Home      Library      Discussions      About
Join us

@iie.ac.cn

Dec 21, 2017
Number Theory
Information Theory
Combinatorics

This work was supported by the National Key Research and Development Program of China (No. 2016YFB0800401), the National Natural Science Foundation of China (No. 61572491 and 11688101) and NSERC of Canada.

A Recursive Construction of Permutation Polynomials over $\mathbb{F…

In this paper, we construct two classes of permutation polynomials over $\mathbb{F}_{q^2}$ with odd characteristic from rational R\'{e}dei functions.…
Jun 18, 2019
Machine Learning
Computer Vision

Learning Personalized Attribute Preference via Multi-task AUC Optim…

Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of …
May 27, 2019
Sound
Computation and Language
Audio and Speech Processing

EG-GAN: Cross-Language Emotion Gain Synthesis based on Cycle-Consiste…

Despite remarkable contributions from existing emotional speech synthesizers, we find that these methods are based on Text-to-Speech system or limite…
Nov 16, 2017
Machine Learning

HodgeRank with Information Maximization for Crowdsourced Pairwise R…

Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requeste…
Apr 02, 2013
Cryptography and Security

In this paper, we use a combination of a distributed scheme and quantum cryptography to construct an unconditionally secure distributed anonymous quantum key distributed scheme, based on which we developed a new type of unconditionally secure electi…

Distributed quantum election scheme

In an electronic voting protocol, a distributed scheme can be used for forbidding the malicious acts of the voting administrator and the counter duri…
Apr 10, 2019
Computer Vision

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aer…

The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Ne…
Apr 02, 2014

While the best known classical algorithm for computing Walsh spectral is of order O(n2n), the quantum algorithm (specifically the Bernstein-Vazirani algorithm) can give some informations of it efficiently. Based on this, We present a polynomial-time…

A quantum algorithm to approximate the linear structures of Boolean …

We present a quantum algorithm for approximating the linear structures of a Boolean function $f$. Different from previous algorithms (such as Simon's…
Jul 05, 2017
Computer Vision
Multimedia

Copy-move Forgery Detection based on Convolutional Kernel Network

In this paper, a copy-move forgery detection method based on Convolutional Kernel Network is proposed. Different from methods based on conventional h…
Nov 17, 2017
Machine Learning
Information Retrieval
Optimization and Control

Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borw…

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the exi…
Nov 04, 2017
Computer Vision

An Iterative Co-Saliency Framework for RGBD Images

As a newly emerging and significant topic in computer vision community, co-saliency detection aims at discovering the common salient objects in multi…
Oct 14, 2019
Machine Learning

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing i…
Sep 09, 2019
Computation and Language

Graph-Based Reasoning over Heterogeneous External Knowledge for Com…

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key …
Sep 10, 2019
Computation and Language
Information Retrieval
Social and Information Networks

Jointly embedding the local and global relations of heterogeneous gra…

The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal pl…
Feb 20, 2019
Computer Vision

Learning Transferable Self-attentive Representations for Action Rec…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume vi…
Jun 02, 2010

Quantum Public-Key Encryption with Information Theoretic Security

We propose a definition for the information theoretic security of a quantum public-key encryption scheme, and present bit-oriented and two-bit-orient…
Apr 21, 2017
Networking and Internet Architecture

SFCSD: A Self-Feedback Correction System for DNS Based on Active and …

Domain Name System (DNS), one of the important infrastructure in the Internet, was vulnerable to attacks, for the DNS designer didn't take security i…
Jan 02, 2020
Computer Vision

Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning

We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first gene…
Mar 09, 2020
Machine Learning

In this paper, we studied the risk performance of distributed ERM and derived tight risk bounds for general loss functions and hypothesis spaces. We first show that when the number of processors satisfy some restrictions, we can obtain tight risk bo…

Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss an…

Theoretical analysis of the divide-and-conquer based distributed learning with least square loss in the reproducing kernel Hilbert space (RKHS) have …
Feb 20, 2020
Machine Learning

Input Perturbation: A New Paradigm between Central and Local Differ…

Traditionally, there are two models on differential privacy: the central model and the local model. The central model focuses on the machine learning…
Dec 24, 2019
Computation and Language

Improving Abstractive Text Summarization with History Aggregation

Recent neural sequence to sequence models have provided feasible solutions for abstractive summarization. However, such models are still hard to tack…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description