作者：
Vivacqua, Ade Souza, JComputer Science Program
Graduate School Engineering Federal University of Rio de Janeiro Rio de Janeiro Brazil DCC
Institute of Mathematics Federal University of Rio de Janeiro Rio de Janeiro Brazil
Creativity has become an important asset in today's fast changing environment. It is especially important in design, which demands innovative solutions for every project. We believe that creativity can and should ...
详细信息
ISBN:
(纸本)0780379411
Creativity has become an important asset in today's fast changing environment. It is especially important in design, which demands innovative solutions for every project. We believe that creativity can and should be encouraged in work groups. In this paper, we propose a framework for supporting creativity in problem solving. Through the use of problem, domain and user models and information retrieval and agent technology, we hope to support creative cooperative work.
The Semantic Web is now emerging to give the explicit meanings to information that makes the process and integration of Web-based information easier for machines to carry out automatically, so services on the semantic...
详细信息
When sending a scalable video sequence over packet loss channels, one usually partitions it into groups of frames (GOFs), and protects each GOF using the FEC based multiple description coding (FEC-MDC) method. In this...
详细信息
When sending a scalable video sequence over packet loss channels, one usually partitions it into groups of frames (GOFs), and protects each GOF using the FEC based multiple description coding (FEC-MDC) method. In this paper, we consider the inter-GOF bit allocation problem which attempts to smooth the expected qualities of all GOFs of a sequence, and proposed three algorithms. Analytical results show that all these algorithms can achieve very good constant expected quality among all GOFs, however with different computing speeds. The fastest one is very efficient and can be used in real time applications.
We consider applying the FEC-based multiple description coding method for multicasting a source to a set of clients with heterogeneous access bandwidths. In the scenario where different clients access the server via s...
详细信息
In this paper, we present a novel scheme for coding multiview video sequence based on global motion prediction between adjacent views. For that, the left-most view is compressed as reference sequence using standard bl...
详细信息
Case retrieval in case-based reasoning relies heavily on the design of a good similarity function. This paper provides an approach to utilizing the correlative information among features to compute the similarity of c...
详细信息
H.264/AVC is a new international standard for the compression of natural video images, in which a deblocking filter has been adopted to remove blocking artifacts. We propose an efficient processing order for the deblo...
详细信息
ISBN:
(纸本)0780385543
H.264/AVC is a new international standard for the compression of natural video images, in which a deblocking filter has been adopted to remove blocking artifacts. We propose an efficient processing order for the deblocking filter, and present the VLSI architecture according to the order. Making good use of data dependence between neighboring 4/spl times/4 blocks, our design reduces the requirement of on-chip SRAM bandwidth and increases the throughput of the filter processing. The architecture has been described in Verilog HDL, simulated with VCS and synthesized using 0.25 /spl mu/m CMOS cells library by Synopsys Design Compiler. The circuit costs about 24k logic gates (not including a 32/spl times/64 SRAM and two 32/spl times/96 SRAMs) when the working frequency is set to 100 MHz. This design can support real-time deblocking of HDTV (1280/spl times/720, 60 fps) H.264/AVC video. This architecture is valuable for the hardware design of an H.264/AVC codec.
This paper reports an investigation on adult images detection based on the shape features of skin regions. In order to accurately detect skin regions, we propose a skin detection method using multi-Bayes classifiers i...
详细信息
This paper reports an investigation on adult images detection based on the shape features of skin regions. In order to accurately detect skin regions, we propose a skin detection method using multi-Bayes classifiers in the paper. Based on skin color detection results, shape features are extracted and fed into a boosted classifier to decide whether or not the skin regions represent a nude. We evaluate adult image detection performance using different boosted classifiers and different shape descriptors. Experimental results show that classification using boosted C4.5 classifier and combination of different shape descriptors outperforms other classification schemes.
The extensive amount of diversified Web-based information necessitates the development of automated subject-specific Web site classification techniques. Given that Web sites are in essence heterogeneous, multi-structu...
详细信息
The extensive amount of diversified Web-based information necessitates the development of automated subject-specific Web site classification techniques. Given that Web sites are in essence heterogeneous, multi-structured and often accompanied with much noise, it is important to design Web site classification algorithms that can scale well in the context of noise and heterogeneity. In this paper, we propose a novel approach for Web site classification based on the content, structure and context information of Web sites. In our approach, the site structure is represented as a two-layered tree, i.e., each page is modeled as a DOM (Document Object Model) tree, and a page tree is used to hierarchically link all pages within the site. Two context models are formulated to characterize the topical dependences between nodes in the two-layered tree. Using the Hidden Markov Tree (HMT) as the statistical model of page trees and DOM trees, a two-phase Web site classification algorithm is presented. Moreover, for further improving accuracy while reducing the classification overheads, a two-stage denoising procedure is adopted to remove the noise information within sites, and an entropy-based strategy is introduced to dynamically prune the page trees. The experiments demonstrate that the proposed approach is able to offer high accuracy and efficient processing performance.
In this paper, a new sign-wise tied mixture HMM (SWTMHMM) is proposed and applied in vision-based sign language recognition (SLR). In the SWTMHMM, the mixture densities of the same sign model are tied so that the stat...
详细信息
暂无评论