TY - JOUR
AU - 
TI - VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs
JF - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DO - 10.1109/cvpr46437.2021.00693
DA - 2021-06-01
UR - https://www.deepdyve.com/lp/unpaywall/vx2text-end-to-end-learning-of-video-based-text-generation-from-2aE3CdODn3
DP - DeepDyve
ER -