2,510 Hits in 1.8 sec

Group Membership Prediction [article]

Ziming Zhang, Yuting Chen, Venkatesh Saligrama
2015 arXiv   pre-print
Recently, Zhang et al. [32] proposed an interesting feature representation to handle visual ambiguity and spatial distortion in images for person re-id.  ... 
arXiv:1509.04783v1 fatcat:zf52rxxruvemxmj3iqxnh6xwfy

Perfect codes in vertex-transitive graphs [article]

Yuting Wang, Junyang Zhang
2021 arXiv   pre-print
Very recently, Zhang and Zhou [20] generalized several results about normal subgroups in [10] to general subgroups, and in particular they proved that every subgroup of a group of odd order or odd  ... 
arXiv:2112.06236v1 fatcat:ygj7qld5ezeydb3jd63w4ogwje

Low-rank Regularized Multimodal Representation for Micro-video Event Detection

Jing Zhang, Yuting Wu, Jinghui Liu, Peiguang Jing, Yuting Su
2020 IEEE Access  
Currently, micro-videos are becoming one of the most representative products in the new media age. Although the length of micro-videos is limited to cater to the fast pace of life and are beneficial for rapid distribution, micro-videos are usually recorded in specific scenarios and tend to convey relatively complete events. To more accurately obtain the event types of micro-videos to facilitate potential applications, we propose a low-rank regularized multimodal representation method for
more » ... ideo event detection. To solve the less descriptive power of each modality, the latent common representation of micro-videos is obtained by exploiting complementarity among modalities. A considerable gain in accuracy on this basis can be achieved by further considering the low-rank constraint for the lowest-rank intrinsic representation and a flexible label-relaxation strategy for mappings between representations and their correspondences. A newly constructed micro-video dataset is used to verify the advantages of our proposed model. The experimental results demonstrated the superior performance of our proposed method compared with stateof-the-art methods. INDEX TERMS Micro-video, event detection, multimodal, low-rank representation. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see VOLUME 8, 2020
doi:10.1109/access.2020.2992436 fatcat:wsagxo6qirftxcetqlqshzf26m

Quantifying Robustness to Adversarial Word Substitutions [article]

Yuting Yang, Pei Huang, FeiFei Ma, Juan Cao, Meishan Zhang, Jian Zhang, Jintao Li
2022 arXiv   pre-print
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper
more » ... nd lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises.
arXiv:2201.03829v1 fatcat:qritdyb2ojazvbeigmmppoo2cu

Visual Question Answering on Image Sets [article]

Ankan Bansal, Yuting Zhang, Rama Chellappa
2020 arXiv   pre-print
We introduce the task of Image-Set Visual Question Answering (ISVQA), which generalizes the commonly studied single-image VQA problem to multi-image settings. Taking a natural language question and a set of images as input, it aims to answer the question based on the content of the images. The questions can be about objects and relationships in one or more images or about the entire scene depicted by the image set. To enable research in this new topic, we introduce two ISVQA datasets - indoor
more » ... d outdoor scenes. They simulate the real-world scenarios of indoor image collections and multiple car-mounted cameras, respectively. The indoor-scene dataset contains 91,479 human annotated questions for 48,138 image sets, and the outdoor-scene dataset has 49,617 questions for 12,746 image sets. We analyze the properties of the two datasets, including question-and-answer distributions, types of questions, biases in dataset, and question-image dependencies. We also build new baseline models to investigate new research challenges in ISVQA.
arXiv:2008.11976v1 fatcat:wdehxlf3cfbk7fsevmuh7l76hm

Dynamically Grown Generative Adversarial Networks [article]

Lanlan Liu, Yuting Zhang, Jia Deng, Stefano Soatto
2021 arXiv   pre-print
designs (Li et al. 2019; Nguyen et al. 2017; Zhang et al. 2019; Radford, Metz, and Chintala 2016; Karras et al. 2018) .  ...  GANs Since the proposal of GANs (Goodfellow et al. 2014) , there have been several lines of work to improve GANs, including improving loss functions (Arjovsky, Chintala, and Bottou 2017; Deshpande, Zhang  ... 
arXiv:2106.08505v1 fatcat:wafdk7qlefcevddsqxxsaiorvu

