In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

The Analysis of Time Series: An Introduction, 4th edn. By C. Chatfield. ISBN 0 412 31820 2. Chapman and Hall, London, 1989. 242 pp. £13.50.

The Analysis of Time Series: An Introduction

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

MPEG-4 and H.263 encoded video is expected to account for a large portion of the traffic in future wireline and wireless networks. However, due to a lack of sufficiently long frame size traces of MPEG-4 and H.263 encoded videos, most network performance evaluations currently use MPEG-1 encodings. We present and study a publicly available library of frame size traces of long MPEG-4 and H.263 encoded videos, which we have generated at the Technical University Berlin. The frame size traces have been generated from MPEG-4 and H.263 encodings of over 10 video sequences each 60 minutes long. We conduct a thorough statistical analysis of the traces.

MPEG-4 and H.263 video traces for network performance evaluation

Light field imaging has emerged as a technology allowing to capture richer visual information from our world. As opposed to traditional photography, which captures a 2D projection of the light in the scene integrating the angular domain, light fields collect radiance from rays in all directions, demultiplexing the angular information lost in conventional photography. On the one hand, this higher dimensional representation of visual data offers powerful capabilities for scene understanding, and substantially improves the performance of traditional computer vision problems such as depth sensing, post-capture refocusing, segmentation, video stabilization, material classification, etc. On the other hand, the high-dimensionality of light fields also brings up new challenges in terms of data capture, data compression, content editing, and display. Taking these two elements together, research in light field image processing has become increasingly popular in the computer vision, computer graphics, and signal processing communities. In this paper, we present a comprehensive overview and discussion of research in this field over the past 20 years. We focus on all aspects of light field image processing, including basic light field representation and theory, acquisition, super-resolution, depth estimation, compression, editing, processing algorithms for light field display, and computer vision applications of light field data.

/pdf/light-field-image-processing-an-overview-3jq61afb1y.pdf

Light Field Image Processing: An Overview

Holoscopic imaging, also known as integral, light field, and plenoptic imaging, is an appealing technology for glassless 3D video systems, which has recently emerged as a prospective candidate for future image and video applications, such as 3D television. However, to successfully introduce 3D holoscopic video applications into the market, adequate coding tools that can efficiently handle 3D holoscopic video are necessary. In this context, this paper discusses the requirements and challenges for 3D holoscopic video coding, and presents an efficient 3D holoscopic coding scheme based on High Efficiency Video Coding (HEVC). The proposed 3D holoscopic codec makes use of the self-similarity (SS) compensated prediction concept to efficiently explore the inherent correlation of the 3D holoscopic content in Intra- and Inter-coded frames, as well as a novel vector prediction scheme to take advantage of the peculiar characteristics of the SS prediction data. Extensive experiments were conducted, and have shown that the proposed solution is able to outperform HEVC as well as other coding solutions proposed in the literature. Moreover, a consistently better performance is also observed for a set of different quality metrics proposed in the literature for 3D holoscopic content, as well as for the visual quality of views synthesized from decompressed 3D holoscopic content. An efficient 3D holoscopic video coding solution based on HEVC is proposed.It relies on a self-similarity prediction and a new micro-image based vector prediction.Superior coding efficiency is shown compared to HEVC and other benchmark solutions.Consistently better performance regarding a set of different objective quality metrics.

/pdf/hevc-based-3d-holoscopic-video-coding-using-self-similarity-1moewd4jq4.pdf

HEVC-based 3D holoscopic video coding using self-similarity compensated prediction

This paper proposes an efficient light field image coding (LFC) solution based on High Efficiency Video Coding (HEVC). The proposed light field codec makes use of the self-similarity (SS) compensated prediction concept to efficiently explore the inherent correlation of this type of content. To further improve the coding performance, a bi-predicted SS estimation and SS compensation is proposed, where the candidate predictor can be also devised as a linear combination of two blocks within the same search window. In addition, an improved vector prediction scheme is also used to take advantage of the particular characteristics of the SS prediction vectors. Experimental results show that the proposed LFC scheme is able to outperform the benchmark solutions with significant gains.

/pdf/hevc-based-light-field-image-coding-with-bi-predicted-self-3530saznqi.pdf

HEVC-based light field image coding with bi-predicted self-similarity compensation

We demonstrated a 3D holoscopic video system for 3DTV application. We showed that using a field lens and a square aperture significantly reduces the vignetting problem associated with a relay system and achieves over 95 percent fill factor. The main problem for such a relay system is the nonlinear distortion during the 3D image capturing, which can seriously affect the reconstruction process for a 3D display. The nonlinear distortion mainly includes lens radial distortion (intrinsic) and microlens array perspective distortion (extrinsic). This is the task of future work. Our results also show that the SS coding approach performs better than the standard HEVC scheme. Furthermore, we show that search and retrieval performance relies on the depth map's quality and that the multimodal fusion boosts the retrieval performance.

/pdf/immersive-3d-holoscopic-video-system-1b51tktk5g.pdf

Immersive 3D Holoscopic Video System

Light field imaging is a promising new technology that allows the user not only to change the focus and perspective after taking a picture, as well as to generate 3D content, among other applications. However, light field images are characterized by large amounts of data and there is a lack of coding tools to efficiently encode this type of content. Therefore, this paper proposes the addition of two new prediction tools to the HEVC framework, to improve its coding efficiency. The first tool is based on the local linear embedding-based prediction and the second one is based on the self-similarity compensated prediction. Experimental results show improvements over JPEG and HEVC in terms of average bitrate savings of 71.44% and 31.87%, and average PSNR gains of 4.73dB and 0.89dB, respectively.

Light field HEVC-based image coding using locally linear embedding and self-similarity compensated prediction

Holoscopic imaging is an advantageous solution for glassless 3D video systems, which promises to revolutionize the 3D market in the near future. Besides freeing the user from wearing any viewing device, it supports full motion parallax, improving this way the users' viewing experience. However, in order to provide 3D holoscopic content with convenient visual quality in terms of resolution and 3D perception, ultra-high resolution acquisition and display devices are required. Consequently, efficient video coding tools to deal with this large amount of data become of paramount importance. The recent standardization project called High Efficiency Video Coding (HEVC) addresses the requirements of high resolution video coding, but does not yet address the specific characteristics of 3D holoscopic content. To remedy this situation, this paper proposes to incorporate new prediction modes in HEVC to explore the particular structure of 3D holoscopic content, in order to further improve the performance of HEVC for this type of content. Experimental results, based on the HEVC test model version 4.0 are presented and clearly show the advantages of using this approach.

Luís Ducla Soares

Papers

HEVC-based 3D holoscopic video coding using self-similarity compensated prediction

HEVC-based light field image coding with bi-predicted self-similarity compensation

Immersive 3D Holoscopic Video System

Light field HEVC-based image coding using locally linear embedding and self-similarity compensated prediction

New HEVC prediction modes for 3D holoscopic video coding