检索结果-内蒙古大学图书馆

WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zeng, Jishen Tan, Shunquan Liu, Guangqing Li, Bin Huang, Jiwu Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Guangdong Key Lab. of Intelligent Info. Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Peng Cheng Laboratory Shenzhen518052 China

Until recently, deep steganalyzers in spatial domain have been all designed for gray-scale images. In this paper, we propose WISERNet (the wider separate-then-reunion network) for steganalysis of color images. We provide theoretical rationale to claim that the summation in normal convolution is one sort of "linear collusion attack" which reserves strong correlated patterns while impairs uncorrelated noises. Therefore in the bottom convolutional layer which aims at suppressing correlated image contents, we adopt separate channel-wise convolution without summation instead. Conversely, in the upper convolutional layers we believe that the summation in normal convolution is beneficial. Therefore we adopt united normal convolution in those layers and make them remarkably wider to reinforce the effect of "linear collusion attack". As a result, our proposed wide-and-shallow, separate-then-reunion network structure is specifically suitable for color image steganalysis. We have conducted extensive experiments on color image datasets generated from BOSSBase raw images and another large-scale dataset which contains 100,000 raw images, with di_erent demosaicking algorithms and downsampling algorithms. The experimental results show that our proposed network outperforms other state-of-the-art color image steganalytic models either hand-crafted or learned using deep networks in the literature by a clear margin. Specifically, it is noted that the detection performance gain is achieved with less than half the complexity compared to the most advanced deeplearning steganalyzer as far as we know, which is scarce in the literature. Copyright © 2018, The Authors. All rights reserved.

关键词： Steganography

Automatic Chinese Multiple-Choice Question Generation for Human Resource Performance Appraisal

学校读者我要写书评

暂无评论

Procedia Computer Science 2018年 139卷 165-172页

作者： Pei Quan Yong Shi Lingfeng Niu Ying Liu Tianlin Zhang School of Computer and Control Engineering University of Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA

Performance appraisal has always been an important research topic in human resource management. A reasonable performance appraisal plan lays a solid foundation for the development of an enterprise. Especially as globalization and technology advance, in order to meet the fast-changing strategic goals and increasing cross-functional tasks, enterprises face new challenges in performance appraisal. How to improve employees’ ability to accept new knowledge efficiently and constantly has been an urgent problem for enterprises. In this paper, we propose an automatic method which generation multiple-choice questions by utilizing the relations between different terminology. Graphical model is used to extract core concept from different corpus while word embedding technology is used to indicate the relevant relations. Experimental results demonstrate that the proposed question generation method outperforms the traditional manual method in both efficiency and confusion.

关键词： Human resource management multiple-choice question generation natural language processing word embedding

New parameter-free mobility model: Opportunity priority selection model

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Erjian Yan, Xiao-Yong Key Lab. of Integrated Transportation Big Data Application Technology for Transportation Industry Beijing Jiaotong University Beijing100044 China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing100044 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China

Predicting human mobility patterns has many practical applications in urban planning, traffic engineering, infectious disease epidemiology, emergency management and location-based services. Developing a universal model capable of accurately predicting the mobility fluxes between locations is a fundamental and challenging problem in regional economics and transportation science. Here, we propose a new parameter-free model named opportunity priority selection model as an alternative in human mobility prediction. The basic assumption of the model is that an individual will select destination locations that present higher opportunity benefits than the location opportunities of the origin and the intervening opportunities between the origin and destination. We use real mobility data collected from a number of cities and countries to demonstrate the predictive ability of this simple model. The results show that the new model offers universal predictions of intracity and intercity mobility patterns that are consistent with real observations, thus suggesting that the proposed model better captures the mechanism underlying human mobility than previous models. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

Robust latent poisson deconvolution from multiple imperfect features for web topic detection

学校读者我要写书评

暂无评论

Robust latent poisson deconvolution from multiple imperfect ...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Fei Tao Junbiao Pang Chunjie Zhang Liang Li Li Su Weigang Zhang Qingming Huang Guiping Su School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China College of Metropolitan Transportation Beijing University of Technology China Key Lab on Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9781467372596

In web topic detection, detecting “hot” topics from enormous User-Generated Content (UGC) on web data poses two main difficulties that conventional approaches can barely handle: 1) poor feature representations from noisy images and short texts; and 2) uncertain roles of modalities where visual content is either highly or weakly relevant to textual cues due to less-constrained data. In this paper, following the detection by ranking approach, we address the problem by learning a robust shared representation from multiple, noisy and complementary features, and integrating both textual and visual graphs into a k-Nearest Neighbor Similarity Graph (k-N 2 SG). Then Non-negative Matrix Factorization using Random walk (NMFR) is introduced to generate topic candidates. An efficient fusion of multiple graphs is then done by a Latent Poisson Deconvolution (LPD) which consists of a poisson deconvolution with sparse basis similarities for each edge. Experiments show significantly improved accuracy of the proposed approach in comparison with the state-of-the-art methods on two public data sets.

