Two Minute Papers's profile - ShortScience.org

www.graphics.stanford.edu
scholar.google.com

Face2Face: Real-time Face Capture and Reenactment of RGB Videos
Thies, J. and Zollh{\"o}fer, M. and Stamminger, M. and Theobalt, C. and Nie{\ss}ner, M.
Conference and Computer Vision and Pattern Recognition - 2016 via Local
Keywords:

2	[link] Summary by Two Minute Papers 8 years ago https://www.youtube.com/watch?v=_S1lyQbbJM4 more less

dx.doi.org
sci-hub
scholar.google.com

Narrow Band FLIP for Liquid Simulations
Ferstl, Florian and Ando, Ryoichi and Wojtan, Chris and Westermann, Rüdiger and Thuerey, Nils
Comput. Graph. Forum - 2016 via Local Bibsonomy
Keywords: dblp

2	[link] Summary by Two Minute Papers 8 years ago https://www.youtube.com/watch?v=nfPBT71xYVQ more less

hi.cs.waseda.ac.jp
sci-hub
scholar.google.com

Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification
Satoshi Iizuka and Edgar Simo-Serra and Hiroshi Ishikawa
ACM Transactions on Graphics (Proc. of SIGGRAPH 2016) - 2016 via Local
Keywords:

2	[link] Summary by Two Minute Papers 8 years ago https://www.youtube.com/watch?v=MfaTOXxA8dM more less

arxiv.org
scholar.google.com

Deep Visual-Semantic Alignments for Generating Image Descriptions
Karpathy, Andrej and Li, Fei-Fei
arXiv e-Print archive - 2014 via Local Bibsonomy
Keywords: dblp

[link] Summary by Two Minute Papers 8 years ago

https://www.youtube.com/watch?v=e-WB4lfg30M


This technique is a combination of two powerful machine learning algorithms:
- convolutional neural networks are excellent at image classification, i.e., finding out what is seen on an input image,
- recurrent neural networks that are capable of processing a sequence of inputs and outputs, therefore it can create sentences of what is seen on the image.

Combining these two techniques makes it possible for a computer to describe in a sentence what is seen on an input image.

Two Minute Papers

sciscore: 2