Publications

Distinctive Image Features from Scale-Invariant Keypoints

Microsoft COCO: Common Objects in Context

ImageNet Large Scale Visual Recognition Challenge

Rethinking the Inception Architecture for Computer Vision

Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to bec...

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer ...

Squeeze-and-Excitation Networks

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local ...

MobileNetV2: Inverted Residuals and Linear Bottlenecks

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as acr...

Snakes: Active contour models

Normalized cuts and image segmentation

We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach...

Nonlinear total variation based noise removal algorithms

Toward a knowledge‐based theory of the firm

Abstract Given assumptions about the characteristics of knowledge and the knowledge requirements of production, the firm is conceptualized as an institution for integrating know...

Nonlinear Dimensionality Reduction by Locally Linear Embedding

Many areas of science depend on exploratory data analysis and visualization. The need to analyze large amounts of multivariate data raises the fundamental problem of dimensional...