no code implementations • CVPR 2023 • Yushi Yao, Chang Ye, Junfeng He, Gamaleldin F. Elsayed
We then traina model with a primary contrastive objective; to this stan-dard configuration, we add a simple output head trained topredict the attentional map for each image, guided by thepseudo labels from teacher model.
no code implementations • 12 Dec 2016 • Yushi Yao, Guangjian Li
Because of its great performance in representing inter-word relation, we use sentiment word vectors to identify the special words.
no code implementations • 16 Feb 2016 • Yushi Yao, Zheng Huang
Recurrent neural network(RNN) has been broadly applied to natural language processing(NLP) problems.