Let's read! We will often find out this sentence everywhere. When still being a kid, mom used to order us to always read, so did the teacher. Some books are fully read in a week and we need the obligation to support reading. What about now? Do you still love reading? Is reading only for you who have obligation? Absolutely not! We here offer you a new book enPDFd the perception of the visual world to read.

The Perception of the Visual World. By James J. Gibson. U.S.A.: Houghton Mifflin Company, 1950 (George Allen & Unwin, Ltd., London). Price 35s.

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

Texture features for image classification and retrieval.

A review on neural networks with random weights

Internet of Things (IoT) is a concept that envisions all objects around us as part of internet. IoT coverage is very wide and include variety of objects like smart phones, tablets, digital cameras, sensors, etc. Once all these devices are connected with each other, they enable more and more smart processes and services that support our basic needs, economies, environment and health. Such enormous number of devices connected to internet provides many kinds of services and produce huge amount of data and information. Cloud computing is a model for on-demand access to a shared pool of configurable resources (e.g. compute, networks, servers, storage, applications, services, and software) that can be easily provisioned as Infrastructure (IaaS), software and applications (SaaS). Cloud based platforms help to connect to the things (IaaS) around us so that we can access anything at any time and any place in a user friendly manner using customized portals and in built applications (SaaS). Hence, cloud acts as a front end to access Internet of Things. Applications that interact with devices like sensors have special requirements of massive storage to storage big data, huge computation power to enable the real time processing of the data, and high speed network to stream audio or video. In this paper, we describe how Internet of Things and Cloud computing can work together can address the Big Data issues. We also illustrate about Sensing as a service on cloud using few applications like Augmented Reality, Agriculture and Environment monitoring. Finally, we also propose a prototype model for providing sensing as a service on cloud.

Cloud computing for Internet of Things & sensing based applications

In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks (CNNs) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects (using a CAD model) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.

CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

In recent years, automated human tracking over camera networks is getting essential for video surveillance. The tasks of tracking human over camera networks are not only inherently challenging due to changing human appearance, but also have enormous potentials for a wide range of practical applications, ranging from security surveillance to retail and health care. This review paper surveys the most widely used techniques and recent advances for human tracking over camera networks. Two important functional modules for the human tracking over camera networks are addressed, including human tracking within a camera and human tracking across non-overlapping cameras. The core techniques of human tracking within a camera are discussed based on two aspects, i.e., generative trackers and discriminative trackers. The core techniques of human tracking across non-overlapping cameras are then discussed based on the aspects of human re-identification, camera-link model-based tracking and graph model-based tracking. Our survey aims to address existing problems, challenges, and future research directions based on the analyses of the current progress made toward human tracking techniques over camera networks.

/pdf/human-tracking-over-camera-networks-a-review-10g0sfioif.pdf

Human tracking over camera networks: a review

In this paper, we propose a method called Convolutional Neural Network-Markov Random Field (CNN-MRF) to estimate the crowd count in a still image. We first divide the dense crowd visible image into overlapping patches and then use a deep convolutional neural network to extract features from each patch image, followed by a fully connected neural network to regress the local patch crowd count. Since the local patches have overlapping portions, the crowd count of the adjacent patches has a high correlation. We use this correlation and the Markov random field to smooth the counting results of the local patches. Experiments show that our approach significantly outperforms the state-of-the-art methods on UCF and Shanghaitech crowd counting datasets.

Image Crowd Counting Using Convolutional Neural Network and Markov Random Field

Advanced Encryption Standard (AES) and Elliptic Curve Cryptosystems (ECC) is the best two algorithms of symmetric encryption technology and asymmetric encryption technology. The paper analyzes the AES algorithm and S-box structure, then the replace plan based on S-box structure is proposed to improve AES encryption algorithm, secondly the ECC algorithm is been discussed. Based on this we put forward an mix encryption scheme of improved AES and ECC. This plan has high operation speed, high security performance and strong usability.

Research and realization based on hybrid encryption algorithm of improved AES and ECC

Human pose estimation has been an important research topic for computer vision community. It has been in focus of researchers mainly because of its significant applications in various important fields like human computer interaction, action recognition, surveillance, picture understanding, threat prediction, etc. It's difficult to cover all aspects of this domain because of the diversity of its application areas, therefore this review is focused on the most significant contributions in Human Pose Estimation methods from a single two-dimensional image. We start our study with the traditional pictorial structure, go through a discussion of the use of Deep Neural Networks that improved the human pose estimation significantly and then the most recent, more famous approach namely Stacked Hourglass. Modern methods are based on training, evaluating and comparing on some common datasets using different architectures of Deep learning modules. Hence, starting from the first practical models for estimating human pose, we provide a comprehensive study of some of the most famous deep learning methods in order to provide a concise analytical review of these most influential methods.

Wanggen Wan

Papers

CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

Human tracking over camera networks: a review

Image Crowd Counting Using Convolutional Neural Network and Markov Random Field

Research and realization based on hybrid encryption algorithm of improved AES and ECC

A Review of Human Pose Estimation from Single Image