Home      Library      Discussions      About
Join us

@mails.ucas.ac.cn

Apr 05, 2015

Stronger Schrödinger-like Uncertainty Relations

Uncertainty relation is one of the fundamental building blocks of quantum theory. Nevertheless, the traditional uncertainty relations do not fully ca…
Jul 24, 2018
Computer Vision

Dermoscopic Image Analysis for ISIC Challenge 2018

This short paper reports the algorithms we used and the evaluation performances for ISIC Challenge 2018. Our team participates in all the tasks in th…
Oct 13, 2016
Computation and Language
Machine Learning

Compressing Neural Language Models by Sparse Word Representations

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to dist…
Jun 09, 2019
Computation and Language
Machine Learning

A Survey on Neural Network Language Models

As the core component of Natural Language Processing (NLP) system, Language Model (LM) can provide word representation and probability indication of …
Dec 30, 2018
Symbolic Computation

In this paper, we develop a new deflation method for refining or verifying the isolated singular zeros of polynomial systems. Given a polynomial system F⊂C[x] with an isolated singular zero p, by computing the derivatives of the input polynomials di…

A New Deflation Method For Verifying the Isolated Singular Zeros of …

In this paper, we develop a new deflation technique for refining or verifying the isolated singular zeros of polynomial systems. Starting from a poly…
Mar 03, 2017
Machine Learning

Applying Ricci Flow to High Dimensional Manifold Learning

Traditional manifold learning algorithms often bear an assumption that the local neighborhood of any point on embedded manifold is roughly equal to t…
Jan 08, 2015

Pre-inflationary primordial perturbations

The large-scale power deficit in the cosmic microwave background fluctuations might be relevant with the physics of pre-inflation, a bounce, or a sup…
Sep 26, 2012

$B_c$ Exclusive Decays to Charmonium and a Light Meson at Next-to-L…

In this paper the next-to-leading order (NLO) corrections to $B_c$ meson exclusive decays to S-wave charmonia and light pseudoscalar or vector mesons…
Nov 17, 2018
Computer Vision

SCRDet: Towards More Robust Detection for Small, Cluttered and Rotate…

Object detection has been a building block in computer vision. Though considerable progress has been made, there still exist challenges for objects w…
Apr 04, 2018
Computer Vision

Building Efficient CNN Architecture for Offline Handwritten Chinese …

Deep convolutional networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwri…
Aug 30, 2016

The influence of chiral chemical potential, parallel electric and m…

We study the influence of external electric, $E$, and magnetic, $B$, fields parallel to each other, and of a chiral chemical potential, $\mu_5$, on t…
Oct 15, 2019
Graphics
Machine Learning

PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models

In geometry processing, symmetry is the universal high level structural information of the 3d models and benefits many geometry processing tasks incl…
Apr 04, 2019
Computer Vision

Comparison Network for One-Shot Conditional Object Detection

The current advances in object detection depend on large-scale datasets to get good performance. However, there may not always be sufficient samples …
Sep 05, 2019
Computer Vision
Machine Learning

FreeAnchor: Learning to Match Anchors for Visual Object Detection

Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In thi…
Dec 05, 2019
Computer Vision

Multiple Anchor Learning for Visual Object Detection

Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized …
Jan 07, 2017
Conferences: CVPR
Computer Vision

Oriented Response Networks

Deep Convolution Neural Networks (DCNNs) are capable of learning unprecedentedly effective image representations. However, their ability in handling …
Jan 26, 2019
Computer Vision

See Better Before Looking Closer: Weakly Supervised Data Augmentation…

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However…
May 03, 2015

NLO QCD Corrections to $η_c+h_c(1P)/ψ_{1,2}(1D)$ Production at B-fa…

We calculate the next-to-leading order (NLO) quantum chromodynamics (QCD) corrections to double charmonium production processes $e^+e^-\to\gamma^*\to…
Oct 14, 2015

Probing triple-Higgs productions via $4b2γ$ decay channel at a 100 …

The quartic self-coupling of the Standard Model Higgs boson can only be measured by observing the triple-Higgs production process, but it is challeng…
Aug 10, 2017
Dynamical Systems

In this part, we obtain the pointwise convergence with rationally independent rotation on the torus of the multiple ergodic averages.

On the convergence of the time average for skew-product structure and…

In this paper, for a discontinuous skew-product transformation with the integrable observation function, we obtain uniform ergodic theorem and semi-u…
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