The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
People share their opinions about things like products, movies and services using social media channels. The analysis of these textual contents for sentiments is a gold mine for marketing experts, thus automatic sentiment analysis is a popular area of applied artificial intelligence. We propose a latent syntactic structure-based approach for sentiment analysis which requires only sentence-level polarity...
This paper constructs speech features based on a generative model using a deep latent Gaussian model (DLGM), which is trained using stochastic gradient variational Bayes (SGVB) algorithm and performs efficient approximate inference and learning with a directed probabilistic graphical model. The trained DLGM then generate latent variables based on Gaussian distribution, which is used as new features...
Recent work in video compression has shown that using multiple 2D transforms instead of a single transform in order to de-correlate residuals provides better compression efficiency. These transforms are tested competitively inside a video encoder and the optimal transform is selected based on the Rate Distortion Optimization (RDO) cost. However, one needs to encode a syntax to indicate the chosen...
In recent years, the machine translation system based on neural network, called Neural Machie Translation, have attracted much attention, in which the entire translation steps are implemented in a single large neural network. In this framework, dealing with a large vocabulary size on its input (source) and output (target) often make the training computationally intractable. Therefore, the most frequent...
Research shows that speech dereverberation (SD) with Deep Neural Network (DNN) achieves the state-of-the-art results by learning spectral mapping, which, simultaneously, lacks the characterization of the local temporal spectral structures (LTSS) of speech signal and calls for a large storage space that is impractical in real applications. Contrarily, the Convolutional Neural Network (CNN) offers a...
Data representation plays an important role in performance of machine learning algorithms. Since data usually lacks the desired quality, many efforts have been made to provide a more desirable representation of data. Among many different approaches, sparse data representation has gained popularity in recent years. In this paper, we propose a new sparse autoencoder by imposing the power two of smoothed...
Lossy image compression methods always introduce various unpleasant artifacts into the compressed results, especially at low bit-rates. In recent years, many effective soft decoding methods for JPEG compressed images have been proposed. However, to the best of our knowledge, very few works have been done on soft decoding of JPEG 2000 compressed images. Inspired by the outstanding performance of Convolution...
This paper addresses the problem of unsupervised video summarization, formulated as selecting a sparse subset of video frames that optimally represent the input video. Our key idea is to learn a deep summarizer network to minimize distance between training videos and a distribution of their summarizations, in an unsupervised way. Such a summarizer can then be applied on a new video for estimating...
Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the...
We propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style, for neural image style transfer. To transfer an image to a specific style, the corresponding filter bank is operated on top of the intermediate feature embedding produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt, where the learning...
We describe a modular framework for video frame prediction. We refer to it as a Flexible Spatio-Temporal Network (FSTN) as it allows the extrapolation of a video sequence as well as the estimation of synthetic frames lying in between observed frames and thus the generation of slow-motion videos. By devising a customized objective function comprising decoding, encoding, and adversarial losses, we are...
Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g. attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g. attribute prediction) or classification. When applied to test data, which in the context of ZSL contains different (unseen)...
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model that classifies pixels based not only on their visual appearance, as in the traditional page segmentation task, but also on the content of underlying text. Moreover,...
We present a method for synthesizing a frontal, neutral-expression image of a persons face, given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous generative approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this...
Most of the conventional face hallucination methods assume the input image is sufficiently large and aligned, and all require the input image to be noise-free. Their performance degrades drastically if the input image is tiny, unaligned, and contaminated by noise. In this paper, we introduce a novel transformative discriminative autoencoder to 8X super-resolve unaligned noisy and tiny (16X16) low-resolution...
Training convolutional networks (CNNs) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large networks that do not fit in the memory of a few GPU cards, or for parallelizing CNN training. In this work we show that a simple hard mixture of experts model can be efficiently trained to good effect...
Image matting is a fundamental computer vision problem and has many applications. Previous algorithms have poor performance when an image has similar foreground and background colors or complicated textures. The main reasons are prior methods 1) only use low-level features and 2) lack high-level context. In this paper, we propose a novel deep learning based algorithm that can tackle both these problems...
The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem – unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) a Watch, Listen, Attend and Spell...
Colorization is an ambiguous problem, with multiple viable colorizations for a single grey-level image. However, previous methods only produce the single most probable colorization. Our goal is to model the diversity intrinsic to the problem of colorization and produce multiple colorizations that display long-scale spatial co-ordination. We learn a low dimensional embedding of color fields using a...
We focus on the non-Lambertian object-level intrinsic problem of recovering diffuse albedo, shading, and specular highlights from a single image of an object. Based on existing 3D models in the ShapeNet database, a large-scale object intrinsics database is rendered with HDR environment maps. Millions of synthetic images of objects and their corresponding albedo, shading, and specular ground-truth...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.