{"id":"openalex:W2970608575","kind":"article","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","authors":["Jiasen Lu","Dhruv Batra","Devi Parikh","Stefan Lee"],"author_count":4,"year":2019,"published":"2019-08-06","venue":"neural information processing systems","cited_by":772,"doi":null,"arxiv_id":null,"nct_id":null,"source_url":"https://papers.nips.cc/paper/8297-vilbert-pretraining-task-agnostic-visiolinguistic-representations-for-vision-and-language-tasks.pdf","archive_url":"https://space-kitty.com/papers/openalex:W2970608575","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2970608575","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Multimodal Machine Learning Applications"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"llm-architectures","name":"LLM Architectures & Pretraining","domain_slug":"ai"}],"cited_in_dossiers":[]}