检索结果-内蒙古大学图书馆

作者： Hubschman, Harold Zucker, Steven W. Computer Vision and Graphics Laboratory Department of Electrical Engineering McGill University MontrealQC Canada

Frame-to-frame coherence is the highly structured relationship that exists between successive frames of certain animation sequences. From the point of view of the hidden surface computation, this implies that parts of the scene will become visible or invisible in a predictable fashion. In this paper the frame-to-frame coherence constraints are identified and characterized for static scenes restricted to stationary, closed, convex, nonintersecting polyhedra. The animation derives from a continuous movement of the viewer. The mathematical analysis of the constraints is geometric and leads to a characterization of the self-occlusion or change of self-occlusion relationship over a single polyhedron, and to a characterization of the occlusion or change of occlusion relationship over two polyhedra. On the basis of these constraints, an algorithm which generates successive frames in an animation sequence is presented. © 1982 ACM.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Training sequential on-line boosting classifier for visual tracking

Training sequential on-line boosting classifier for visual t...

引用

作者： Grabner, Helmut Šochman, Jan Bischof, Horst Matas, Jiří Institute for Computer Graphics and Vision Graz University of Technology Austria Center for Machine Perception Czech Technical University Prague Czech Republic Computer Vision Laboratory ETH Zurich Switzerland

ISBN: (纸本)9781424421756

On-line boosting allows to adapt a trained classifier to changing environmental conditions or to use sequentially available training data. Yet, two important problems in the on-line boosting training remain unsolved: (i) classifier evaluation speed optimization and, (ii) automatic classifier complexity estimation. In this paper we show how the on-line boosting can be combined with Wald's sequential decision theory to solve both of the problems. The properties of the proposed on-lineWaldBoost algorithm are demonstrated on a visual tracking problem. The complexity of the classifier is changing dynamically depending on the difficulty of the problem. On average, a speedup of a factor of 5-10 is achieved compared to the non-sequential on-line boosting. © 2008 IEEE.

关键词： Decision theory

来源：评论

学校读者我要写书评

暂无评论

FAST3D: Flow-Aware Self-Training for 3D Object Detectors 32

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

引用

32nd British Machine vision Conference, BMVC 2021

作者： Fruhwirth-Reisinger, Christian Opitz, Michael Possegger, Horst Bischof, Horst Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria Amazon

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g. geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method that enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art. © 2021. The copyright of this document resides with its authors.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

TAEC: Unsupervised action segmentation with temporal-Aware embedding and clustering 26

TAEC: Unsupervised action segmentation with temporal-Aware e...

引用

26th computer vision Winter Workshop, CVWW 2023

作者： Lin, Wei Kukleva, Anna Possegger, Horst Kuehne, Hilde Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Austria Max-Planck-Institute for Informatics Germany Goethe University Frankfurt Germany

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To address this issue, we propose an unsupervised approach for learning action classes from untrimmed video sequences. In particular, we propose a temporal embedding network that combines relative time prediction, feature reconstruction, and sequence-To-sequence learning, to preserve the spatial layout and sequential nature of the video features. A two-step clustering pipeline on these embedded feature representations then allows us to enforce temporal consistency within, as well as across videos. Based on the identified clusters, we decode the video into coherent temporal segments that correspond to semantically meaningful action classes. Our evaluation on three challenging datasets shows the impact of each component and, furthermore, demonstrates our state-of-The-Art unsupervised action segmentation results. © 2023 Copyright for this paper by its authors.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A virtual reality platform for dynamic human-scene interaction 16

A virtual reality platform for dynamic human-scene interacti...

引用

2016 SIGGRAPH ASIA Virtual Reality Meets Physical Reality: Modelling and Simulating Virtual Humans and Environments, SA 2016

作者： Lin, Jenny Guo, Xingwen Shao, Jingyu Jiang, Chenfanfu Zhu, Yixin Zhu, Song-Chun UCLA Center for Vision Cognition Learning and Autonomy United States University of Hong Kong Electrical and Electronic Engineering Department Hong Kong UCLA Computer Graphics and Vision Laboratory United States

ISBN: (纸本)9781450345484

Both synthetic static and simulated dynamic 3D scene data is highly useful in the fields of computer vision and robot task planning. Yet their virtual nature makes it difficult for real agents to interact with such data in an intuitive way. Thus currently available datasets are either static or greatly simplified in terms of interactions and dynamics. In this paper, we propose a system in which Virtual Reality and human/finger pose tracking is integrated to allow agents to interact with virtual environments in real time. Segmented object and scene data is used to construct a scene within Unreal Engine 4, a physics-based game engine. We then use the Oculus Rift headset with a Kinect sensor, Leap Motion controller and a dance pad to navigate and manipulate objects inside synthetic scenes in real time. We demonstrate how our system can be used to construct a multi-jointed agent representation as well as fine-grained finger pose. In the end, we propose how our system can be used for robot task planning and image semantic segmentation. © 2016 Copyright held by the owner/author(s). SA '16, December 05-08 2016.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Stability analysis for the generalized Hopfield neural networks with multi-level activation functions

Stability analysis for the generalized Hopfield neural netwo...

