10 citations · 23 across the 5 of their papers we have counts for
5 papers
ReFormer: The Relational Transformer for Image Captioning
Xuewen Yang, Yingru Liu, Xin Wang
Image captioning is shown to be able to achieve a better performance by using scene graphs to represent the relations of objects in the image. The current captioning encoders gener…
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
Xuewen Yang, Heming Zhang, Di Jin +6
Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides th…
Learning Continuous-Time Dynamics by Stochastic Differential Networks
Yingru Liu, Yucheng Xing, Xuewen Yang +4
Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and d…
Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
Yingru Liu, Xuewen Yang, Dongliang Xie +4
Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still…
Latent Part-of-Speech Sequences for Neural Machine Translation
Xuewen Yang, Yingru Liu, Dongliang Xie +2
Learning target side syntactic structure has been shown to improve Neural Machine Translation (NMT). However, incorporating syntax through latent variables introduces additional co…