Human-Object Interaction Recognition Based on Modeling Context

This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.

Effective approach for outdoor obstacle detection by clustering LIDAR data context

A method of environment mapping using laser-based light detection and ranging （LIDAR） is proposed in this paper. This method not only has a good detection performance in a wide range of detection angles, but also facilitates the detection of dynamic and hollowed-out obstacles. Essentially using this method, an improved clustering algorithm based on fast search and discovery of density peaks （CBFD） is presented to extract various obstacles in the environment map. By comparing with other cluster algorithms, CBFD can obtain a favorable number of clusterings automatically. Furthermore, the experiments show that CBFD is better and more robust in functionality and performance than the K-means and iterative self-organizing data analysis techniques algorithm （ISODATA）.

DATA CONTEXT MODEL IN THE PRO-CESS INTEGRATION FRAMEWORK

Process integration is the important aspect of product development process. The recent researches focus on project management, workflow management and process modeling. Based on the analysis of the process, product development process is divided into three levels according to different grains from macroscopy to microcosm. Our research concentrate on the workflow and the free-grained design process. According to the need of representing the data and the relationships among them for process integration, context model is introduced, and its characters are analyzed. The tree-like structure of inheritance among context model＇s classes is illustrated; The relationships of reference among them are also explained. Then, extensible markup language （XML） file is used to depict these classes. A four-tier framework of process integration has been established, in which model-view-controller pattern is designed to realize the separation between context model and its various views. The integration of applications is applied by the encapsulation of enterprise＇s business logic as distributed services. The prototype system for the design of air filter is applied in an institute.

Construction of an Evaluation Indicator System for Civic and Political Applications in Professional Practice Courses Based on CIPP:Taking the VBSE Practical Training Course as an Example

This study takes the virtual business society environment(VBSE)practical training course as a case study and applies the theoretical framework of the context,input,process,product(CIPP)model to construct an evaluation indicator system for the application of civic and politics in professional practice courses.The context evaluation is measured from the support of the VBSE practical training course into course civic and politics,teachers’cognition,and the integration of course objectives;the input evaluation is measured from the matching degree of teachers’civic and political competence,and the matching degree of teaching resources;the process evaluation is measured from the degree of implementation of civic and politics teaching and the degree of students’acceptance;and the product evaluation is measured from the degree of impact of civic and politics teaching.

A HIGH-PERFORMANCE VLSI ARCHITECTURE OF EBCOT BLOCK CODING IN JPEG2000

The paper presents a new architecture composed of bit plane-parallel coder for Embedded Block Coding with Optimized Truncation (EBCOT) entropy encoder used in JPEG2000. In the architecture, the coding information of each bit plane can be obtained simultaneously and processed parallel. Compared with other architectures, it has advantages of high parallelism, and no waste clock cycles for a single point. The experimental results show that it reduces the processing time about 86% than that of bit plane sequential scheme. A Field Programmable Gate Array (FPGA) prototype chip is designed and simulation results show that it can process 512×512 gray-scaled images with more than 30 frames per second at 52MHz.

Ranking and tagging bursty features in text streams with context language models

Detecting and using bursty pattems to analyze text streams has been one of the fundamental approaches in many temporal text mining applications. So far, most existing studies have focused on developing methods to detect bursty features based purely on term frequency changes. Few have taken the semantic contexts of bursty features into consideration, and as a result the detected bursty features may not always be interesting and can be hard to interpret. In this article, we propose to model the contexts of bursty features using a language modeling approach. We propose two methods to estimate the context language models based on sentence-level context and document-level context. We then propose a novel topic diversity-based metric using the context models to find newsworthy bursty features. We also propose to use the context models to automatically assign meaningful tags to bursty features. Using a large corpus of news articles, we quantitatively show that the proposed context language models for bursty features can effectively help rank bursty features based on their newsworthiness and to assign meaningful tags to annotate bursty features. We also use two example text mining applications to qualitatively demonstrate the usefulness of bursty feature ranking and tagging.

Ontology-Based Context-Aware Middleware for Smart Spaces

Context-awareness enhances human-centric, intelligent behavior in a smart environment; however context-awareness is not widely used due to the lack of effective infrastructure to support context-aware applications. This paper presents an agent-based middleware for providing context-aware services for smart spaces to afford effective support for context acquisition, representation, interpretation, and utilization to applications. The middleware uses a formal context model, which combines first order probabilistic logic （FOPL） and web ontology language （OWL） ontologies, to provide a common understanding of contextual information to facilitate context modeling and reasoning about imperfect and ambiguous contextual information and to enable context knowledge sharing and reuse. A context inference mechanism based on an extended Bayesian network approach is used to enable automated reactive and deductive reasoning. The middleware is used in a case study in a smart classroom, and performance evaluation result shows that the context reasoning algorithm is good for non-time-critical applications and that the complexity is highly sensitive to the size of the context dataset.

A hierarchical ontology context model for work-based learning

Context modelling involves a） characterizing a situation with related information, and b） dealing and stor- ing the information in a computer-understandable form. It is the keystone to enable a system to possess the perception ca- pacity and adapt its functionality properly for different situa- tions. However, a context model focusing on the characteris- tics of work-based learning is not well studied by pioneering researchers. For addressing this issue, in this work we firstly analyze several existing context models to identify the essen- tials of context modelling, whereby a hierarchical ontology context model is proposed to characterize work-based learn- ing. Subsequently, we present the application of the proposed model in work-based learning scenario to provide adapted learning supports to professionals. Hence, this work has sig- nificance in both theory and practice.

Exploiting a depth context model in visual tracking with correlation filter

Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preventing the tracker from failure in these two situations by integrating the depth information into a correlation filter based tracker. By using RGB-D data, we construct a depth context model to reveal the spatial correlation between the target and its surrounding regions. Furthermore, we adopt a region growing method to make our tracker robust to occlusion and scale variation. Additional optimizations such as a model updating scheme are applied to improve the performance for longer video sequences. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed tracker performs favourably against state-of-the-art algorithms.

A wavelet packet based block-partitioning image coding algorithm with rate-distortion optimization

As an elegant generalization of wavelet transform, wavelet packet （WP） provides an effective representation tool for adaptive waveform analysis. Recent work shows that image-coding methods based on WP decomposition can achieve significant gain over those based on a usual wavelet transform. However, most of the work adopts a tree-structured quantization scheme, which is a successful technique for wavelet image coding, but not appropriate for WP subbands. This paper presents an image-coding algorithm based on a rate-distortion optimized wavelet packet decomposition and on an intraband block-partitioning scheme. By encoding each WP subband separately with the block-partitioning algorithm and the JPEG2000 context modeling, the proposed algorithm naturally avoids the difficulty in defining parent-offspring relationships for the WP coefficients, which has to be faced when adopting the tree-structured quanUzation scheme. The experimental results show that the proposed algorithm significantly outperforms SPIHT and JPEG2000 schemes and also surpasses state-of-the-art WP image coding algorithms, in terms of both PSNR and visual quality.