L
Long Mai
Researcher at Adobe Systems
Publications - 57
Citations - 3487
Long Mai is an academic researcher from Adobe Systems. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 19, co-authored 53 publications receiving 2222 citations. Previous affiliations of Long Mai include King Abdullah University of Science and Technology & Portland State University.
Papers
More filters
Proceedings ArticleDOI
Video Frame Interpolation via Adaptive Separable Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
TL;DR: In this article, a deep fully convolutional neural network is proposed to estimate pairs of 1D kernels for all pixels simultaneously, which allows for the incorporation of perceptual loss to train the network to produce visually pleasing frames.
Posted Content
Video Frame Interpolation via Adaptive Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
TL;DR: This paper presents a robust video frame interpolation method that considers pixel synthesis for the interpolated frame as local convolution over two input frames and employs a deep fully convolutional neural network to estimate a spatially-adaptive convolution kernel for each pixel.
Proceedings ArticleDOI
Video Frame Interpolation via Adaptive Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
TL;DR: In this paper, a deep fully convolutional neural network is proposed to estimate a spatially-adaptive convolution kernel for each pixel, which captures both the local motion between the input frames and the coefficients for pixel synthesis.
Posted Content
Video Frame Interpolation via Adaptive Separable Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
TL;DR: This paper develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously, which allows for the incorporation of perceptual loss to train the neural network to produce visually pleasing frames.
Proceedings ArticleDOI
Composition-Preserving Deep Photo Aesthetics Assessment
Long Mai,Hailin Jin,Feng Liu +2 more
TL;DR: This paper presents a composition-preserving deep Con-vNet method that directly learns aesthetics features from the original input images without any image transformations, and adds an adaptive spatial pooling layer upon the regular convolution and pooling layers to directly handle input images with original sizes and aspect ratios.