检索结果-内蒙古大学图书馆

15th ACM International Conference on Multimedia, MM'07

作者： Chen, Yanhua Rege, Manjeet Dong, Ming Fotouhi, Farshad Machine Vision Pattern Recognition Lab. Department of Computer Science Wayne State University Detroit MI 48202 United States Database and Multimedia Systems Group Department of Computer Science Wayne State University Detroit MI 48202 United States

ISBN: (纸本)9781595937025

Image clustering solely based on visual features without any knowledge or background information suffers from the problem of semantic gap. In this paper, we propose SS-NMF: a semi-supervised non-negative matrix factorization framework for image clustering. Accumulated relevance feedback in a CBIR system is treated as user provided supervision for guiding the image clustering. We consider the set of positive images in the feedback as constraints on the clustering specifying that the images "must" be clustered together. Similarly, negative images provide constraints specifying that they "cannot" be clustered along with the positive images. Through an iterative algorithm, we perform symmetric tri-factorization of the image-image similarity matrix to infer the clustering. Theoretically, we prove the correctness of SS-NMF by showing that the algorithm is guaranteed to converge. Through experiments conducted on general purpose image datasets, we demonstrate the superior performance of SS-NMF for clustering images effectively. Copyright 2007 ACM.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Image co-clustering with multi-modality features and user feedbacks 09

Image co-clustering with multi-modality features and user fe...

引用

17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums

作者： Chen, Yanhua Dong, Ming Wan, Wanggen Machine Vision and Pattern Recognition Lab. Department of Computer Science Wayne State University Detroit MI 48202 United States School of Communication and Info. Eng. Shanghai University Shanghai 200072 China

ISBN: (纸本)9781605586083

In Content-based Image Retrieval (CBIR) research, advanced technology that fuses the heterogeneous information into image clustering has drawn extensive attention recently. However, using multiple features for co-clustering images without any user feedbacks is a challenging problem. In this paper, we propose a Semi-Supervised Non-negative Matrix Factorization (SS-NMF) framework for image co-clustering. Our method computes new relational matrices by incorporating user provided feedbacks into images through simultaneous distance metric learning and feature selection for different low-level visual features. Using an iterative algorithm, we perform tri-factorizations of the new matrices to infer image clusters. Theoretically, we show the convergence and correctness of SS-NMF co-clustering and the advantages of SS-NMF co-clustering over existing approaches. Through extensive experiments conducted on image data sets, we demonstrate that SS-NMF provides an effective and efficient solution for image co-clustering. Copyright 2009 ACM.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Adversarial feature augmentation for unsupervised domain adaptation

arXiv

引用

arXiv 2017年

作者： Volpi, Riccardo Morerio, Pietro Savarese, Silvio Murino, Vittorio Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia Stanford Vision and Learning Lab Stanford University Computer Science Department Università di Verona

Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a lab.led source dataset and an unlab.led target dataset, the goal is to train powerful classifiers for the target samples. In particular, it was shown that a GAN objective function can be used to learn target features indistinguishable from the source ones. In this work, we extend this framework by (i) forcing the learned feature extractor to be domain-invariant, and (ii) training it through data augmentation in the feature space, namely performing feature augmentation. While data augmentation in the image space is a well established technique in deep learning, feature augmentation has not yet received the same level of attention. We accomplish it by means of a feature generator trained by playing the GAN minimax game against source features. Results show that both enforcing domain-invariance and performing feature augmentation lead to superior or comparable performance to state-of-the-art results in several unsupervised domain adaptation benchmarks. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fast anatomical structure localization using top-down image patch regression

Fast anatomical structure localization using top-down image ...

引用

15th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2012

作者： Donner, René Menze, Bjoern H. Bischof, Horst Langs, Georg Computational Image Analysis and Radiology Lab. Department of Radiology Medical University Vienna Austria Institute for Computer Graphics and Vision Graz University of Technology Austria CSAIL MIT Cambridge MA United States Asclepios Project INRIA Sophia-Antipolis France Computer Vision Laboratory ETH Zurich Switzerland

ISBN: (纸本)9783642366192

Fully automatic localization of anatomical structures in 2D and 3D radiological data sets is important in both computer aided diagnosis, and the rapid automatic processing of large amounts of data. We present a simple, accurate and fast approach with low computational complexity to find anatomical landmarks, based on a multi-scale regression codebook of informative image patches and encoded landmark contexts. From a set of annotated training volumes the method captures the appearance of landmarks over several scales together with relative positions of neighboring landmarks and a spatial distribution model. During multi-scale search in a target volume, starting from the coarsest level, each landmark model predicts all landmark positions it has encoded, with the median of all predictions yielding the final prediction for each scale. We present results on two challenging data sets (hand radiographs and hand CTs), where our method achieves comparable accuracy to the state of the art with substantially improved run-time. © 2013 Springer-Verlag.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Multi robot SLAM for features based environment modelling

Multi robot SLAM for features based environment modelling

引用

IEEE International Conference on Mechatronics and Automation

作者： Syed Riaz un Nabi Jafri Waheed Ahmed Zubair Ashraf Ryad Chellali Electronic Engineering Department NED UET Karachi Pakistan Pattern Analysis and Computer Vision LAB-IIT Genova Italy

ISBN: (纸本)9781479939800

This paper is presenting a multi robot simultaneous localization and mapping (SLAM) framework for environment modelling using 2D and 3D features. The proposed solution is using a team of mobile robots which are exploring unknown environment with unknown poses. Each team member is allowed to build its independent features based SLAM solution and to share the local map model among other mates. By matching the overlapping tendency of any two mates, a map merging strategy is introduced which in result is building global map. The overall approach has tested in 2D and 3D features based environment and results have shown.

