检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Desai, Aadesh Parikh, Saagar Kumari, Seema Raman, Shanmuganathan Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics. However, processing point clouds using deep learning-based algorithms is quite challenging due to the irregular point formats. Voxelization or 3D grid-based representation are different ways of applying deep neural networks to this problem. In this paper, we propose PointResNet, a residual block-based approach. Our model directly processes the 3D points, using a deep neural network for the segmentation and classification tasks. The main components of the architecture are: 1) residual blocks and 2) multi-layered perceptron (MLP). We show that it preserves profound features and structural information, which are useful for segmentation and classification tasks. The experimental evaluations demonstrate that the proposed model produces the best results for segmentation and comparable results for classification in comparison to the conventional baselines. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MULTI-TASK LEARNING FOR CAMERA CALIBRATION

arXiv

引用

arXiv 2022年

作者： Butt, Talha Hanif Taj, Murtaza Computer Vision and Graphics Lab Lahore University of Management Sciences Lahore Pakistan

For a number of tasks, such as 3D reconstruction, robotic interface, autonomous driving, etc., camera calibration is essential. In this study, we present a unique method for predicting intrinsic (principal point offset and focal length) and extrinsic (baseline, pitch, and translation) properties from a pair of images. We suggested a novel method where camera model equations are represented as a neural network in a multi-task learning framework, in contrast to existing methods, which build a comprehensive solution. By reconstructing the 3D points using a camera model neural network and then using the loss in reconstruction to obtain the camera specifications, this innovative camera projection loss (CPL) method allows us that the desired parameters should be estimated. As far as we are aware, our approach is the first one that uses an approach to multi-task learning that includes mathematical formulas in a framework for learning to estimate camera parameters to predict both the extrinsic and intrinsic parameters jointly. Additionally, we provided a new dataset named as CVGL Camera Calibration Dataset [1] which has been collected using the CARLA Simulator [2]. Actually, we show that our suggested strategy outperforms both conventional methods and methods based on deep learning on 6 out of 10 parameters that were assessed using both real and synthetic data. Our code and generated dataset are available at https://***/thanif/Camera-Calibration-through-Camera-Projection-Loss. © 2022, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Reflecting on Excellence: VR Simulation for Learning Indirect vision in Complex Bi-Manual Tasks

Reflecting on Excellence: VR Simulation for Learning Indirec...

引用

IEEE Annual International Symposium Virtual Reality

作者： Maximilian Kaluschke Rene Weller Myat Su Yin Benedikt W. Hosp Farin Kulapichitr Siriwan Suebnukarn Peter Haddawy Gabriel Zachmann Computer Graphics & VR University of Bremen Faculty of ICT Mahidol University ZEISS Vision Science Lab University of Tübingen Faculty of Dentistry Thammasat University

Indirect vision through a mirror, while bi-manually manipulating both the mirror and another tool is a relatively common way to perform operations in various types of surgery. However, learning such psychomotor skills requires extensive training; they are difficult to teach; and they can be quite costly, for instance, for dentistry schools. In order to study the effectiveness of VR simulators for learning these kinds of skills, we developed a simulator for training dental surgery procedures, which supports tracking of eye gaze and tool trajectories (mirror and drill), as well as automated outcome scoring. We carried out a pre-/post-test study in which 30 fifth-year dental students received six training sessions in the access opening stage of the root canal procedure using the simulator. In addition, six experts performed three trials using the simulator. The outcomes of drilling performed on realistic plastic teeth showed a significant learning effect due to the training sessions. Also, students with larger improvements in the simulator tended to improve more in the real-world tests. Analysis of the tracking data revealed novel relationships between several metrics w.r.t. eye gaze and mirror use, and performance and learning effectiveness: high rates of correct mirror placement during active drilling and high continuity of fixation on the tooth are associated with increased skills and increased learning effectiveness. Larger time allocation for tooth inspections using the mirror, i.e., indirect vision, and frequency of inspection are associated with increased learning effectiveness. Our findings suggest that eye tracking can provide valuable insights into student learning gains of bi-manual psychomotor skills, particularly in indirect vision environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CUDA and Applications to Task-based Programming

