output
20142024
most citedNTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

1.8k citations

Showing 2019Show all

45 papers · 1 filter

cs.LG20191 cited

Which Channel to Ask My Question? Personalized Customer Service Request Stream Routing using Deep Reinforcement Learning

Zining Liu, Chong Long, Xiaolu Lu +3

Customer services are critical to all companies, as they may directly connect to the brand reputation. Due to a great number of customers, e-commerce companies often employ multipl…

cs.LG20191 cited

A New Ensemble Adversarial Attack Powered by Long-term Gradient Memories

Zhaohui Che, Ali Borji, Guangtao Zhai +3

Deep neural networks are vulnerable to adversarial attacks.

cs.CV20191 cited

Distribution Context Aware Loss for Person Re-identification

Zhigang Chang, Qin Zhou, Mingyang Yu +3

To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obta…

cs.CV2019

Learning To Characterize Adversarial Subspaces

Xiaofeng Mao, Yuefeng Chen, Yuhong Li +2

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially de…

cs.CL2019

Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce

Zhenxin Fu, Feng Ji, Wenpeng Hu +4

Information-seeking conversation system aims at satisfying the information needs of users through conversations. Text matching between a user query and a pre-collected question is…

cs.LG2019100 cited

Learning Disentangled Representations for Recommendation

Jianxin Ma, Chang Zhou, Peng Cui +2

User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangle…