{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001438612,0.0002198218,0.0002928567,0.0002797194,0.0003333049,0.0001408871,0.003792818,0.00005184806,0.0002373109],"category_scores_gemma":[0.0007432603,0.0001849174,0.0001571977,0.0008305204,0.0002065114,0.000387788,0.00152816,0.0005343712,0.00002008647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252312,"about_ca_system_score_gemma":0.0001366588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001988351,"about_ca_topic_score_gemma":0.0000805459,"domain_scores_codex":[0.9970998,0.00006994529,0.0008302303,0.000557697,0.001189873,0.000252476],"domain_scores_gemma":[0.9973458,0.0002625229,0.0008364739,0.0004417466,0.001037119,0.00007636206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001138495,0.0004937642,0.0008779544,0.00002668179,0.00004359282,5.121116e-7,0.004407074,0.01824323,0.01855159,0.9407126,0.0001370585,0.01639207],"study_design_scores_gemma":[0.00005685314,0.0002122189,0.01801511,0.00009044784,0.000006923699,0.000007574803,0.0004266881,0.8683635,0.02715075,0.08542056,0.00004281114,0.0002065563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7610486,0.00005234881,0.1949646,0.01877477,0.001392664,0.00138333,0.0002346389,0.0002895969,0.02185937],"genre_scores_gemma":[0.9951455,0.000009845175,0.004325453,0.0001707131,0.00003273653,0.0001095392,0.000007494324,0.00001629149,0.0001824262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8552921,"threshold_uncertainty_score":0.7540712,"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."}}