检索结果-内蒙古大学图书馆

VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Su, Jiajun Wang, Chunyu Ma, Xiaoxuan Zeng, Wenjun Wang, Yizhou Center for Data Science Peking University China Center on Frontiers of Computing Studies Peking University China Dept. of Computer Science Peking University China Inst. for Artificial Intelligence Peking University China Microsoft Research Asia China EIT Institute for Advanced Study United States

While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find that they get notably larger errors when tested on different cameras, human poses and appearance. To address the problem, we introduce VirtualPose, a two-stage learning framework to exploit the hidden "free lunch" specific to this task, i.e. generating infinite number of poses and cameras for training models at no cost. To that end, the first stage transforms images to abstract geometry representations (AGR), and then the second maps them to 3D poses. It addresses the generalization issue from two aspects: (1) the first stage can be trained on diverse 2D datasets to reduce the risk of over-fitting to limited appearance;(2) the second stage can be trained on diverse AGR synthesized from a large number of virtual cameras and poses. It outperforms the SOTA methods without using any paired images and 3D poses from the benchmarks, which paves the way for practical applications. Code is available at https://***/wkom/VirtualPose. Copyright © 2022, The Authors. All rights reserved.

关键词： Cameras

On the Violation of Honesty in Mobile Apps: Automated Detection and Categories

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Obie, Humphrey O. Ilekura, Idowu Du, Hung Shahin, Mojtaba Grundy, John Li, Li Whittle, Jon Turhan, Burak HumaniSE Lab Monash University Melbourne Australia Data Science Nigeria Lagos Nigeria Applied Artificial Intelligence Inst. Deakin University Melbourne Australia School of Computing Technologies RMIT University Melbourne Australia Faculty of IT Monash University Melbourne Australia CSIRO's Data61 Melbourne Australia University of Oulu Oulu Finland

Human values such as integrity, privacy, curiosity, security, and honesty are guiding principles for what people consider important in life. Such human values may be violated by mobile software applications (apps), and the negative effects of such human value violations can be seen in various ways in society. In this work, we focus on the human value of honesty. We present a model to support the automatic identification of violations of the value of honesty from app reviews from an end-user perspective. Beyond the automatic detection of honesty violations by apps, we also aim to better understand different categories of honesty violations expressed by users in their app reviews. The result of our manual analysis of our honesty violations dataset shows that honesty violations can be characterised into ten categories: unfair cancellation and refund policies;false advertisements;delusive subscriptions;cheating systems;inaccurate information;unfair fees;no service;deletion of reviews;impersonation;and fraudulent-looking apps. Based on these results, we argue for a conscious effort in developing more honest software artefacts including mobile apps, and the promotion of honesty as a key value in software development practices. Furthermore, we discuss the role of app distribution platforms as enforcers of ethical systems supporting human values, and highlight some proposed next steps for human values in software engineering (SE) research. © 2022, CC BY.

关键词： Application programs

One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yin, Zihao Gong, Ping Wang, Chunyu Yu, Yizhou Wang, Yizhou Center for Data Science Peking University Beijing China Deepwise AI Lab Beijing China Microsoft Research Asia Beijing China The University of Hong Kong Hong Kong Center on Frontiers of Computing Studies School of Computer Science Peking University Beijing China Inst. for Artificial Intelligence Peking University Beijing China

As an important upstream task for many medical applications, supervised landmark localization still requires non-negligible annotation costs to achieve desirable performance. Besides, due to cumbersome collection procedures, the limited size of medical landmark datasets impacts the effectiveness of large-scale self-supervised pre-training methods. To address these challenges, we propose a two-stage framework for one-shot medical landmark localization, which first infers landmarks by unsupervised registration from the labeled exemplar to unlabeled targets, and then utilizes these noisy pseudo labels to train robust detectors. To handle the significant structure variations, we learn an end-to-end cascade of global alignment and local deformations, under the guidance of novel loss functions which incorporate edge information. In stage II, we explore self-consistency for selecting reliable pseudo labels and cross-consistency for semi-supervised learning. Our method achieves state-of-the-art performances on public datasets of different body parts, which demonstrates its general applicability. Copyright © 2022, The Authors. All rights reserved.

