1.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Tsinghua UniversityCN67 papers
- Tsinghua–Berkeley Shenzhen InstituteCN23 papers
- Harbin Institute of TechnologyCN10 papers
- Peng Cheng LaboratoryCN6 papers
- University College LondonGB5 papers
- Chinese Academy of SciencesCN4 papers
- Hong Kong University of Science and TechnologyHK4 papers
- Peking UniversityCN4 papers
- University of California San DiegoUS4 papers
- Collaborative Innovation Center of Quantum MatterCN3 papers
- Nankai UniversityCN3 papers
- Shandong UniversityCN3 papers
14 papers · 1 filter
Match4Rec: A Novel Recommendation Algorithm Based on Bidirectional Encoder Representation with the Matching Task
Lingxiao Zhang, Jiangpeng Yan, Yujiu Yang +1
Characterizing users' interests accurately plays a significant role in an effective recommender system. The sequential recommender system can learn powerful hidden representations…
Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
Tiankuang Zhou, Xing Lin, Jiamin Wu +7
Application-specific optical processors have been considered disruptive technologies for modern computing that can fundamentally accelerate the development of artificial intelligen…
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
Yiyang Zhang, Feng Liu, Zhen Fang +3
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain…
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng +5
Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is…
Prior knowledge distillation based on financial time series
Jie Fang, Jianwu Lin
One of the major characteristics of financial time series is that they contain a large amount of non-stationary noise, which is challenging for deep neural networks. People normall…
Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration
Ming Zhang, Yawei Wang, Xiaoteng Ma +4
The generative adversarial imitation learning (GAIL) has provided an adversarial learning framework for imitating expert policy from demonstrations in high-dimensional continuous t…
Rethinking the Trigger of Backdoor Attack
Yiming Li, Tongqing Zhai, Baoyuan Wu +3
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden bac…
OODT: Obstacle Aware Opportunistic Data Transmission for Cognitive Radio Ad Hoc Networks
Xiaoxiong Zhong, Li Li, Yuanping Zhang +3
In recent years, a large number of smart devices will be connected in Internet of Things (IoT) using an ad hoc network, which needs more frequency spectra. The cognitive radio (CR)…
CL-ADMM: A Cooperative Learning Based Optimization Framework for Resource Management in MEC
Xiaoxiong Zhong, Xinghan Wang, Li Li +5
We consider the problem of intelligent and efficient resource management framework in mobile edge computing (MEC), which can reduce delay and energy consumption, featuring distribu…
Real-MFF: A Large Realistic Multi-focus Image Dataset with Ground Truth
Juncheng Zhang, Qingmin Liao, Shaojun Liu +3
Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently…
MQA: Answering the Question via Robotic Manipulation
Yuhong Deng, Di Guo, Xiaofeng Guo +3
In this paper, we propose a novel task, Manipulation Question Answering (MQA), where the robot performs manipulation actions to change the environment in order to answer a given qu…
Flexo-diffusion effect: the strong influence on lithium diffusion induced by strain gradient
Gao Xu, Feng Hao, Mouyi Weng +3
Lithium ion batteries (LIBs) work under sophisticated external force field and its electrochemical properties could be modulated by strain. Owing to the electro-mechanical coupling…
Neural Architecture Search for Compressed Sensing Magnetic Resonance Image Reconstruction
Jiangpeng Yan, Shuo Chen, Yongbing Zhang +1
Recent works have demonstrated that deep learning (DL) based compressed sensing (CS) implementation can accelerate Magnetic Resonance (MR) Imaging by reconstructing MR images from…
Reed-Muller Codes: Theory and Algorithms
Emmanuel Abbe, Amir Shpilka, Min Ye
Reed-Muller (RM) codes are among the oldest, simplest and perhaps most ubiquitous family of codes. They are used in many areas of coding theory in both electrical engineering and c…