arXiv subjects

Jing Yu

Publications and source records attributed to Jing Yu.

At least 145 records · Page 8Linked to original sources

arXiv2020

DARWIN: A Highly Flexible Platform for Imaging Research in Radiology

To conduct a radiomics or deep learning research experiment, the radiologists or physicians need to grasp the needed programming skills, which, however, could be frustrating and costly when they have limited coding experience. In this paper, we present DARWIN, a flexible research platform with a graphical user interface for medical imaging research. Our platform is consists of a radiomics module and a deep learning module. The radiomics module can extract more than 1000 dimension features(first-, second-, and higher-order) and provided many draggable supervised and unsupervised machine learning models. Our deep learning module integrates state of the art architectures of classification, detection, and segmentation tasks. It allows users to manually select hyperparameters, or choose an algorithm to automatically search for the best ones. DARWIN also offers the possibility for users to define a custom pipeline for their experiment. These flexibilities enable radiologists to carry out various experiments easily.

eess.IV↗

arXiv2020

Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering

Knowledge-based Visual Question Answering (KVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing KVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the correct answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. Inspired by the human cognition theory, in this paper, we depict an image by multiple knowledge graphs from the visual, semantic and factual views. Thereinto, the visual graph and semantic graph are regarded as image-conditioned instantiation of the factual graph. On top of these new representations, we re-formulate Knowledge-based Visual Question Answering as a recurrent reasoning process for obtaining complementary evidence from multimodal information. To this end, we decompose the model into a series of memory-based reasoning steps, each performed by a G raph-based R ead, U pdate, and C ontrol ( GRUC ) module that conducts parallel reasoning over both visual and semantic information. By stacking the modules multiple times, our model performs transitive reasoning and obtains question-oriented concept representations under the constrain of different modalities. Finally, we perform graph neural networks to infer the global-optimal answer by jointly considering all the concepts. We achieve a new state-of-the-art performance on three popular benchmark datasets, including FVQA, Visual7W-KB and OK-VQA, and demonstrate the effectiveness and interpretability of our model with extensive experiments.

cs.AI↗

arXiv2020

KBGN: Knowledge-Bridge Graph Network for Adaptive Vision-Text Reasoning in Visual Dialogue

Visual dialogue is a challenging task that needs to extract implicit information from both visual (image) and textual (dialogue history) contexts. Classical approaches pay more attention to the integration of the current question, vision knowledge and text knowledge, despising the heterogeneous semantic gaps between the cross-modal information. In the meantime, the concatenation operation has become de-facto standard to the cross-modal information fusion, which has a limited ability in information retrieval. In this paper, we propose a novel Knowledge-Bridge Graph Network (KBGN) model by using graph to bridge the cross-modal semantic relations between vision and text knowledge in fine granularity, as well as retrieving required knowledge via an adaptive information selection mode. Moreover, the reasoning clues for visual dialogue can be clearly drawn from intra-modal entities and inter-modal bridges. Experimental results on VisDial v1.0 and VisDial-Q datasets demonstrate that our model outperforms existing models with state-of-the-art results.

cs.CV↗

arXiv2020

DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1.0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is available at https://github.com/JXZe/DAM.

cs.CV↗

arXiv2020

Achieving Performance and Safety in Large Scale Systems with Saturation using a Nonlinear System Level Synthesis Approach

We present a novel class of nonlinear controllers that interpolates among differently behaving linear controllers as a case study for recently proposed Linear and Nonlinear System Level Synthesis framework. The structure of the nonlinear controller allows for simultaneously satisfying performance and safety objectives defined for small- and large-disturbance regimes. The proposed controller is distributed, handles delays, sparse actuation, and localizes disturbances. We show our nonlinear controller always outperforms its linear counterpart for constrained LQR problems. We further demonstrate the anti-windup property of an augmented control strategy based on the proposed controller for saturated systems via simulation.

