Abstractive document summarization seeks to automatically generate a summary for a document, based on some abstract “understanding” of the original document. State-of-the-art techniques traditionally use attentive encoder–decoder architectures. However, due to the large number of parameters in these models, they require large training datasets and long training times. In this paper, we propose ...

This thesis deals with multiterminal source coding problems for a general framework of coding systems, called coding systems with cooperation, where there are some linkages among encoders and decoders. Especially, the main focus of this thesis is encoder cooperation. Two types of coding systems are investigated that incorporate encoder cooperation: the Slepian-Wolf coding system with linkages (...

H.264 is an emerging video coding standard, which aims at compressing high-quality video contents at low bit-rates. While the new encoding and decoding processes are similar to many previous standards, the new standard includes a number of new features and thus requires much more computation than most existing standards do. The complexity of H.264 standard poses a large amount of challenges to ...

Single-view distributed video coding (DVC) is a video compression method that allows for the computational complexity of the system to be shifted from the encoder to the decoder. The reduced encoding complexity makes DVC attractive for use in systems where processing power or energy use at the encoder is constrained, for example, in wireless devices and surveillance systems. One of the biggest ...

What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper clarifies some of these previous intuitive observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstructi...

The multiplication operation is present in many parts of a digital system or digital computer, most notably in signal processing, graphics and scientific computation. With advances in technology, various techniques have been proposed to design multipliers, which offer high speed, low power consumption and lesser area. Thus making them suitable for various high speeds, low power compact VLSI imp...

Video encoding due to its high processing requirements has been traditionally done using special-purpose hardware. Software solutions have been explored but are considered to be feasible only for nonreal-time applications requiring low encoding rates. However, a software solution using a general-purpose computing system has numerous advantages: It is more available and flexible and allows exper...

Neural style transfer has drawn broad attention in recent years. However, most existing methods aim to explicitly model the transformation between different styles, and the learned model is thus not generalizable to new styles. We here attempt to separate the representations for styles and contents, and propose a generalized style transfer network consisting of style encoder, content encoder, m...

Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps define better justified sampling algorithms for deep learning based on auto-encoder variants. We consider an MCMC where each step samples from a Gaussian whose me...

This paper presents a memory efficient VLSI architecture of low complex video encoder using three dimensional (3-D) wavelet and Compressed Sensing (CS) is proposed for space and low power video applications. Majority of the conventional video coding schemes are based on hybrid model, which requires complex operations like transform coding (DCT), motion estimation and deblocking filter at the en...