检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ni, Saijie Zhang, Xiaopeng Wang, Botao Xiong, Hongkai Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9781509060672

Conventional image classification and object detection methods depend on manual annotations, such as image-level labels and bounding boxes. However, the acquisition of such annotations for millions of images is trivial. This paper addresses the problem of webly-supervised visual concept learning, and develops an automatic algorithm using parallel text and visual corpora to discover informative visual patterns from the web images. Based on the mined patterns, a cardinalityguided multiple instance learning algorithm is designed to establish the link between the image patterns and the literal concepts. Furthermore, due to the diversity of visual concepts, we perform clustered multitask refinement on the learned concept classifiers to enhance their generalization capability via a clustered regularization. Experiments demonstrate the superiority of the proposed method over traditional approaches.

关键词： visual concept learning multiple instance learning multitask learning

来源：评论

学校读者我要写书评

暂无评论

Regularized Semi-Supervised Latent Dirichlet Allocation for visual concept learning

引用

NEUROCOMPUTING 2013年 119卷 26-32页

作者： Zhuang, Liansheng Gao, Haoyuan Luo, Jiebo Lin, Zhouchen Univ Sci & Technol China Hefei 230027 Peoples R China Univ Rochester Dept Comp Sci Rochester NY 14627 USA Peking Univ Key Lab Machine Percept MOE Beijing 100871 Peoples R China

Topic model is a popular tool for visual concept learning. Most topic models are either unsupervised or fully supervised. In this paper, to take advantage of both limited labeled training images and rich unlabeled images, we propose a novel regularized Semi-Supervised Latent Dirichlet Allocation (r-SSLDA) for learning visual concept classifiers. Instead of introducing a new complex topic model, we attempt to find an efficient way to learn topic models in a semi-supervised way. Our r-SSLDA considers both semi-supervised properties and supervised topic model simultaneously in a regularization framework. Furthermore, to improve the performance of r-SSLDA, we introduce the low rank graph to the framework. Experiments on Caltech 101 and Caltech 256 have shown that r-SSLDA outperforms both unsupervised LDA and achieves competitive performance against fully supervised LDA with much fewer labeled images. (c) 2013 Elsevier B.V. All rights reserved.

关键词： visual concept learning Semi-supervised learning Latent Dirichlet Allocation Low rank graph

来源：评论

学校读者我要写书评

暂无评论

Same or different?Abstract relational concept use in juvenile bamboo sharks and Malawi cichlids

引用

Current Zoology 2021年第3期67卷 279-292页

作者： Theodora Fuss Leonie John Vera Schluessel Institute of Zoology Rheinische Friedrich-Wilhelms-University BonnMeckenheimer Allee 169Bonn53115Germany

Sorting objects and events into categories and concepts is an important cognitive prerequisite that spares an individual the learning of every object or situation encountered in its daily ***,specific items are classified in general groups that allow fast responses to novel *** present study assessed whether bamboo sharks Chiloscyllium griseum and Malawi cichlids Pseudotropheus zebra can distinguish sets of stimuli(each stimulus consisting of two abstract,geometric objects)that meet two conceptual preconditions,i.e.,(1)"sameness"versus"difference"and(2)a certain spatial arrangement of both *** two alternative forced choice experiments,individuals were first trained to choose two different,vertically arranged objects from two different but horizontally arranged *** discriminations were followed by extensive transfer test *** tests using stimuli consisting of(a)black and gray circles and(b)squares with novel geometric patterns provided conflicting information with respect to the learnt rule"choose two different,vertically arranged objects",thereby investigating(1)the individuals'ability to transfer previously gained knowledge to novel stimuli and(2)the abstract relational concept(s)or rule(s)applied to categorize these novel *** results suggest that the level of processing and usage of both abstract concepts differed considerably between bamboo sharks and Malawi *** sharks seemed to combine both concepts-although not with equal but hierarchical prominence-pointing to advanced cognitive ***,Malawi cichlids had difficulties in discriminating between symbols and failed to apply the acquired training knowledge on new sets of geometric and,in particular,gray-level transfer stimuli.