Efficient and Effective Community Search on Large-scale Bipartite Graphs [article]

Kai Wang, Wenjie Zhang, Xuemin Lin, Ying Zhang, Lu Qin, Yuting Zhang
2020 arXiv   pre-print
Wenjie Zhang is supported by ARC DP180103096 and ARC DP200101116. Ying Zhang is supported by FT170100128 and ARC DP180103096. We would like to thank Yizhang He for his proofreading.  ... 
arXiv:2011.08399v1 fatcat:nykvhstjhjdlfpfay75f5wwrp4

Towards Understanding the Invertibility of Convolutional Neural Networks [article]

Anna C. Gilbert, Yi Zhang, Kibok Lee, Yuting Zhang, Honglak Lee
2017 arXiv   pre-print
Many efficient algorithms have been proposed for sparse coding and compressive sensing [Olshausen and others, 1996; Mallat and Zhang, 1993; Beck and Teboulle, 2009] .  ...  Zhang et al. [2016] showed that CNNs discriminately trained for image classification (e.g., VGGNet [Simonyan and Zisserman, 2015] ) are almost fully invertible using pooling switches.  ... 
arXiv:1705.08664v1 fatcat:uetqbzmtgjgurcsf47fsi7xi2u

The Neuroprotective Effect of Tea Polyphenols on the Regulation of Intestinal Flora

Zhicheng Zhang, Yuting Zhang, Junmin Li, Chengxin Fu, Xin Zhang
2021 Molecules  
Tea polyphenols (TPs) are the general compounds of natural polyhydroxyphenols extracted in tea. Although a large number of studies have shown that TPs have obvious neuroprotective and neuro repair effects, they are limited due to the low bioavailability in vivo. However, TPs can act indirectly on the central nervous system by affecting the "microflora–gut–brain axis", in which the microbiota and its composition represent a factor that determines brain health. Bidirectional communication between
more » ... the intestinal microflora and the brain (microbe–gut–brain axis) occurs through a variety of pathways, including the vagus nerve, immune system, neuroendocrine pathways, and bacteria-derived metabolites. This axis has been shown to influence neurotransmission and behavior, which is usually associated with neuropsychiatric disorders. In this review, we discuss that TPs and their metabolites may provide benefits by restoring the imbalance of intestinal microbiota and that TPs are metabolized by intestinal flora, to provide a new idea for TPs to play a neuroprotective role by regulating intestinal flora.
doi:10.3390/molecules26123692 fatcat:dnyyp5mja5fflehyzobfs5g4rq

A comparison theorem under sublinear expectations and related limit theorems [article]

Ning Zhang, Yuting Lan
2017 arXiv   pre-print
In this paper, on the sublinear expectation space, we establish a comparison theorem between independent and convolutionary random vectors, which states that the partial sums of those two sequences of random vectors are identically distributed. Under the sublinear framework, through the comparison theorem, several fundamental limit theorems for convolutionary random vectors are obtained, including the law of large numbers, the central limit theorem and the law of iterated logarithm.
arXiv:1710.01624v1 fatcat:h6xmtj6wxfahzjcedtwzbwgegq


Yuting Xi, Xing Zhang, Ruisong Ye
2016 Zenodo  
This paper proposed a novel color image encryption scheme based on multiple chaotic systems. The ergodicity property of chaotic system is utilized to perform the permutation process; a substitution operation is applied to achieve the diffusion effect. In permutation stage, the 3D color plain-image matrix is converted to a 2D image matrix, then two generalized Arnold maps are employed to generate hybrid chaotic sequences which are dependent on the plain-image's content. The generated chaotic
more » ... ences are then applied to perform the permutation process. The encryption's key streams not only depend on the cipher keys but also depend on plain-image and therefore can resist chosen-plaintext attack as well as known-plaintext attack. In the diffusion stage, four pseudo-random gray value sequences are generated by another generalized Arnold map. The gray value sequences are applied to perform the diffusion process by bitxoring operation with the permuted image row-by-row or column-by-column to improve the encryption rate. The security and performance analysis have been performed, including key space analysis, histogram analysis, correlation analysis, information entropy analysis, key sensitivity analysis, differential analysis etc. The experimental results show that the proposed image encryption scheme is highly secure thanks to its large key space and efficient permutation-substitution operation, and therefore it is suitable for practical image and video encryption.
doi:10.5281/zenodo.3255292 fatcat:qgjljxfhbvfpbbqb6c7qeqqyre

