Learn More
We consider the automated recognition of human actions in surveillance videos. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. Convolutional neural networks (CNNs) are a type of deep model that can act directly on the raw inputs. However, such models are currently limited to handling 2D inputs. In(More)
In this paper, we propose a novel document clustering method based on the non-negative factorization of the term-document matrix of the given document corpus. In the latent semantic space derived by the non-negative matrix factorization (NMF), each axis captures the base topic of a particular document cluster, and each document is represented as an additive(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)
In this paper, we present the mQA model, which is able to answer questions about the content of an image. The answer can be a sentence, a phrase or a single word. Our model contains four components: a Long Short-Term Memory (LSTM) to extract the question representation, a Convolutional Neural Network (CNN) to extract the visual representation, an LSTM for(More)
Surprisingly, console logs rarely help operators detect problems in large-scale datacenter services, for they often consist of the voluminous intermixing of messages from many software components written by independent developers. We propose a general methodology to mine this rich source of information to automatically detect system runtime problems. We(More)
— This paper describes a new region-growing algorithm for interferometric synthetic aperture radar (SAR) phase unwrapping. The algorithm is designed to handle noisy interfer-ograms and based on the following principles. 1) Unwrapping is carried out on the perimeter of " growth regions, " and these regions are allowed to grow with consistency checking. 2)(More)
Qualitative Results Experiments m-RNN model for one time frame (a). Our m-RNN model. The model consists of a deep CNN, a deep RNN with two word embedding layers and a multimodal layer connecting the RNN and the CNN. (b). The unfolded m-RNN model. The sentence description of the image is: a man at a giant tree in the jungle. The model parameters are shared(More)
Because of name variations, an author may have multiple names and multiple authors may share the same name. Such name ambiguity affects the performance of document retrieval, web search, database integration, and may cause improper attribution to authors. This paper presents a hierarchical naive Bayes mixture model, an unsupervised learning approach, for(More)
Policy-based confinement, employed in SELinux and specification-based intrusion detection systems, is a popular approach for defending against exploitation of vul-nerabilities in benign software. Conventional access control policies employed in these approaches are effective in detecting privilege escalation attacks. However, they are unable to detect(More)