,0.02521205,0.8748607],"study_design_scores_gemma":[0.00002702603,0.0003483755,0.001583101,0.0006960859,0.0001717221,0.0003258375,0.0001305683,0.8869478,0.01116733,0.02512463,0.07339535,0.00008217558],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01597613,0.07578043,0.8786578,0.002837071,0.0009339406,0.0001945984,0.001103144,0.007855053,0.0166619],"genre_scores_gemma":[0.3618589,0.08828411,0.4787536,0.004141655,0.00163568,0.0007813876,0.01187052,0.002454492,0.0502197],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009325035,"threshold_uncertainty_score":0.02058542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06806887872685286,"score_gpt":0.3226548770219884,"score_spread":0.2545859982951356,"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."}}