Home /

Research

Showing 793 - 798 / 897

Stochastic Hard Thresholding Algorithms for AUC Maximization


Authors:  ZhenhuanYang, BaojianZhou, YunwenLei....
Published date-11/04/2020

Abstract: In this paper, we aim to develop stochastic hard thresholding algorithms for the important problem of AUC maximization in imbalanced classification. The main challenge is the pairwise loss involved in …

An Improved Attention for Visual Question Answering


Authors:  TanzilaRahman, Shih-HanChou, LeonidSigal....
Published date-11/04/2020
Tasks:  QuestionAnswering, VisualQuestionAnswering

Abstract: We consider the problem of Visual Question Answering (VQA). Given an image and a free-form, open-ended, question, expressed in natural language, the goal of VQA system is to provide accurate …

A BERT-based Dual Embedding Model for Chinese Idiom Prediction


Authors:  MinghuanTan, JingJiang....
Published date-11/04/2020

Abstract: Chinese idioms are special fixed phrases usually derived from ancient stories, whose meanings are oftentimes highly idiomatic and non-compositional. The Chinese idiom prediction task is to select the correct idiom …

Quantized Variational Inference


Authors:  AmirDib....
Published date-11/04/2020
Tasks:  VariationalInference

Abstract: We present Quantized Variational Inference, a new algorithm for Evidence Lower Bound maximization. We show how Optimal Voronoi Tesselation produces variance free gradients for ELBO optimization at the cost of …

CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation


Authors:  HengliWang, RuiFan, MingLiu....
Published date-11/04/2020
Tasks:  OpticalFlowEstimation

Abstract: The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical …

BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh


Authors:  MingQian, CongyuQiao, JiaminLin....
Published date-11/04/2020

Abstract: A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred. DSLR can easily render this kind of effect naturally. However, …

Filter by

Categories

Tags