Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Wilber, Michael"'
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 content and style representation based on deep features and statistics
Externí odkaz:
http://arxiv.org/abs/1805.09987
Autor:
Wilber, Michael J., Fang, Chen, Jin, Hailin, Hertzmann, Aaron, Collomosse, John, Belongie, Serge
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 photographs. Artwork produced by people is not constrained to mimic the phy
Externí odkaz:
http://arxiv.org/abs/1704.08614
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 seem to enable very deep networks by leveraging only the short paths duri
Externí odkaz:
http://arxiv.org/abs/1605.06431
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 becoming less able to do so. Where do we stand in this cat-and-mouse rac
Externí odkaz:
http://arxiv.org/abs/1602.04504
Autor:
Veit, Andreas, Wilber, Michael, Vaish, Rajan, Belongie, Serge, Davis, James, Anand, Vishal, Aviral, Anshu, Chakrabarty, Prithvijit, Chandak, Yash, Chaturvedi, Sidharth, Devaraj, Chinmaya, Dhall, Ankit, Dwivedi, Utkarsh, Gupte, Sanket, Sridhar, Sharath N., Paga, Karthik, Pahuja, Anuj, Raisinghani, Aditya, Sharma, Ayush, Sharma, Shweta, Sinha, Darpana, Thakkar, Nisarg, Vignesh, K. Bala, Verma, Utkarsh, Abhishek, Kanniganti, Agrawal, Amod, Aishwarya, Arya, Bhattacharjee, Aurgho, Dhanasekar, Sarveshwaran, Gullapalli, Venkata Karthik, Gupta, Shuchita, G, Chandana, Jain, Kinjal, Kapur, Simran, Kasula, Meghana, Kumar, Shashi, Kundaliya, Parth, Mathur, Utkarsh, Mishra, Alankrit, Mudgal, Aayush, Nadimpalli, Aditya, Nihit, Munakala Sree, Periwal, Akanksha, Sagar, Ayush, Shah, Ayush, Sharma, Vikas, Sharma, Yashovardhan, Siddiqui, Faizal, Singh, Virender, S., Abhinav, Yadav, Anurag. D.
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 crowd workers. However, if researchers wish to integrate the crowd with "
Externí odkaz:
http://arxiv.org/abs/1509.07543
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 complimentary: human insight can capture relationships that are not apparen
Externí odkaz:
http://arxiv.org/abs/1509.07479
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 convolutional neural network, we find that a state-of-the-art neural
Externí odkaz:
http://arxiv.org/abs/1508.02091
Publikováno v:
In Computers & Graphics April 2020 87:1-11
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 $n$ points is specified by $n^3$ triplets, making collecting every triplet
Externí odkaz:
http://arxiv.org/abs/1404.3291
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 reduced to the simplest case of recognizing matching pairs, often struct
Externí odkaz:
http://arxiv.org/abs/1302.4673