The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Influenced by the grammatical system of western languages, there are more and more syntactic structures in modern Chinese that can be translated into English attributive clauses. But for the great differences of the syntactic structures, parsing Chinese by western grammatical rules usually does not lead to satisfactory results, which will result in poor translation performance in complex syntactic...
In this paper, we propose to use acoustic feature based submodular function optimization to select a subset of untranscribed data for manual transcription, and retrain the initial acoustic model with the additional transcribed data. The acoustic features are obtained from an unsupervised Gaussian mixture model. We also integrate the acoustic features with the phonetic features, which are obtained...
In this paper, we present an action recognition framework based on binary stochastic latent variables model, Hidden unit Conditional Random Fields(HuCRF). It is a chain structured undirected graphs model with nonlinear dependencies at each frame/segment, contrast to standard log-linear models like CRF. So it is more powerful in sequence modeling tasks like action recognition. The observations of actions...
Action recognition is always a very active and challenging research topic in the field of computer vision. Kinect, as a motion sensing input device which can capture both color and depth images, open up new possibilities of dealing with this task. In this paper, we build a system to track and classify the human action based on the Microsoft Kinect technology. During the feature extraction step, we...
In this paper, a robust gait recognition algorithm based on key frame and ellipse model is proposed, which solves the problems including finding key frames on discontinuous contour segmentation and accurate feature extraction on ellipse model. Firstly, a robust extraction algorithm of key fame is introduced, which makes detection of key fames easier and more accurate. Secondly, human bodies corresponding...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.