关键词： Simultaneous localization and mapping Cameras Robot vision systems Lasers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A HYBRID MODEL FOR INTELLIGENT CONTROL-SYSTEMS

引用

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 1994年第3期10卷 221-241页

作者： AN, YF PANG, G APLEVICH, D 1. Pattern Analysis and Machine Intelligence Lab. System Design Engineering University of Waterloo N2L 3G1 Waterloo Ontario Canada 2. Department of Electrical and Computer Engineering University of Waterloo N2L 3G1 Waterloo Ontario Canada

Hybrid continuous-time and discrete-event system models are developed for applications to intelligent robot and autonomous control systems. Certain general properties, including the interface structure between the discrete event part and the continuous part of hybrid systems, are studied. Petri nets are proposed as the model for the discrete event sub-system (DES), and state equations with a set of binary parameters as the model for the continuous time sub-system (CTS) in a hybrid system. The quantized CTS is formulated in prime event structures, which can also be modeled by a condition/event Petri net. Therefore, a complete hybrid system can be fit into an extended Petri net formalism, which provides a unified framework for hybrid system description. The validity of the proposed model is demonstrated by modeling a two-tank system.

关键词： CONTINUOUS TIME SYSTEMS DISCRETE EVENT SYSTEMS HYBRID SYSTEMS PETRI NETS MODELING INTELLIGENT CONTROL

来源：评论

学校读者我要写书评

暂无评论

Evaluation of fast 2D and 3D medical image retrieval approaches based on image miniatures

Evaluation of fast 2D and 3D medical image retrieval approac...

引用

2nd MICCAI International Workshop on Medical Content-Based Retrieval for Clinical Decision Support, MCBR-CDS 2011

作者： Donner, René Haas, Sebastian Burner, Andreas Holzer, Markus Bischof, Horst Langs, Georg Computational Image Analysis and Radiology Lab. Department of Radiology Medical University of Vienna Austria Institute for Computer Graphics and Vision Graz University of Technology Austria Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA United States

ISBN: (纸本)9783642284595

The present work evaluates four medical image retrieval approaches based on features derived from image miniatures. We argue that due to the restricted domain of medical image data, the standardized acquisition protocols and the absence of a potentially cluttered background a holistic image description is sufficient to capture high-level image similarities. We compare four different miniature 2D and 3D descriptors and corresponding metrics, in terms of their retrieval performance: (A) plain miniatures together with euclidean distances in a k Nearest Neighbor based retrieval backed by kD-trees;(B) correlations of rigidly aligned miniatures, initialized using the kD-tree;(C) distribution fields together with the l1-norm;(D) SIFT-like histogram of gradients using the χ2-distance. We evaluate the approaches on two data sets: the ImageClef 2009 benchmark of 2D radiographs with the aim to categorize the images and a large set of 3D-CTs representing a realistic sample in a hospital PACS with the objective to estimate the location of the query volume. © 2012 Springer-Verlag.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

On Moving Object Segmentation from Monocular Video with Transformers

On Moving Object Segmentation from Monocular Video with Tran...

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Christian Homeyer Christoph Schnörr Robert Bosch GmbH Corporate Research Computer Vision Lab Hildesheim Germany Image and Pattern Analysis Group Heidelberg University Germany Image and Pattern Analysis Group Heidelberg University Germany

Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem, where appearance and motion features need to be combined for classification and *** this paper, we present a novel fusion architecture for monocular motion segmentation - M 3 Former, which leverages the strong performance of transformers for segmentation and multi-modal fusion. As reconstructing motion from monocular video is ill-posed, we systematically analyze different 2D and 3D motion representations for this problem and their importance for segmentation performance. Finally, we analyze the effect of training data and show that diverse datasets are required to achieve SotA performance on Kitti and Davis. Code will be released upon publication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT ONLINE lab.L CONSISTENT HASHING FOR LARGE-SCALE CROSS-MODAL RETRIEVAL

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CR...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online lab.l Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE computer Society. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

On Moving Object Segmentation from Monocular Video with Transformers

arXiv

引用

arXiv 2024年

作者： Homeyer, Christian Schnörr, Christoph Robert Bosch GmbH Corporate Research Computer Vision Lab Hildesheim Germany Image and Pattern Analysis Group Heidelberg University Germany

Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem, where appearance and motion features need to be combined for classification and segmentation. In this paper, we present a novel fusion architecture for monocular motion segmentation - M3Former, which leverages the strong performance of transformers for segmentation and multi-modal fusion. As reconstructing motion from monocular video is ill-posed, we systematically analyze different 2D and 3D motion representations for this problem and their importance for segmentation performance. Finally, we analyze the effect of training data and show that diverse datasets are required to achieve SotA performance on Kitti and Davis. Copyright © 2024, The Authors. All rights reserved.

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：