596 citations · 637 across the 7 of their papers we have counts for
9 papers
Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
Zheng Xu, Michael Wilber, Chen Fang +2
We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs. Besides the traditional…
BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography
Michael J. Wilber, Chen Fang, Hailin Jin +3
Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photo…
Residual Networks Behave Like Ensembles of Relatively Shallow Networks
Andreas Veit, Michael Wilber, Serge Belongie
In this work we propose a novel interpretation of residual networks showing that they can be seen as a collection of many paths of differing length. Moreover, residual networks see…
Can we still avoid automatic face detection?
Michael J. Wilber, Vitaly Shmatikov, Serge Belongie
After decades of study, automatic face detection and recognition systems are now accurate and widespread. Naturally, this means users who wish to avoid automatic recognition are be…
Learning Concept Embeddings with Combined Human-Machine Expertise
Michael J. Wilber, Iljung S. Kwak, David Kriegman +1
This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are compl…
On Optimizing Human-Machine Task Assignments
Andreas Veit, Michael Wilber, Rajan Vaish +48
When crowdsourcing systems are used in combination with machine inference systems in the real world, they benefit the most when the machine system is deeply integrated with the cro…
Image Representations and New Domains in Neural Image Captioning
Jack Hessel, Nicolas Savva, Michael J. Wilber
We examine the possibility that recent promising results in automatic caption generation are due primarily to language models. By varying image representation quality produced by a…
Cost-Effective HITs for Relative Similarity Comparisons
Michael J. Wilber, Iljung S. Kwak, Serge J. Belongie
Similarity comparisons of the form "Is object a more similar to b than to c?" are useful for computer vision and machine learning applications. Unfortunately, an embedding of p…
Good Recognition is Non-Metric
Walter J. Scheirer, Michael J. Wilber, Michael Eckmann +1
Recognition is the fundamental task of visual cognition, yet how to formalize the general recognition problem for computer vision remains an open issue. The problem is sometimes re…