eess.SY↗

arXiv2020

Resilience for Landslide Geohazards and Promoting Strategies in the Three Gorges Reservoir Area

Recently, resilience is increasingly used as a concept for understanding natural disaster systems. Landslide is one of the most frequent geohazards in the Three Gorges Reservoir Area (TGRA).However, it is difficult to measure local disaster resilience, because of special geographical location in the TGRA and the special disaster landslide. Current approaches to disaster resilience evaluation are usually limited either by the qualitative method or properties of different disaster. Therefore, practical evaluating methods for the disaster resilience are needed. In this study, we developed an indicator system to evaluate landslides disaster resilience in the TGRE at the county level. It includes two properties of inherent geological stress and external social response, which are summarized into physical stress and social forces. The evaluated disaster resilience can be simulated for promoting strategies with fuzzy cognitive map (FCM).

stat.AP↗

arXiv2019

Solving Optimal Experimental Design with Sequential Quadratic Programming and Chebyshev Interpolation

We propose an optimization algorithm to compute the optimal sensor locations in experimental design in the formulation of Bayesian inverse problems, where the parameter-to-observable mapping is described through an integral equation and its discretization results in a continuously indexed matrix whose size depends on the mesh size n. By approximating the gradient and Hessian of the objective design criterion from Chebyshev interpolation, we solve a sequence of quadratic programs and achieve the complexity $\mathcal{O}(n\log^2(n))$. An error analysis guarantees the integrality gap shrinks to zero as $n\to\infty$, and we apply the algorithm on a two-dimensional advection-diffusion equation, to determine the LIDAR's optimal sensing directions for data collection.

stat.CO↗

arXiv2019

DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects, relationships or semantics. The key challenge in Visual Dialogue task is thus to learn a more comprehensive and semantic-rich image representation which may have adaptive attentions on the image for variant questions. In this research, we propose a novel model to depict an image from both visual and semantic perspectives. Specifically, the visual view helps capture the appearance-level information, including objects and their relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Futhermore, on top of such multi-view image features, we propose a feature selection framework which is able to adaptively capture question-relevant information hierarchically in fine-grained level. The proposed method achieved state-of-the-art results on benchmark Visual Dialogue datasets. More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values. It gives us insights in understanding of human cognition in Visual Dialogue.

cs.CV↗

arXiv2019

Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering

One of the key issues of Visual Question Answering (VQA) is to reason with semantic clues in the visual content under the guidance of the question, how to model relational semantics still remains as a great challenge. To fully capture visual semantics, we propose to reason over a structured visual representation - scene graph, with embedded objects and inter-object relationships. This shows great benefit over vanilla vector representations and implicit visual relationship learning. Based on existing visual relationship models, we propose a visual relationship encoder that projects visual relationships into a learned deep semantic space constrained by visual context and language priors. Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer. We demonstrate the model's effectiveness and interpretability on the challenging GQA dataset and the classical VQA 2.0 dataset, remarkably achieving state-of-the-art 54.56% accuracy on GQA compared to the existing best model.

cs.MM↗

arXiv2019

Dual Reweighted Lp-Norm Minimization for Salt-and-pepper Noise Removal

The robust principal component analysis (RPCA), which aims to estimate underlying low-rank and sparse structures from the degraded observation data, has found wide applications in computer vision. It is usually replaced by the principal component pursuit (PCP) model in order to pursue the convex property, leading to the undesirable overshrink problem. In this paper, we propose a dual weighted lp-norm (DWLP) model with a more reasonable weighting rule and weaker powers, which greatly generalizes the previous work and provides a better approximation to the rank minimization problem for original matrix as well as the l0-norm minimization problem for sparse data. Moreover, an approximate closed-form solution is introduced to solve the lp-norm minimization, which has more stability in the nonconvex optimization and provides a more accurate estimation for the low-rank and sparse matrix recovery problem. We then apply the DWLP model to remove salt-and-pepper noise by exploiting the image nonlocal self-similarity. Both qualitative and quantitative experiments demonstrate that the proposed method outperforms other state-of-the-art methods. In terms of PSNR evaluation, our DWLP achieves about 7.188dB, 5.078dB, 3.854dB, 2.536dB and 0.158dB improvements over the current WSNM-RPCA under 10\% to 50\% salt-and-pepper noise with an interval 10\% respectively.