引用

作者： Liu, Yiguang You, Zhisheng Institute of Image and Graphics Key Laboratory of Fundamental Synthetic Vision Graphics and Image for National Defense Sichuan University Chengdu 610064 China School of Computer Science and Engineering Sichuan University Chengdu 610064 China

Using the continuity property of neuron state variables and Lyapunov functional, this paper religiously gives sufficient conditions ensuring the equilibrium number, local stable state number, global stability and complete stability of the Hopfield neural networks with multi-level activation functions. Compared with the known relevant literatures, the obtained results are more precise. Finally, three examples are employed to illustrate the obtained criteria. © 2008 Elsevier B.V. All rights reserved.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic computation of fundamental matrix based on voting 1st

Automatic computation of fundamental matrix based on voting

引用

1st International Conference on Smart Multimedia, ICSM 2018

作者： Li, Xin Sheng Yuan, Xuedong College of Computer Science Sichuan University ChengDu China Key Laboratory of Fundamental Synthetic Vision Graphics and Image for National Defense Sichuan University ChengDu China

ISBN: (纸本)9783030043742

To reconstruct point geometry from multiple images, a new method to compute the fundamental matrix is proposed in this paper. This method uses a new selection method for fundamental matrix under the RANSAC (Random Sample And Consensus) framework. It makes good use of some low quality fundamental matrices to fuse a better quality fundamental matrix. At first, some fundamental matrices are computed as candidates in a few iterations. Then some of the best candidates are chosen based on voting the epipoles of their fundamental matrices to fuse a better fundamental matrix. The fusion can be simple mean or weighted summation of fundamental matrices from the first step. This selection method leads to better result such as more inliers or less projective errors. Our experiments prove and validate this new method of composed fundamental matrix computation. © 2018, Springer Nature Switzerland AG.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

PET-Train: Automatic Ground Truth Generation from PET Acquisitions for Urinary Bladder Segmentation in CT Images using Deep Learning 11

PET-Train: Automatic Ground Truth Generation from PET Acquis...

引用

11th Biomedical Engineering International Conference, BMEiCON 2018

作者： Gsaxner, Christina Pfarrkirchner, Birgit Lindner, Lydia Pepe, Antonio Roth, Peter M. Egger, Jan Wallner, Jurgen Inst. of Computer Graphics and Vision Graz University of Technology Graz Austria Department of Maxillofacial Surgery Medical University of Graz Graz Austria Computer Algorithms for Medicine Laboratory Graz Austria

ISBN: (纸本)9781538657249

In this contribution, we propose an automatic ground truth generation approach that utilizes Positron Emission Tomography (PET) acquisitions to train neural networks for automatic urinary bladder segmentation in Computed Tomography (CT) images. We evaluated different deep learning architectures to segment the urinary bladder. However, deep neural networks require a large amount of training data, which is currently the main bottleneck in the medical field, because ground truth labels have to be created by medical experts on a time-consuming slice-by-slice basis. To overcome this problem, we generate the training data set from the PET data of combined PET/CT acquisitions. This can be achieved by applying simple thresholding to the PET data, where the radiotracer accumulates very distinct in the urinary bladder. However, the ultimate goal is to entirely skip PET imaging and its additional radiation exposure in the future, and only use CT images for segmentation. © 2018 IEEE.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

arXiv

引用

arXiv 2021年

作者： Oner, Doruk Kozinski, Mateusz Citraro, Lenoardo Fua, Pascal The Computer Vision Laboratory EPFL Switzerland The Institute of Computer Vision and Graphics TU Graz Austria

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data is often hard to interpret visually and in part because the 3D interfaces are awkward to use. In this paper, we introduce a method that explicitly accounts for annotation inaccuracies. To this end, we treat the annotations as active contour models that can deform themselves while preserving their topology. This enables us to jointly train the network and correct potential errors in the original annotations. The result is an approach that boosts performance of deep networks trained with potentially inaccurate annotations. Code has been released at https://***/dorukoner/AdjustingAnnotationswithSnakes. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking 32

DRT: Detection Refinement for Multiple Object Tracking

引用

32nd British Machine vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：