CUDA and Applications to Task-based Programming

引用

42nd Annual Conference on European Association for computer graphics, EUROgraphics 2021

作者： Kenzel, M. Kerbl, B. Winter, M. Steinberger, M. Saarland University Computer Graphics Lab Germany TU Wien Institute of Visual Computing and Human-Centered Technology Austria Graz University of Technology Institute of Computer Graphics and Vision Austria

ISBN: (纸本)9783038681359

Since its inception, the CUDA programming model has been continuously evolving. Because the CUDA toolkit aims to consistently expose cutting-edge capabilities for general-purpose compute jobs to its users, the added features in each new version reflect the rapid changes that we observe in GPU architectures. Over the years, the changes in hardware, growing scope of built-in functions and libraries, as well as an advancing C++ standard compliance have expanded the design choices when coding for CUDA, and significantly altered the directives to achieve peak performance. In this tutorial, we give a thorough introduction to the CUDA toolkit, demonstrate how a contemporary application can benefit from recently introduced features and how they can be applied to task-based GPU scheduling in particular. For instance, we will provide detailed examples of use cases for independent thread scheduling, cooperative groups, and the CUDA standard library, libcu++, which are certain to become an integral part of clean coding for CUDA in the near future. © 2021 The Author(s).

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge

arXiv

引用

arXiv 2023年

作者： Lin, Wei Karlinsky, Leonid Shvetsova, Nina Possegger, Horst Kozinski, Mateusz Panda, Rameswar Feris, Rogerio Kuehne, Hilde Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria MIT-IBM Watson AI Lab United States Goethe University Frankfurt Germany

Large scale vision Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other exciting tasks. However, VL models tend to over-represent objects while paying much less attention to verbs, and require additional tuning on video data for best zero-shot action recognition performance. While previous work relied on large-scale, fully-annotated data, in this work we propose an unsupervised approach. We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary. Based on that, we leverage Large Language Models and VL models to build a text bag for each unlabeled video via matching, text expansion and captioning. We use those bags in a Multiple Instance Learning setup to adapt an image-text backbone to video data. Although finetuned on unlabeled video data, our resulting models demonstrate high transferability to numerous unseen zero-shot downstream tasks, improving the base VL model performance by up to 14%, and even comparing favorably to fully-supervised baselines in both zero-shot and few-shot video recognition transfer. The code will be released later at https://***/wlin-at/MAXI. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Teacher-Class Network: A Neural Network Compression Mechanism 32

Teacher-Class Network: A Neural Network Compression Mechanis...

引用

32nd British Machine vision Conference, BMVC 2021

作者： Malik, Shaiq Munir Tharani, Mohbat Haider, Muhammad Umair Rasheed, Muhammad Musab Taj, Murtaza Computer Vision and Graphics Lab Lahore Univ. of Management Sciences Lahore Pakistan Rensselaer Polytechnic Institute New York United States

To reduce the overwhelming size of Deep Neural Networks, teacher-student techniques aim to transfer knowledge from a complex teacher network to a simple student network. We instead propose a novel method called the teacher-class network consisting of a single teacher and multiple student networks (class of students). Instead of transferring knowledge to one student only, the proposed method divides learned space into sub-spaces, and each sub-space is learned by a student. Our students are not trained for problem-specific logits;they are trained to mimic knowledge (dense representation) learned by the teacher network;thus, the combined knowledge learned by the class of students can be used to solve other problems. The proposed teacher-class architecture is evaluated on several benchmark datasets such as MNIST, Fashion MNIST, IMDB Movie Reviews, CIFAR-10, and ImageNet on multiple tasks such as image and sentiment classification. Our approach outperforms the state-of-the-art single student approach in terms of accuracy and computational cost while achieving a 10−30 times reduction in parameters. Code is available at https://***/musab-r/TCN. © 2021. The copyright of this document resides with its authors.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

ROStopbox: A Human-Centered Vehicle Environment Data Acquisition System

ROStopbox: A Human-Centered Vehicle Environment Data Acquisi...