关键词： Medical applications

TOM2C: TARGET-ORIENTED MULTI-AGENT COMMUNICATION AND COOPERATION WITH THEORY OF MIND

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yuanfei Zhong, Fangwei Xu, Jing Wang, Yizhou Center for Data Science Peking University China School of Artificial Intelligence Peking University China Center on Frontiers of Computing Studies School of Computer Science Peking University China Adv. Inst. of Info. Tech Peking University China China

Being able to predict the mental states of others is a key factor to effective social interaction. It is also crucial for distributed multi-agent systems, where agents are required to communicate and cooperate. In this paper, we introduce such an important social-cognitive skill, i.e. Theory of Mind (ToM), to build socially intelligent agents who are able to communicate and cooperate effectively to accomplish challenging tasks. With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation. Based on the inferred states, the agents decide "when" and with "whom" to share their intentions. With the information observed, inferred, and received, the agents decide their sub-goals and reach a consensus among the team. In the end, the low-level executors independently take primitive actions to accomplish the sub-goals. We demonstrate the idea in two typical target-oriented multi-agent tasks: cooperative navigation and multi-sensor target coverage. The experiments show that the proposed model not only outperforms the state-of-the-art methods on reward and communication efficiency, but also shows good generalization across different scales of the environment. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

Context modeling in 3D human pose estimation: A unified perspective

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Xiaoxuan Su, Jiajun Wang, Chunyu Ci, Hai Wang, Yizhou Dept. of Computer Science Center on Frontiers of Computing Studies Peking University China Center for Data Science Adv. Inst. of Info. Tech. Peking University China Beijing Film Academy China Microsoft Research Asia Deepwise AI Lab

Estimating 3D human pose from a single image suffers from severe ambiguity since multiple 3D joint configurations may have the same 2D projection. The state-of-the-art methods often rely on context modeling methods such as pictorial structure model (PSM) or graph neural network (GNN) to reduce ambiguity. However, there is no study that rigorously compares them side by side. So we first present a general formula for context modeling in which both PSM and GNN are its special cases. By comparing the two methods, we found that the end-to-end training scheme in GNN and the limb length constraints in PSM are two complementary factors to improve results. To combine their advantages, we propose ContextPose based on attention mechanism that allows enforcing soft limb length constraints in a deep network. The approach effectively reduces the chance of getting absurd 3D pose estimates with incorrect limb lengths and achieves state-of-the-art results on two benchmark datasets. More importantly, the introduction of limb length constraints into deep networks enables the approach to achieve much better generalization performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

FlickerNet: Adaptive 3D gesture recognition from sparse point clouds 30

学校读者我要写书评

暂无评论

FlickerNet: Adaptive 3D gesture recognition from sparse poin...

30th British Machine Vision Conference, BMVC 2019

作者： Min, Yuecong Chai, Xiujuan Zhao, Lei Chen, Xilin Inst. of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Lab of Agricultural Big Data Ministry of Agriculture Beijing100081 China HUAWEI Technologies CO. LTD. Beijing100095 China

Recent studies on gesture recognition use deep convolutional neural networks (CNNs) to extract spatio-temporal features from individual frames or short video clips. However, extracting features frame-by-frame will bring a lot of redundant and ambiguous gesture information. Inspired by the flicker fusion phenomena, we propose a simple but efficient network, called FlickerNet, to recognize gesture from a sequence of sparse point clouds sampled from depth videos. Different from the existing CNN-based methods, FlickerNet can adaptively recognize hand postures and hand motions from the flicker of gestures: the point clouds of the stable hand postures and the sparse point-cloud motion for fast hand motions. Notably, FlickerNet significantly outperforms the previous state-of-the-art approaches on two challenging datasets with much higher computational efficiency. © 2019. The copyright of this document resides with its authors.

关键词： Computational efficiency

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Mingzhou Zheng, Xiangyu Sun, Xinwei Fang, Fang Wang, Yizhou Sch. of Computer Science Peking University China Center on Frontiers of Computing Studies Peking University China Dep. of Statistics Guanghua Sch. of Management Peking University China Sch. of Data Science Fudan University China Sch. of Psychological and Cognitive Sciences Peking University China Inst. for Artificial Intelligence Peking University China

A major barrier to deploying current machine learning models lies in their non-reliability to dataset shifts. To resolve this problem, most existing studies attempted to transfer stable information to unseen environments. Particularly, independent causal mechanisms-based methods proposed to remove mutable causal mechanisms via the do-operator. Compared to previous methods, the obtained stable predictors are more effective in identifying stable information. However, a key question remains: which subset of this whole stable information should the model transfer, in order to achieve optimal generalization ability? To answer this question, we present a comprehensive minimax analysis from a causal perspective. Specifically, we first provide a graphical condition for the whole stable set to be optimal. When this condition fails, we surprisingly find with an example that this whole stable set, although can fully exploit stable information, is not the optimal one to transfer. To identify the optimal subset under this case, we propose to estimate the worst-case risk with a novel optimization scheme over the intervention functions on mutable causal mechanisms. We then propose an efficient algorithm to search for the subset with minimal worst-case risk, based on a newly defined equivalence relation between stable subsets. Compared to the exponential cost of exhaustively searching over all subsets, our searching strategy enjoys a polynomial complexity. The effectiveness and efficiency of our methods are demonstrated on synthetic data and the diagnosis of Alzheimer’s disease. © 2021, CC BY.

