An epidemic model gives an efficient approach for transaction processing of replication systems in weakly connected environments. The approach has the advantages of high adaptation, support for low-bandwidth network, and committing updates in an entirely decentralized control fashion. But the previous implementing protocols, like ROWA protocol, quorum protocol, and voting protocol, have a common shortcoming that they are pessimistic in conict reconciliation, therefore bring high transaction abort rate and reduce system perfor-mance dramatically when the workload scales up. In this paper, an optimistic voting protocol, which introduces condition vote and order vote in the voting process of transactions, is pro-posed. The condition vote and order vote postpone the nal decision on con icting transactions and avoid transaction aborts that are incurred by read-write and write-write concts. Exper-imental results indicate thatthe optimistic voting protocol decreases abort rate and improvesaverage response time of transactions markedly when compared to other protocols.

Real-time face tracking and 3D reconstruction from video is a challenge in computer graphics and computer vision. We develop a system to track face by integrating image pyramid algorithm and Kalman filter. First, Facial features of the first frame are acquired automatically by Plessey corner detector according to FDP in MPEG-4 and FACS based on anatomical knowledge and general 3D model. And then corner disparity is obtained by image pyramid algorithm and Kalman filter. Kalman filter is employed to resolve the tracking speed and occlusion problems. Finally, 3D model is reconstructed by SfM (Structure from motion). Experimental results show the high prospect of this algorithm, and the two issues of real-time face tracking and modeling are resolved in our algorithm.

With the increasing number of people who can afford to make videos to record their lives, home videos play more and more important role in multimedia. Video abstraction is an efficient way to help review such a huge amount of home videos. In this paper, a home video abstraction technique combining audio and video features is presented. The audio contents are firstly classified as silence, pure speech, non-pure speech, music and background sound using SVMs. Then non-pure speech is further classified into song and other non-pure speechusing SVM. and background sound is classified into laughter, applause, scream and others using Hidden Markov Models (HMMs). For video contents, motion level and blur degree are acquired. Finally, video segments containing special effects, such as speech, laughter, song, applause, scream, and specified motion level and blur degree, are extracted as the main parts of the abstract. The remaining parts of the abstract are generated using key frame infonllation The experimental results show that the proposed algorithm can extract desired parts of home video to generate satisfactory video abstracts.

An approach to user-assisted video object extraction at pixellevel framework that aims at reducing users' workload while making full use of user interaction. The framework takes over multi-pass scan on a video sequence and bidirectional tracking on the sequence's sub-shots during each pass. Systems based on this framework can not only free users from laborious work, but also be allowed to embed various complex but effective tracking algorithms. To fulfill a system, we propose an extended Intelligent Scissors for machine to precisely track VOs. The approach to tracking is a multi-level process, locating VO boundaries from a coarse level to a fine one and yielding pixelaccurate results of extraction. Experiments on MPEG test sequences show that this approach together with the proposed framework performs well in practice.

A new method is proposed for real-time video object segmentation from static background under shadows and varying lighting. The method firstly learns a statistical model and a type model for a background scene in HSV space. The latter one represents the reflection characteristic of object surface in background and helps decide whether hue or saturation component should be used to detect changes in the statistical model. In the stage of change detection, multi-criteria decision is taken in order to deal with various lightness conditions such as shadows. At last a speedup morphologic filter and a connected components labeling algorithm will refine segmentation results. The method makes full and better use of color information in images. The capability of accurate segmentation and real-time execution is demonstrated for several test and practical video sequences.

In this paper, a Customizable and Dynamic Locking (CDL) scheme is proposed for concurrency control in Internet-based real-time collaborative editors. The idea of dynamic-locking is that: locking mechanism dynamically determines locking set according to locking policies and latest collaborative activities happened in the shared workspace, and pre-locks objects for succeeding editing and preventing from other user's edit. Dynamic locking is optional: user decides whether and when to use locking mechanism. In the proposed scheme, locking policy is separated from locking mechanism. Locking policies can be customized for different collaboration tasks. Locking scope is dynamically determined according to locking policies and collaborative activities among users. Multiple users can select different policies in the same collaborative session, and change locking policies at different phases of collaboration as well. Protocols and algorithms for locking conflict resolution and consistency maintenance are also presented in this paper.

Active Shape Models (ASM) is a powerful statistical tool for extracting objects, e.g. face, from images. It is composed of two parts: ASM model and ASM search. In ASM, these two parts are treated separately. First, ASM model is trained. Then, ASM search is performed using this model. However, we find that these two parts are closely interrelated. The performance of ASM depends on both of them. Improvement on one of them does not consequentially improve the overall performance, for it may worsen the other. In this paper, we find the key parameter that relates these two parts: subspace explanation proportion. By optimizing subspace explanation proportion, the overall performance of ASM can improve by a percentage of about 20 in our experiments. Furthermore, this paper proposes to decompose the ASM overall error into ASM model subspace reconstruction error and ASM search error, proving that the square of the subspace reconstruction error is linearly related with the subspace explanation proportion and finding that the square of the search error is a piecewise function of the explanation proportion. This decomposition is a new method for further analysis and possible improvement. Based on this decomposition, we propose a method to estimate the optimal explanation proportion. Experiments show that the estimation is satisfactory.

Bitmap-based collaborative graphics editing systems are a special class of real-time collaborative editing systems. Undo is an important and difficult problem in these systems. Existing solutions show low efficiency because additional space cost should be added to achieve the function of undo. In this paper, we propose a new solution to resolve the undo problem. The basic idea is to reduce space cost through exploring relations among operations. The algorithm given in the paper can undo any operation a any time, and can greatly reduce the space cost while increasing a few time cost. The issues about undo scope and undo mode are also discussed in the paper.

This paper proposes a reversible color transform for 16-bit-color (hicolor) picture coding. The work is motivated by the increasing needs of multimedia applications on low-end devices such as mobile phones and PDAs. They have limited resources and up to 16-bit displays. Current image/video coding systems can hardly manage this case effectively. To enhance coding efficiency on this condition, a reversible color transform customized for hicolor systems is derived from Y'CrCb and JPEG2000 Reversible Component Transformation (RCT). The transform proves simple but highly-decorrelating, and able to reduce the computation time of decoding. Comparison experiment demonstrates the effectiveness of this transform with equal or even higher coding efficiency on low-end devices with 16-bit display mode.

Emotion recognition is one of the latest challenges in intelligent human/computer communication. Most of previous work on emotion recognition focused on extracting emotions from visual or audio information separately. A novel approach is presented in this paper, including both visual and audio from video clips, to recognize the human emotion. The Facial Animation Parameters (FAPs) compliant facial feature tracking based on active appearance model is performed on the video to generate two vector stream which represent the expression feature and the visual speech one. Combined with the visual vectors, the audio vector is extracted in terms of low level features. Then, a tripled Hidden Markov Model is introduced to perform the recognition which allows the state asynchrony of the audio and visual observation sequences while preserving their natural correlation over time. The experimental results show that this approach outperforms only using visual or audio separately.