关键词： Visualization Deconvolution Robustness Feature extraction Optimization Correlation Noise measurement

Smartphone-based video surveillance system

学校读者我要写书评

暂无评论

Journal of Computational Information Systems 2014年第17期10卷 7637-7644页

作者： Ling, Wenjing Zheng, Limin Wang, Tianzi Wu, Ping Song, Zheng College of Information and Electrical Engineering China Agricultural University Beijing China Beijing Laboratory of Food Quality and Safety China Agricultural University Beijing China Tongfang Knowledge Network Technology Co. Ltd. Beijing China State Key Lab. of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China

Smartphone based surveillance systems have gained popularity against camera-based surveillance systems for cost-efficiency and ease of deployment. However, existing smartphone-based surveillance systems need expensive additional devices to achieve the remote control functions of pan-tilt-zoom cameras, which limits their usage. In this paper, we present a smartphone-based video surveillance system with steering function and remote control operations. To realize the function of steering, a small clip is creatively used as a pedestal, while the vibration motor and digital compass embedded in the smartphone are responsible for rotation generating and orientation control, respectively. A set of protocols for remote control operations are also provided. Real-testbed based experiments show that the steering system is easy to deploy and very accurate, with an average rotation deviation less than 2.500 degrees. The latency of remote control under real network conditions is satisfactory, with an average time delay less than 5 seconds.

关键词： Smartphones

The minority matters: a diversity-promoting collab.rative metric learning algorithm 22

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative me...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

Simulation of two-phase flows at large density ratios and high Reynolds numbers using a discrete unified gas kinetic scheme

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lai, Jun Xiao, Zuoli Wang, Lian-Ping State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing100871 China Guangdong Provincial Key Laboratory of Turbulence Research and Applications Center for Complex Flows and Soft Matter Research Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Jt. Lab. for Data-Driven Fluid Mechanics and Engineering Applications Southern University of Science and Technology Shenzhen518055 China

In order to treat immiscible two-phase flows at large density ratios and high Reynolds numbers, a three-dimensional code based on the discrete unified gas kinetic scheme (DUGKS) is developed, incorporating two major improvements. First, the particle distribution functions at cell interfaces are reconstructed using a weighted essentially non-oscillatory scheme. Second, the conservative lower-order Allen-Cahn equation is chosen, instead of the higher-order Cahn-Hilliard equation, to evolve the free-energy-based phase field governing the dynamics of two-phase interfaces. Five benchmark problems are simulated to demonstrate the capability of the approach in treating two-phase flows at large density ratios and high Reynolds numbers, including three two-dimensional problems (a stationary droplet, Rayleigh-Taylor instability, and a droplet splashing on a thin liquid film) and two three-dimensional problems (binary droplets collision and Rayleigh-Taylor instability). All results agree well with the previous numerical and the experimental results. In these simulations, the density ratio and Reynolds number can reach a large value of O(1000). Our improved approach sets the stage for the DUGKS scheme to handle realistic two-phase flow problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Reynolds number

GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gu, Zhouhong Jiang, Sihang Liu, Jingping Xiao, Yanghua Feng, Hongwei Li, Zhixu Liang, Jiaqing Zhong, Jian Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Information Science and Engineering East China University of Science and Technology China Fudan-Aishu Cognitive Intelligence Joint Research Center China School of Data Science Fudan University China HUAWEI CBG Edu AI Lab. China

Taxonomy is formulated as directed acyclic concepts graphs or trees that support many downstream tasks. Many new coming concepts need to be added to an existing taxonomy. The traditional taxonomy expansion task aims only at finding the best position for new coming concepts in the existing taxonomy. However, they have two drawbacks when being applied to the real-scenarios. The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts. They also suffer from low-effectiveness since they collect training samples only from the existing taxonomy, which limits the ability of the model to mine more hypernym-hyponym relationships among real concepts. This paper proposes a pluggable framework called Generative Adversarial Network for Taxonomy Entering Evaluation (GANTEE) to alleviate these drawbacks. A generative adversarial network is designed in this framework by discriminative models to alleviate the first drawback and the generative model to alleviate the second drawback. Two discriminators are used in GANTEE to provide long-term and short-term rewards, respectively. Moreover, to further improve the efficiency, pre-trained language models are used to retrieve the representation of the concepts quickly. The experiments on three real-world large-scale datasets with two different languages show that GANTEE improves the performance of the existing taxonomy expansion methods in both effectiveness and efficiency. © 2023, CC BY.

关键词： Taxonomies

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Vi...

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings