Re-identifying the same person in different images is a distinct challenge for visual surveillance systems. Building an accurate correspondence between highly variable images requires a suitable dissimilarity measure. To date, most existing measures have used adapted distance based on a learned metric. Unfortunately, real-world human image data, which tends to show large intra-class variations ...

We propose a new type system for Java-like languages which allows compilation of a class in isolation, that is, in a context where no information is available on other classes. Indeed, by this type system it is possible to infer the assumptions guaranteeing type correctness of a class c, and generate (abstract) bytecode for c, by just inspecting the source code of c. Then, a collection of class...

The bag-of-visual-words (BOVW) approaches are widely used in human action recognition. Usually, large vocabulary size of the BOVW is more discriminative for inter-class action classification while small one is more robust to noise and thus tolerant to the intra-class invariance. In this pape, we propose a pyramid vocabulary tree to model local spatio-temporal features, which can characterize th...

With the emergence of rich online content, efficient information retrieval systems are required. Application content includes rich text, speech, still images and videos. This content, either stored or queried, can be assigned to many classes or labels at the same time. This calls for the use of multi-label classification techniques. In this paper, a new kernel-basedmulti-label classification al...

Linear discriminant analysis (LDA) is a well-known scheme for supervised subspace learning. It has been widely used in the applications of computer vision and pattern recognition. However, an intrinsic limitation of LDA is the sensitivity to the presence of outliers, due to using the Frobenius norm to measure the inter-class and intra-class distances. In this paper, we propose a novel rotationa...

Word spotting is to make searchable unindexed image documents by locating word/words in a doc-ument image, given a query word. This problem is challenging, mainly due to the large numberof word classes with very small inter-class and substantial intra-class distances. In this paper, asegmentation-based word spotting method is presented for multi-writer Persian handwritten doc-...

New network applications which involve transmission of continuous media data such as au dio and video conferencing introduce immense challenges for the design of packet switching internetworks Existing ow and congestion control mechanisms have been shown to be ine ec tive for supporting the real time requirements of continuous media data transfers We propose a novel bandwidth regulation mechani...

This paper proposes new inter{agent and intra{agent negotiation mechanisms for improving the performance of multi{agent or decentralized manufacturing systems. The overall performance of this system depends on the eeective interactions between agents. This research presents methods which would permit cooperation and multi{stage interactions among agents. Agents may collaborate or preempt other ...

[Purpose] The purpose of this study was to translate the Trunk Control Measurement Scale into a Korean version and to analyze the intra- and inter-rater reliability. [Subjects and Methods] Fifteen children with spastic cerebral palsy and four physical therapists with over 10 years of clinical experience participated in this study. A Korean-American physical therapist translated the trunk contro...

This paper is focused on the Rate and Time Continuous Fluid Simulation technology (RTC-FSIM) [Ber02a], [Ber02b] a modular and extendable simulation technology based on differential equations paradigm realised in MATLAB and SIMULINK. RTC-FSIM is intended to be used in INTERMON [INTERMON] project for QoS based inter-domain modelling and simulation considering priority classes to describe traffic ...