activity
20132023
most citedJointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification

40 citations · 278 across the 25 of their papers we have counts for

collaborators
Showing 2019Show all

14 papers · 1 filter

cs.CL2019

Discourse-Aware Neural Extractive Text Summarization

Jiacheng Xu, Zhe Gan, Yu Cheng +1

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninforma…

cs.CL2019

FreeLB: Enhanced Adversarial Training for Natural Language Understanding

Chen Zhu, Yu Cheng, Zhe Gan +3

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In…

cs.CL2019

What Makes A Good Story? Designing Composite Rewards for Visual Storytelling

Junjie Hu, Yu Cheng, Zhe Gan +3

Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr. In this paper, we re-examine this problem from a different angle, b…

cs.LG2019

Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation

Shuyang Dai, Yu Cheng, Yizhe Zhang +3

Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order…

cs.CV2019

Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs

Zhikang Zou, Yu Cheng, Xiaoye Qu +3

Crowd counting is a challenging task due to the large variations in crowd distributions. Previous methods tend to tackle the whole image with a single fixed structure, which is una…

cs.CL2019

Domain Adaptive Text Style Transfer

Dianqi Li, Yizhe Zhang, Zhe Gan +4

Text style transfer without parallel data has achieved some practical success. However, in the scenario where less data is available, these methods may yield poor performance. In t…