Learn More
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction , representations are formed locally and independent of other regions. We present a novel siamese Long Short-Term Memory (LSTM) architecture that can(More)
In this paper, we propose to learn a discriminative and share-able feature transformation filter bank to transform local image patches (represented as raw pixel values) into features for scene image classification. The learned filters are expected to: (1) encode common visual patterns of a flexible number of categories; (2) encode discriminative and(More)
In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded. In this paper, we introduce recurrent neural networks (RNNs) to address this issue. Specifically, directed acyclic graph RNNs (DAG-RNNs) are proposed to process DAG-structured(More)
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification. As visually similar pixels are indistinguishable from local context, we alleviate such ambiguity by introducing a global scene constraint. We estimate the global potential in a non-parametric framework.(More)
—In the last few years, deep learning has lead to very good performance on a variety of problems, such as object recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Due to the lack of training data and computing power in early days,(More)
Impairments in mood and cognitive function are the key brain abnormalities observed in Gulf war illness (GWI), a chronic multisymptom health problem afflicting ∼25% of veterans who served in the Persian Gulf War-1. Although the precise cause of GWI is still unknown, combined exposure to a nerve gas prophylaxis drug pyridostigmine bromide (PB) and pesticides(More)
In existing convolutional neural networks (CNNs), both convolution and pooling are locally performed for image regions separately, no contextual dependencies between different image regions have been taken into consideration. Such dependencies represent useful spatial structure information in images. Whereas recurrent neural networks (RNNs) are designed for(More)
In this paper, we study the challenging problem of multiobject tracking in a complex scene captured by a single camera. Different from the existing tracklet associationbased tracking methods, we propose a novel and efficient way to obtain discriminative appearance-based tracklet affinity models. Our proposed method jointly learns the convolutional neural(More)
Fully Convolution Networks (FCN) have achieved great success in dense prediction tasks including semantic seg-mentation. In this paper, we start from discussing FCN by understanding its architecture limitations in building a strong segmentation network. Next, we present our Improved Fully Convolution Network (IFCN). In contrast to FCN, IFCN introduces a(More)
Acute seizure (AS) activity in old age has an increased predisposition for evolving into temporal lobe epilepsy (TLE). Furthermore, spontaneous seizures and cognitive dysfunction after AS activity are often intense in the aged population than in young adults. This could be due to an increased vulnerability of inhibitory interneurons in the aged hippocampus(More)