关键词： Optimization

Detection and Blocking of DGA-based Bot Infected Computers by Monitoring NXDOMAIN Responses

学校读者我要写书评

暂无评论

Detection and Blocking of DGA-based Bot Infected Computers b...

IEEE International Conference on Cyber Security and Cloud computing (CSCloud)

作者： Yuki Iuchi Yong Jin Hikaru Ichise Katsuyoshi Iida Yoshiaki Takai Graduate School of Information Science and Technology Hokkaido Univ. Sapporo Japan Global Scientific Information and Computing Center Tokyo Inst. Tech. Tokyo Japan Technical Department Tokyo Inst. Tech. Tokyo Japan Information Initiative Center Hokkaido Univ. Sapporo Japan

ISBN: (数字)9781728165509

ISBN: (纸本)9781728165516

Cyberattacks by botnets keep on increasing. In this research, we aim to detect and block Domain Generation Algorithm (DGA)-based bot-infected computers by focusing on the characteristics of domain name resolution for searching the Command & Control (C&C) servers. The attackers register only few of the DGA-based domain names for the C&C servers and make the bot-infected computers search them using DNS domain name resolution for the further inst.uctions. This makes the DNS domain name resolution in C&C server searching process inevitably causing NXDOMAIN responses for queries about nonexistence domain names. In this paper, we designed and implemented a detection and blocking system against.DGA-based bot-infected computers searching for the C&C servers by analyzing the DNS traffic resulted with NXDOMAIN responses. According to the feature evaluation results, we confirmed that the prototype system was effective for multiple types of DGA-based bots thus the approach could be applicable to detect and block the malicious DNS traffic from the bot-infected computers at the early stage.

关键词： Bot DNS DGA NXDOMAIN and SDN domain name server domain name resolution Computers Domain name blocking system Servers Attackers

Multiple Pseudo-Local Feedbacks for Controlling High-Order Oscillatory Objects 15

学校读者我要写书评

暂无评论

Multiple Pseudo-Local Feedbacks for Controlling High-Order O...

15th International Scientific-Technical Conference on Actual Problems of Electronic inst.ument Engineering, APEIE 2021

作者： Zhmud, V.A. Nosek, J. Mansurova, M.E. Semibalamut, V.M. Fomin, Yu. N. Stukach, O.V. Novosibirsk State Technical University Institute of Laser Physics Sb Ras Dept. of Automation Novosibirsk Russia Technical University of Liberec Inst. of Mechatronics and Computer Engineering Liberec Czech Republic Al-Farabi Kazakh National University Department of Artificial Intelligence and Big Data Almaty Kazakhstan Unified Geophysical Service of the Russian Academy of Sciences Siberian Branch of the Federal State Budgetary Institution of Science of the Federal Research Center Novosibirsk Russia Novosibirsk State Technical University Higher School of Economics Dept. of Information Defense Moscow Russia

ISBN: (纸本)9781665434089

Development of the Internet of things (IoT) technologies arises many additional problems as energy harvesting. In particular, a long-Time controlling object needs a device without an external power supply. The control of technical objects with a high order of mathematical model has a large difficulty if a feature of the object is a high tendency to oscillations due to the ratio of the coefficients in the model. In particular, the tendency to oscillations occurs if the object model has complex roots, or if the model has a transport delay. One such example is a model that consists of two oscillatory objects and a delay loop. Widespread controlling such an objects using a PID controller is very difficult since in the transient process in the resulting system there is a large overshoot and many oscillations. If such an object could be stabilized with additional local feedbacks, the control task would be greatly simplified, but the object does not have corresponding outputs and inputs, therefore local feedbacks cannot be used. The pseudo-local feedback approach assumes the use of virtual fragments of the object's mathematical model in the controller to form such connections that the system perceives as local ones. This paper proposed the use of several pseudo-local feedbacks to control an object with elements that increased its tendency to oscillate. The effectiveness of the proposed approach is confirmed by modeling. © 2021 IEEE.

关键词： Feedback