cs.CV↗

arXiv2019

Semantic Modeling of Textual Relationships in Cross-Modal Retrieval

Feature modeling of different modalities is a basic problem in current research of cross-modal information retrieval. Existing models typically project texts and images into one embedding space, in which semantically similar information will have a shorter distance. Semantic modeling of textural relationships is notoriously difficult. In this paper, we propose an approach to model texts using a featured graph by integrating multi-view textual relationships including semantic relations, statistical co-occurrence, and prior relations in the knowledge base. A dual-path neural network is adopted to learn multi-modal representations of information and cross-modal similarity measure jointly. We use a Graph Convolutional Network (GCN) for generating relation-aware text representations, and use a Convolutional Neural Network (CNN) with non-linearities for image representations. The cross-modal similarity measure is learned by distance metric learning. Experimental results show that, by leveraging the rich relational semantics in texts, our model can outperform the state-of-the-art models by 3.4% and 6.3% on accuracy on two benchmark datasets.

cs.MM↗

arXiv2018

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity

Blind image deconvolution is the problem of recovering the latent image from the only observed blurry image when the blur kernel is unknown. In this paper, we propose an edge-based blur kernel estimation method for blind motion deconvolution. In our previous work, we incorporate both sparse representation and self-similarity of image patches as priors into our blind deconvolution model to regularize the recovery of the latent image. Since almost any natural image has properties of sparsity and multi-scale self-similarity, we construct a sparsity regularizer and a cross-scale non-local regularizer based on our patch priors. It has been observed that our regularizers often favor sharp images over blurry ones only for image patches of the salient edges and thus we define an edge mask to locate salient edges that we want to apply our regularizers. Experimental results on both simulated and real blurry images demonstrate that our method outperforms existing state-of-the-art blind deblurring methods even for handling of very large blurs, thanks to the use of the edge mask.

cs.CV↗

arXiv2018

Approximability of the Eight-vertex Model

We initiate a study of the classification of approximation complexity of the eight-vertex model defined over 4-regular graphs. The eight-vertex model, together with its special case the six-vertex model, is one of the most extensively studied models in statistical physics, and can be stated as a problem of counting weighted orientations in graph theory. Our result concerns the approximability of the partition function on all 4-regular graphs, classified according to the parameters of the model. Our complexity results conform to the phase transition phenomenon from physics. We introduce a quantum decomposition of the eight-vertex model and prove a set of closure properties in various regions of the parameter space. Furthermore, we show that there are extra closure properties on 4-regular planar graphs. These regions of the parameter space are concordant with the phase transition threshold. Using these closure properties, we derive polynomial time approximation algorithms via Markov chain Monte Carlo. We also show that the eight-vertex model is NP-hard to approximate on the other side of the phase transition threshold.

cs.CC↗

arXiv2018

Modeling Text with Graph Convolutional Network for Cross-Modal Information Retrieval

Cross-modal information retrieval aims to find heterogeneous data of various modalities from a given query of one modality. The main challenge is to map different modalities into a common semantic space, in which distance between concepts in different modalities can be well modeled. For cross-modal information retrieval between images and texts, existing work mostly uses off-the-shelf Convolutional Neural Network (CNN) for image feature extraction. For texts, word-level features such as bag-of-words or word2vec are employed to build deep learning models to represent texts. Besides word-level semantics, the semantic relations between words are also informative but less explored. In this paper, we model texts by graphs using similarity measure based on word2vec. A dual-path neural network model is proposed for couple feature learning in cross-modal information retrieval. One path utilizes Graph Convolutional Network (GCN) for text modeling based on graph representations. The other path uses a neural network with layers of nonlinearities for image modeling based on off-the-shelf features. The model is trained by a pairwise similarity loss function to maximize the similarity of relevant text-image pairs and minimize the similarity of irrelevant pairs. Experimental results show that the proposed model outperforms the state-of-the-art methods significantly, with 17% improvement on accuracy for the best case.

