Search Results - "Shihao Ji"

Bayesian Compressive Sensing by Shihao Ji, Ya Xue, Carin, L.

“…The data of interest are assumed to be represented as N-dimensional real vectors, and these vectors are compressible in some linear basis B, implying that the…”
Get full text

Multitask Compressive Sensing by Ji, S., Dunson, D., Carin, L.

“…Compressive sensing (CS) is a framework whereby one performs N nonadaptive measurements to constitute a vector v isin R N used to recover an approximation u…”
Get full text

Study on the influence of semiconductive property for the improvement of nanogenerator by wave mode approach by Zhu, Feng, Ji, Shihao, Zhu, Jiaqi, Qian, Zhenghua, Yang, Jiashi

“…Some piezoelectric materials, such as zinc oxide, are semiconductors simultaneously. Usually, the semiconductive property of these materials is omitted in the…”
Get full text

Neural Image Compression and Explanation by Li, Xiang, Ji, Shihao

“…Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of…”
Get full text

Cost-sensitive feature acquisition and classification by Ji, Shihao, Carin, Lawrence

“…There are many sensing challenges for which one must balance the effectiveness of a given measurement with the associated sensing cost. For example, when…”
Get full text

Nonmyopic Multiaspect Sensing With Partially Observable Markov Decision Processes by Shihao Ji, Parr, R., Carin, L.

“…We consider the problem of sensing a concealed or distant target by interrogation from multiple sensors situated on a single platform. The available actions…”
Get full text

Semisupervised Learning of Hidden Markov Models via a Homotopy Method by Shihao Ji, Watson, L.T., Carin, L.

“…Hidden Markov model (HMM) classifier design is considered for the analysis of sequential data, incorporating both labeled and unlabeled data for training; the…”
Get full text

Variational Bayes for continuous hidden Markov models and its application to active learning by Shihao Ji, Krishnapuram, B., Carin, L.

“…In this paper, we present a variational Bayes (VB) framework for learning continuous hidden Markov models (CHMMs), and we examine the VB framework within…”
Get full text

Intent-based diversification of web search results: metrics and algorithms by Chapelle, Olivier, Ji, Shihao, Liao, Ciya, Velipasaoglu, Emre, Lai, Larry, Wu, Su-Lin

“…We study the problem of web search result diversification in the case where intent based relevance scores are available. A diversified search result will…”
Get full text

Adaptive Multimodality Sensing of Landmines by He, L., Shihao Ji, Scott, W.R., Carin, L.

“…The problem of adaptive multimodality sensing of landmines is considered based on electromagnetic induction (EMI) and ground-penetrating radar (GPR) sensors…”
Get full text

Multitask Classification by Learning the Task Relevance by Jun Fang, Shihao Ji, Ya Xue, Carin, L.

“…We consider the problem of multitask learning (MTL), in which we simultaneously learn classifiers for multiple data sets (tasks), with sharing of intertask…”
Get full text

Sparse Graph Attention Networks by Ye, Yang, Ji, Shihao

“…Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art…”
Get full text

Adaptive multiaspect target classification and detection with hidden Markov models by Shihao Ji, Xuejun Liao, Carin, L.

“…Target detection and classification are considered based on backscattered signals observed from a sequence of target-sensor orientations, with the measurements…”
Get full text

MatchXML: An Efficient Text-Label Matching Framework for Extreme Multi-Label Text Classification by Ye, Hui, Sunderraman, Rajshekhar, Ji, Shihao

“…The eXtreme Multi-label text Classification (XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale…”
Get full text

JEM++: Improved Techniques for Training JEM by Yang, Xiulong, Ji, Shihao

“…Joint Energy-based Model (JEM) [12] is a recently proposed hybrid model that retains strong discriminative power of modern CNN classifiers, while generating…”
Get full text

ChiTransformer: Towards Reliable Stereo from Cues by Su, Qing, Ji, Shihao

“…Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size. While single image depth estimation is spared…”
Get full text

Learning with Multiplicative Perturbations by Yang, Xiulong, Ji, Shihao

“…Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial…”
Get full text

Parallelizing Word2Vec in Shared and Distributed Memory by Ji, Shihao, Satish, Nadathur, Li, Sheng, Dubey, Pradeep K.

“…Word2vec is a widely used algorithm for extracting low-dimensional vector representations of words. State-of-the-art algorithms including those by Mikolov et…”
Get full text

Accounting for temporal variability in functional magnetic resonance imaging improves prediction of intelligence by Li, Yang, Ma, Xin, Sunderraman, Raj, Ji, Shihao, Kundu, Suprateek

“…Neuroimaging‐based prediction methods for intelligence have seen a rapid development. Among different neuroimaging modalities, prediction using functional…”
Get full text

A general integrative genomic feature transcription factor binding site prediction method applied to analysis of USF1 binding in cardiovascular disease by Wang, Tianyuan, Furey, Terrence S, Connelly, Jessica J, Ji, Shihao, Nelson, Sarah, Heber, Steffen, Gregory, Simon G, Hauser, Elizabeth R

“…Transcription factors are key mediators of human complex disease processes. Identifying the target genes of transcription factors will increase our…”
Get full text