引用

Automated Vehicle Validation Conference (IAVVC), IEEE International

作者： Daniel Schneider Jonas Nesensohn Bernhard Schick Daniel Watzenig Institute for Advanced Driver Assistance Systems and Connected Mobility Kempten University of Applied Sciences Institute of Computer Graphics and Vision Graz University of Technology AVL Deutschland GmbH Advanced Solution Lab Karlsruhe

ISBN: (数字)9798350354072

ISBN: (纸本)9798350354089

As the development towards fully automated driving continues, passenger trust in automation and human well-being when using advanced driver assistance systems will become increasingly important. To support the existing data-driven development process, systems for acquiring perceptual data such as from camera and LiDAR along with physiological and subjective information will be required in the future. The simultaneous recording of physiological signals alongside data from traditional perception sensors can therefore help to identify scenarios in which passengers are stressed, have an increased workload, or feel unsafe. By recording questionnaires in parallel, it is possible to also correlate the physiological signals with passengers’ subjective perception. The combination of these signal sources makes it possible to identify causes of drivers’ increased workload in the environmental data, describe development targets, and safeguard rules for future assistance systems and automated driving functions, keeping humans in the loop. Here, we present an approach for the simultaneous acquisition of sensor information from multiple domains such as physiological measurement data, environmental sensors, vehicle-internal communication, and subjective questionnaires, paying attention to an unobtrusive measurement setup. We demonstrate the benefits of our approach by identifying a relevant scenario in real traffic conditions in which we observe the impact on the driver’s physiological parameters.

关键词： Laser radar Operating systems Data acquisition Human factors Cameras Physiology Human in the loop Sensors Recording Testing

来源：评论

学校读者我要写书评

暂无评论

Video Test-Time Adaptation for Action Recognition

Video Test-Time Adaptation for Action Recognition

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Wei Lin Muhammad Jehanzeb Mirza Mateusz Kozinski Horst Possegger Hilde Kuehne Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Christian Doppler Laboratory for Embedded Machine Learning Goethe University Frankfurt Germany MIT-IBM Watson AI Lab

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at https://***/wlin-at/ViTTA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LaFTer: label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

arXiv

引用

arXiv 2023年

作者： Mirza, M. Jehanzeb Karlinsky, Leonid Lin, Wei Kozinski, Mateusz Possegger, Horst Feris, Rogerio Bischof, Horst Institute of Computer Graphics and Vision TU Graz Austria Christian Doppler Laboratory for Embedded Machine Learning Austria MIT-IBM Watson AI Lab United States

Recently, large-scale pre-trained vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language prompts. However, despite these great advances, the performance of these zero-shot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine-tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories. Using our label-free approach, we are able to attain significant performance improvements over the zero-shot performance of the base VL model and other contemporary methods and baselines on a wide variety of datasets, demonstrating absolute improvement of up to 11.7% (3.8% on average) in the label-free setting. Moreover, despite our approach being label-free, we observe 1.3% average gains over leading few-shot prompting baselines that do use 5-shot supervision. © 2023, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-...

引用

International Conference on computer vision (ICCV)

作者： Wei Lin Leonid Karlinsky Nina Shvetsova Horst Possegger Mateusz Kozinski Rameswar Panda Rogerio Feris Hilde Kuehne Horst Bischof Institute of Computer Graphics and Vision Graz University of Technology Austria MIT-IBM Watson AI Lab USA Goethe University Frankfurt Germany University of Bonn Germany

关键词：

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：