DynIBaR: Space-time view synthesis from videos of dynamic scenes
RO-ViT: Region-aware pre-training for open-vocabulary object detection with vision transformers
Pic2Word: Mapping pictures to words for zero-shot composed image retrieval
Unifying image-caption and image-classification datasets with prefix conditioning
Google at CVPR 2023
Enabling delightful user experiences via predictive models of human attention
Sparse video tubes for joint video and image vision transformers
Vid2Seq: a pretrained visual language model for describing multi-event videos
View Synthesis with Transformers
LOLNeRF: Learn from One Look
Revisiting Mask Transformer from a Clustering Perspective
