Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation.
By introducing a new operator for IFVs via the linear order based on a score function and an accuracy function, we present that such an operator is a strong negation on IFVs.
Given the significant amount of time people spend in vehicles, health issues under driving condition have become a major concern.
Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user.
In this work, a new causal U-net based multiple-in-multiple-out structure is proposed for real-time multi-channel speech enhancement.
By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with non-sparse FL.
Besides, MetaHeac has been successfully deployed in WeChat for the promotion of both contents and advertisements, leading to great improvement in the quality of marketing.
With the advantage of meta learning which has good generalization ability to novel tasks, we propose a transfer-meta framework for CDR (TMCDR) which has a transfer stage and a meta stage.
The cold item ID embedding has two main problems: (1) A gap is existing between the cold ID embedding and the deep model.
Based on venture capitalists' understanding of future preferences, we consider four types of venture capitalists, namely time-consistent venture capitalists, venture capitalists who only realize critical time point inconsistency, naive venture capitalists and sophisticated venture capitalists, of which the latter three are time-inconsistent.
no code implementations • 11 Mar 2021 • Xingyu Jiang, Mingyang Qin, Xinjian Wei, Zhongpei Feng, Jiezun Ke, Haipeng Zhu, Fucong Chen, Liping Zhang, Li Xu, Xu Zhang, Ruozhou Zhang, Zhongxu Wei, Peiyu Xiong, Qimei Liang, Chuanying Xi, Zhaosheng Wang, Jie Yuan, Beiyi Zhu, Kun Jiang, Ming Yang, Junfeng Wang, Jiangping Hu, Tao Xiang, Brigitte Leridon, Rong Yu, Qihong Chen, Kui Jin, Zhongxian Zhao
Iron selenide (FeSe) - the structurally simplest iron-based superconductor, has attracted tremendous interest in the past years.
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning Social and Information Networks
Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem.
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.
The current methods for the link prediction taskhavetwonaturalproblems:1)the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations.
MLBF-Net is composed of three components: 1) multiple lead-specific branches for learning the diversity of multi-lead ECG; 2) cross-lead features fusion by concatenating the output feature maps of all branches for learning the integrity of multi-lead ECG; 3) multi-loss co-optimization for all the individual branches and the concatenated network.
For points that belong to the same roof shape, a multi-cue, hierarchical RANSAC approach is proposed for efficient and reliable segmenting and reconstructing the building point cloud.
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem.
By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.
Recently, deep learning models play more and more important roles in contents recommender systems.
In this paper, it is the first time to discuss the difficulty without support of old classes in class incremental learning, which is called as softmax suppression problem.
This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space.
By means of a new global Carleman estimate, we establish the exact controllability of our stochastic wave equation with three controls.
Optimization and Control 93B05, 60H15, 93B07, 35B45
An emerging approach for conducting such assessments in the United States is through the US Road Assessment Program (usRAP), which rates roads from highest risk (1 star) to lowest (5 stars).
To investigate whether and to what extent central serous chorioretinopathy (CSC) depicted on color fundus photographs can be assessed using deep learning technology.
It is a longstanding unsolved problem to characterize the optimal feedbacks for general SLQs (i. e., stochastic linear quadratic control problems) with random coefficients in infinite dimensions; while the same problem but in finite dimensions was just addressed in a recent work .
Optimization and Control Probability 60H15, 93E20, 60H25, 49J30
In this paper, we establish some second order necessary/sufficient optimality conditions for optimal control problems of stochastic evolution equations in infinite dimensions.
Optimization and Control Primary 93E20, Secondary, 60H07, 60H15
This problem is NP-hard, so we propose a heuristic algorithm based on semi-definite relaxation (SDR) programming to solve it.
Principal component analysis is a widely-used method for the dimensionality reduction of a given data set in a high-dimensional Euclidean space.
Combinatorics Populations and Evolution
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors.
Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi by defining the concepts of "standard patch" and "canonical feature" and leverage these to train a novel robust covariant detector.
Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi  by defining the concepts of “standard patch” and “canonical feature” and leverage these to train a novel robust covariant detector.
This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR).
We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications.
In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process.
In order to achieve high efficiency of classification in intrusion detection, a compressed model is proposed in this paper which combines horizontal compression with vertical compression.