Factors Affecting Chinese Young Adults' Acceptance of Connected Health

Lin Jia, Yuting Tan, Feiyu Han, Yi Zhou, Chu Zhang, Yufei Zhang
2019 Sustainability  
The global health care industry faces several challenges, such as an aging population, insufficient medical resources, and uneven allocation of high-quality medical resources. These challenges impede the development of a sustainable medical care system. Connected health aims to relieve these challenges by deploying information technology in healthcare. However, there is a lack of research on adoption of connected health and as a result, its acceptance rate is still low. This study summarized 25
more » ... potential factors that may affect its acceptance, and ranked their importance by performing a best–worst scaling experiment. Fifteen important factors were distinguished, which included nine technological factors, five individual factors, and one environmental factor. To explore how these factors affect individuals' acceptance of connected health, this study conducted a qualitative study based on grounded theory. We coded the contents collected in a semi-structural interview by applying open coding, axial coding, and selective coding techniques. Finally, nine core categories were distinguished, and a conceptual model was proposed to explain how these core categories affect individuals' acceptance of connected health. This study deepens our understanding of factors affecting the acceptance of connected health and helps build a sustainable medical care system.
doi:10.3390/su11082376 fatcat:h2ozy5idxzgfvgdrzgi65hdgoq

Crucial Roles of miR-625 in Human Cancer

Menggang Zhang, Fei Xiong, Shuijun Zhang, Wenzhi Guo, Yuting He
2022 Frontiers in Medicine  
In addition, Zhang and his colleagues conducted a series of studies to explore the role of miR-625 in glioma.  ...  Zhang et al. found a negative correlation between the expression of miR-625-5p and PKM2 in clinical melanoma specimens (53) .  ... 
doi:10.3389/fmed.2022.845094 pmid:35308517 pmcid:PMC8931282 fatcat:7agete5hu5h6ddeku5jkgpwgxu

On-shelf Utility Mining of Sequence Data [article]

Chunkai Zhang, Zilin Du, Yuting Yang, Wensheng Gan, Philip S. Yu
2020 arXiv   pre-print
Utility mining has emerged as an important and interesting topic owing to its wide application and considerable popularity. However, conventional utility mining methods have a bias toward items that have longer on-shelf time as they have a greater chance to generate a high utility. To eliminate the bias, the problem of on-shelf utility mining (OSUM) is introduced. In this paper, we focus on the task of OSUM of sequence data, where the sequential database is divided into several partitions
more » ... ing to time periods and items are associated with utilities and several on-shelf time periods. To address the problem, we propose two methods, OSUM of sequence data (OSUMS) and OSUMS+, to extract on-shelf high-utility sequential patterns. For further efficiency, we also designed several strategies to reduce the search space and avoid redundant calculation with two upper bounds time prefix extension utility (TPEU) and time reduced sequence utility (TRSU). In addition, two novel data structures were developed for facilitating the calculation of upper bounds and utilities. Substantial experimental results on certain real and synthetic datasets show that the two methods outperform the state-of-the-art algorithm. In conclusion, OSUMS may consume a large amount of memory and is unsuitable for cases with limited memory, while OSUMS+ has wider real-life applications owing to its high efficiency.
arXiv:2011.13455v1 fatcat:ge2xfh4vnjex5e5femowpjpese

Research on Local Humidity Environment of Ground Parking Aircraft

Teng Zhang, Sheng Zhang, Yuting He, Xu Du, Binlin Ma
2018 Applied Sciences  
Zhang [20] measured and statistically analyzed the temperature and humidity inside the tank of grounded aircraft. Jin et al.  ... 
doi:10.3390/app8101917 fatcat:b2hjlneklfaxzdih3t5tmdrl4u
« Previous Showing results 1 — 15 out of 2,510 results