Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

A macroblock in a video sequence may be undecodable because the corresponding compressed data is lost or the syntax is out of synchronization. An undecodable macroblock may be concealed using error concealment technique. The level of initial visible artifacts caused by undecodable macroblocks may be estimated as a function of motion magnitude, error concealment distance, and/or residual energy. The initial visible artifacts may propagate spatially or temporally to other macroblocks through prediction. Considering both initial visible artifacts and propagated artifacts, levels of overall artifacts may be estimated for individual macroblocks. The visual quality for the video sequence can then be estimated by pooling the macroblock level artifact levels.

Video quality assessment at a bitstream level

In no-reference 360-degree image quality assessment (NR 360IQA), graph convolutional networks (GCNs), which model interactions between viewports through graphs, have achieved impressive performance. However, prevailing GCN-based NR 360IQA methods suffer from three main limitations. First, they only use high-level features of the distorted image to regress the quality score, while the human visual system (HVS) scores the image based on hierarchical features. Second, they simplify complex high-order interactions between viewports in a pairwise fashion through graphs. Third, in the graph construction, they only consider spatial locations of viewports, ignoring its content characteristics. Accordingly, to address these issues, we propose an adaptive hypergraph convolutional network for NR 360IQA, denoted as AHGCN. Specifically, we first design a multi-level viewport descriptor for extracting hierarchical representations from viewports. Then, we model interactions between viewports through hypergraphs, where each hyperedge connects two or more viewports. In the hypergraph construction, we build a location-based hyperedge and a content-based hyperedge for each viewport. Experimental results on two public 360IQA databases demonstrate that our proposed approach has a clear advantage over state-of-the-art full-reference and no-reference IQA models.

Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment.

Various implementations address distortion and quality measurements related to, for example, freeze-with-skip and/or a freeze-without-skip events. In several implementations, information is accessed indicating that a first and second set of one or more consecutive pictures are not to be displayed. A first and second indicator are determined. In one such implementation, the first and second indicators indicate an amount of distortion across one or more types of distortive effects that result from displaying substantially a first, or second, same picture during a display time for the first, or second, set of pictures. The first and second indicators are combined in a non-linear manner. In another such implementation, the distortion is associated with a given type of distortive effect, from among multiple types of distortive effects, and the first and second indicators are combined for the given type of distortive effect.

Distortion/quality measurement

Texture scenes like flickering flames, swaying tree branches, flowing water exhibit a complex stochastic motion character. It presents a great challenge to compress these dynamic texture efficiently even with the state-of-the-art video encoder. Furthermore, these contents only contain a little helpful information in surveillance analysis. In this paper, we propose an approach for compressing the dynamic textures in the surveillance video. In the proposed scheme, the dynamic texture contents are detected by the histogram of motion direction (HMD) algorithm, and then removed at the encoder, these dynamic texture contents will be restored at the decoder directly. Objective and subjective results are presented, demonstrating that the proposed approach provides about 8.7% bitrate saving with visually plausible dynamic textures in comparison with High Efficiency Video Coding (HEVC).

Surveillance video coding with dynamic textural background detection

In the case of packet loss during transmission over an error-prone transmission channel, some decoders may perform error concealment. In real-time systems, application decoders must handle the data loss alone and find out which data are missing. A special syntax within a packet-based framework is provided which is based on identifying and indicating the relationship between RTP packets and the application layer data they carry, before the packets are fed to the multi-layer application decoder. This helps the decoder to employ proper error concealment techniques in time, and prevents unnecessary processing in the decoder. A data stream comprises RTP packets containing application data of a multi-layer application, wherein an RTP packet (p2) contains two kinds of application layer information (NBf,NBn): one relating to the next RTP packet (p3), and one relating to the previous RTP packet (p1). In case of packet loss, the decoder can immediately determine the amount and type (VCLx) of missing data.

Zhibo Chen

Papers

Video quality assessment at a bitstream level

Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment.

Distortion/quality measurement

Surveillance video coding with dynamic textural background detection

Data stream comprising RTP packets, and method and device for encoding/decoding such data stream