Skip to content
conftrace_

vision-language pre-training

152 papers

Explore in graph

Also known as

VLPT VLPRET VL PRE-TRAINING

Co-occurring keywords · papers mentioning both

multimodal learning (54) contrastive learning (41) vision-language model (26) cross-modal alignment (20) zero-shot learning (18) image-text retrieval (16) image captioning (15) medical imaging (15) masked language modeling (13) image-text alignment (12)

Papers

EViLBERT: Learning Task-Agnostic Multimodal Sense Embeddings IJCAI 2020 Unified Vision-Language Pre-Training for Image Captioning and VQA AAAI 2020