cs.IR↗

arXiv2016

The Simulation of Non-Abelian Statistics of Majorana Fermions in Ising Chain with Z2 Symmetry

In this paper, we numerically study the non-Abelian statistics of the zero-energy Majorana fermions on the end of Majorana chain and show its application to quantum computing by mapping it to a spin model with special symmetry. In particular, by using transverse-field Ising model with Z2 symmetry, we verify the nontrivial non-Abelian statistics of Majorana fermions. Numerical evidence and comparison in both Majorana-representation and spin-representation are presented. The degenerate ground states of a symmetry protected spin chain therefore previde a promising platform for topological quantum computation.

cond-mat.mes-hall↗

arXiv2015

An effective criterion for Eulerian multizeta values in positive characteristic

Characteristic p multizeta values were initially studied by Thakur, who defined them as analogues of classical multiple zeta values of Euler. In the present paper we establish an effective criterion for Eulerian multizeta values, which characterizes when a multizeta value is a rational multiple of a power of the Carlitz period. The resulting "t-motivic" algorithm can tell whether any given multizeta value is Eulerian or not. We also prove that if zeta_A(s_1,...,s_r) is Eulerian, then zeta_A(s_2,...,s_r) has to be Eulerian. When r=2, this was conjectured (and later on conjectured for arbitrary r) by Lara Rodriguez and Thakur for the zeta-like case from numerical data. Our methods apply equally well to values of Carlitz multiple polylogarithms at algebraic points and zeta-like multizeta values.

math.NT↗

arXiv2015

A pharmacokinetic -- viral kinetic model describes the effect of alisporivir monotherapy or in combination with peg-IFN on 2 hepatitis C virologic response

Alisporivir is a cyclophilin inhibitor with demonstrated in vitro and in vivo activity against hepatitis C 11 virus (HCV). We estimated antiviral effectiveness of alisporivir alone or in combination with 12 pegylated-Inteferon (peg-IFN) in 88 patients infected with different HCV genotypes treated for four 13 weeks. The pharmacokinetics of both drugs were modeled and used as driving functions for the viral 14 kinetic model. Genotype was found to significantly affect pegylated-Inteferon effectiveness ($ε$= 86.3% 15 and 99.1% in genotype-1/4 and genotype-2/3, respectively, p\textless{}10 -7) and infected cells loss rate ($δ$= 16 0.22 vs 0.39 day -1 in genotype-1/4 and genotype-2/3, respectively, p\textless{}10 -6). Alisporivir effectiveness 17 was not significantly different across genotype and was high for doses $\ge$600 mg QD. We simulated 18 virologic responses with other alisporivir dosing regimens in HCV genotype-2/3 patients using the 19 model. Our predictions consistently matched the observed responses, demonstrating that this model 20 could be a useful tool for anticipating virologic response and optimize alisporivir-based therapies.

q-bio.QM↗

arXiv2012

Preparation of NOON State Induced by Macroscopic Quantum Tunneling in an Ising Chain

In this brief report, we propose a possible way, theoretically and experimentally, to generate a NOON state of the two degenerate ferromagnetic ground states of the Transverse Ising Model. In our scheme we employ the macroscopic quantum tunneling (MQT) effect between the two degenerate ferromagnetic ground states to realize the NOON state. Our calculation about the MQT process is based on a higher-order degenerate perturbation method. After doing a transformation, the MQT process could also be treated as the hopping of individual virtual fermions in the spin chain, which will leads to an analytical description of tunneling process. The experimental feasibility for generating the NOON state is discussed in the setup of linear ion trap.

quant-ph↗