In order to improve the video text recognition performance, this paper provided a new video text enhancement approach. The core of the algorithm relies on using texture fusion in a coarse-to-fine scheme. First, featur...
详细信息
Warping is a common appearance in camera captured document images. It is the primary factor that makes such kind of document images hard to be recognized. Therefore it is necessary to restore warped document image bef...
详细信息
We study the possibility of performing perfect teleportation of unknown quantum states from multiple senders to a single receiver with a previously shared stabilizer state. In the model we considered, the utilized sta...
详细信息
We study the possibility of performing perfect teleportation of unknown quantum states from multiple senders to a single receiver with a previously shared stabilizer state. In the model we considered, the utilized stabilizer state is partitioned into several subsystems and then each subsystem is distributed to a distinct party. We present two sufficient conditions for a stabilizer state to achieve a given nonzero teleportation capacity with respect to a given partition plan. The corresponding teleportation protocols are also explicitly given. Interestingly, we find that even mixed stabilizer states are also useful for perfect many-to-one teleportation. Finally, our work provides a perspective from stabilizer formalism to view the standard teleportation protocol and also suggests a technique for analyzing teleportation capability of multipartite entangled states.
We consider the possibility of using stabilizer states to perform deterministic dense coding among multiple senders and a single receiver. In the model we studied, the utilized stabilizer state is partitioned into sev...
详细信息
We consider the possibility of using stabilizer states to perform deterministic dense coding among multiple senders and a single receiver. In the model we studied, the utilized stabilizer state is partitioned into several subsystems and then each subsystem is held by a distinct party. We present a sufficient condition for a stabilizer state to be useful for deterministic distributed dense coding with respect to a given partition plan. The corresponding protocol is also constructed. Furthermore, we propose a method to partially solve a more general problem of finding the set of achievable alphabet sizes for an arbitrary stabilizer state with respect to an arbitrary partition plan. Finally, our work provides a perspective from the stabilizer formalism to view the standard dense coding protocol and also unifies several previous results in a single framework.
The web is growing at a rapid speed and it is almost impossible for a web crawler to download all new pages. Pages reporting breaking news should be stored into search engine index as soon as they are published, while...
详细信息
We show that any two different unitary operations acting on an arbitrary multipartite quantum system can be perfectly distinguished by local operations and classical communication when a finite number of runs is allow...
详细信息
We show that any two different unitary operations acting on an arbitrary multipartite quantum system can be perfectly distinguished by local operations and classical communication when a finite number of runs is allowed. Intuitively, this result indicates that the lost identity of a nonlocal unitary operation can be recovered locally. No entanglement between distant parties is required.
The idea of local learning, i.e., classifying a particular example based on its neighbors, has been successfully applied to many semi-supervised and clustering problems recently. However, the local learning methods de...
详细信息
The Universum data, defined as a collection of "non-examples" that do not belong to any class of interest, have been shown to encode some prior knowledge by representing meaningful concepts in the same domai...
详细信息
作者：
Liu LinquanCenter for Speech Technology
State Key Laboratory of Intelligent Technology and Systems Department of Computer Science ＆ Technology Tsinghua University Beijing 100084 China
Abstract:With respect to dialectal-accented speech recognition, dialect-specific lexicon adaptation is anindispensable component to improve the performance. In this paper, a phone-based confusion matrix isadopted to o...
详细信息
Abstract:With respect to dialectal-accented speech recognition, dialect-specific lexicon adaptation is anindispensable component to improve the performance. In this paper, a phone-based confusion matrix isadopted to obtain dialect-specific pronunciation variants. A weighting method, improved context-dependentweighting (ICDW) is proposed to characterize the pronunciation probability precisely by taking both thesurface form left-context-dependency and the base form left-context-dependency into account. To make amuch robust lexicon, a pruning criterion, syllable-dependent pruning (SDP), is also proposed which achievesthe most effective result. In summary, the dialect-specific dialect adaptation reduces a 2.9% absolute anda 3.6% absolute in syllable error rate (SER) respectively on read speech and spontaneous speech fromShanghai-accented speakers.
Automatic image annotation (AIA) refers to the association of words to whole images which is considered as a promising and effective approach to bridge the semantic gap between low-level visual features and high-level...
详细信息
Automatic image annotation (AIA) refers to the association of words to whole images which is considered as a promising and effective approach to bridge the semantic gap between low-level visual features and high-level semantic concepts. In this paper, we formulate the task of image annotation as a multi-label multi class semantic image classification problem and propose a simple yet effective algorithm: hybrid self-learning with alternating space between uni-modality and bi-modality, which integrate multi-label boosting with asymmetric binary SVM-based active learning into a joint hierarchical classification framework to perform cross-modal image annotation by incorporating unlabeled images. We conducted experiments on a medium-sized image collection including about 15000 images from Corel Stock Photo CDs. The experimental results demonstrated that our proposed method can enhance a given annotation model by using unlabeled images to some extent, showing the effectiveness of the proposed algorithm and the feasibility of unlabeled data to help the annotation accuracy.
暂无评论