Learn More
In this work, we propose the marginal structured SVM (MSSVM) for structured prediction with hidden variables. MSSVM properly accounts for the uncertainty of hidden variables, and can significantly outperform the previously proposed latent structured SVM (LSSVM; Yu & Joachims (2009)) and other state-of-art methods, especially when that uncertainty is large.(More)
Every insect is considered, from the viewpoint of biological evolution, to be a neural cell that constitutes a neural network in a casual and loose way of joint. Through simulating the ant swarm intelligence on the basis of human neural network, this paper advances a linear binary network. The binary code expects a low intelligence of each ant, and each(More)
In this paper, we present a novel near-duplicate video retrieval system serving one million web videos. To achieve both the effectiveness and efficiency, a visual word based approach is proposed, which quantizes each video frame into a word and represents the whole video as a bag of words. The system can respond to a query in 41ms with 78.4% MAP on average.
We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art approaches for single-speaker neural TTS: Deep Voice 1 and Tacotron. We introduce Deep Voice 2, which is based on a(More)
Nonuniform Fourier transform (FT) has a variety of applications such as medical imaging, radio astronomy and the numerical solution of partial differential equations. Over the last few years, several algorithms have been developed for computing the nonuniform FT based on interpolating an oversampled fast Fourier Transform (FFT). In this paper, we present a(More)
Multi-instance learning, like other machine learning and data mining tasks, requires distance metrics. Although metric learning methods have been studied for many years, metric learners for multi-instance learning remain almost untouched. In this paper, we propose a framework called Multi-Instance MEtric Learning (MIMEL) to learn an appropriate distance(More)
Multi-instance learning, as other machine learning tasks, also suffers from the curse of dimensionality. Although dimensionality reduction methods have been investigated for many years, multi-instance dimension-ality reduction methods remain untouched. On the other hand, most algorithms in multi-instance framework treat instances in each bag as(More)
To improve the performance of motion estimation in video coding, we propose a novel search algorithm, which utilizes the global search ability of particle swarm optimization (PSO) and the local search ability of simplex method (SM).According to the center-biased and temporal-spatial correlation features of motion vector and the global randomness of PSO, the(More)
Kernel method is a powerful tool in multi-instance learning. However, many typical kernel methods for multi-instance learning ignore the correspondence information of instances between two bags or co-occurrence information, and result in poor performance. Additionally, most current multi-instance kernels unreasonably assign all instances in each bag an(More)
Proxy re-signature is greatly concerned by researchers recently. It is a very useful tool for sharing web certificates, forming weak group signatures, and authenticating a network path. In this paper, we propose the first certificateless proxy re-signature scheme. Based on certificateless public cryptosystem, the scheme solves the using of certificate in(More)