Learn More
In allusion to the “on-line beforehand decision-making, real time matching”, this paper proposes the stability control flow based on PMU for interconnected power system, which is a real-time stability control. In this scheme, preventive control, emergency control and corrective control are designed to a closed-loop rolling control process, it(More)
We describe a method for articulated human detection and human pose estimation in static images based on a new representation of deformable part models. Rather than modeling articulation using a family of warped (rotated and foreshortened) templates, we use a mixture of small, nonoriented parts. We describe a general, flexible mixture model that jointly(More)
Compared with supervised learning for feature selection, it is muchmore difficult to select the discriminative features in unsupervised learning due to the lack of label information. Traditional unsupervised feature selection algorithms usually select the features which best preserve the data distribution, e.g., manifold structure, of the whole feature set.(More)
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. It directly models the probability distribution of generating a word given previous words and an image. Image captions are generated according to this distribution. The model consists of two sub-networks: a deep recurrent neural network for(More)
We describe a novel image representation termed spatial pyramid co-occurrence which characterizes both the photometric and geometric aspects of an image. Specifically, the co-occurrences of visual words are computed with respect to spatial predicates over a hierarchical spatial partitioning of an image. The representation captures both the absolute and(More)
Hop-by-hop data aggregation is a very important technique for reducing the communication overhead and energy expenditure of sensor nodes during the process of data collection in a sensor network. However, because individual sensor readings are lost in the per-hop aggregation process, compromised nodes in the network may forge false values as the aggregation(More)
In this paper, we present a new multimedia retrieval paradigm to innovate large-scale search of heterogenous multimedia data. It is able to return results of different media types from heterogeneous data sources, e.g., using a query image to retrieve relevant text documents or images from different data sources. This utilizes the widely available data from(More)
Amyotrophic lateral sclerosis (ALS) is a paralytic and usually fatal disorder caused by motor-neuron degeneration in the brain and spinal cord. Most cases of ALS are sporadic but about 5-10% are familial. Mutations in superoxide dismutase 1 (SOD1), TAR DNA-binding protein (TARDBP, also known as TDP43) and fused in sarcoma (FUS, also known as translocated in(More)