关键词： visual concept learning spatial arrangement relational abstract concept Malawi cichlid bamboo shark

来源：评论

学校读者我要写书评

暂无评论

Sampling and Ontologically Pooling Web Images for visual concept learning

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2012年第4期14卷 1068-1078页

作者： Zhu, Shiai Chong-Wah Ngo Jiang, Yu-Gang City Univ Hong Kong Dept Comp Sci Kowloon Hong Kong Peoples R China Fudan Univ Sch Comp Sci Shanghai 201203 Peoples R China

Sufficient training examples are essential for effective learning of semantic visual concepts. In practice, however, acquiring noise-free training examples has always been expensive. Recently the rapid popularization of social media websites, such as Flickr, has made it possible to collect training exemplars without human assistance. This paper proposes a novel and efficient approach to collect training samples from the noisily tagged Web images for visual concept learning, where we try to maximize two important criteria, relevancy and coverage, of the automatically generated training sets. For the former, a simple method named semantic field is introduced to handle the imprecise and incomplete image tags. Specifically, the relevancy of an image to a target concept is predicted by collectively analyzing the associated tag list of the image using two knowledge sources: WordNet corpus and statistics from ***. To boost the coverage or diversity of the training sets, we further propose an ontology-based hierarchical pooling method to collect samples not only based on the target concept alone, but also from ontologically neighboring concepts. Extensive experiments on three different datasets (NUS-WIDE, PASCAL VOC, and ImageNet) demonstrate the effectiveness of our proposed approach, producing competitive performance even when comparing with concept classifiers learned using expert-labeled training examples.

关键词： Training set construction visual concept learning web images

来源：评论

学校读者我要写书评

暂无评论

Source Model Selection as a Meta-learning Technique to learn Novel concepts 2020

Source Model Selection as a Meta-learning Technique to learn...

引用

12th International Conference on Machine learning and Computing (ICMLC)

作者： Kadam, Suvarna Vaidya, Vinay G. SPPU Dept Technol Pune Maharashtra India

ISBN: (纸本)9781450376426

visual concept classification from a closed set has been successfully solved with supervised deep learning. However, learning a novel visual concept is challenging for deep models, especially when the concept is rare with only a few samples. Deep Transfer learning addresses this lack of training samples by using a model that is pre-trained on several visual concepts, as a feature extractor, to improve the performance on target concept. The effectiveness of such transfer depends on selection of relevant pretrained model. If we have multiple pretrained models, trained on different genre of visual concepts, we intuitively choose a model trained on the source visual concepts that are similar to target concept. In this paper, we attempt to quantify this human intuition that is crucial in human meta-learning for retrieving relevant knowledge. We propose an approach to quantitatively measure the suitability of source model to learn a novel and rare target concept, to automate the model selection which in effect achieves meta-learning.

关键词： Transfer learning Model Selection visual concept learning Generative Machine learning

来源：评论

学校读者我要写书评

暂无评论

Regularized Semi-supervised Latent Dirichlet Allocation for visual concept learning

Regularized Semi-supervised Latent Dirichlet Allocation for ...

引用

17th International Multimedia Modeling Conference, MMM 2011

作者： Zhuang, Liansheng She, Lanbo Huang, Jingjing Luo, Jiebo Yu, Nenghai USTC MOE MS Keynote Lab MCC Hefei 230027 Peoples R China USTC Sch Informat Sci & Technol Hefei 230027 Peoples R China Eastman Kodak Co Kodak Res Labs Rochester NY 14650 USA

ISBN: (纸本)9783642178313

Topic models are a popular tool for visual concept learning. Current topic models are either unsupervised or fully supervised. Although lots of labeled images can significantly improve the performance of topic models, they are very costly to acquire. Meanwhile, billions of unlabeled images are freely available on the internet. In this paper, to take advantage of both limited labeled training images and rich unlabeled images, we propose a novel technique called regularized Semi-supervised Latent Dirichlet Allocation (r-SSLDA) for learning visual concept classifiers. Instead of introducing a new topic model, we attempt to find an efficient way to learn topic models in a semi-supervised way. r-SSLDA considers both semi-supervised properties and supervised topic model simultaneously in a regularization framework. Experiments on Caltech 101 and Caltech 256 have shown that r-SSLDA outperforms unsupervised LDA, and achieves competitive performance against fully supervised LDA, while sharply reducing the number of labeled images required.

关键词： visual concept learning Latent Dirichlet Allocation Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

A New Multiple Kernel Approach for visual concept learning

A New Multiple Kernel Approach for Visual Concept Learning

引用

15th International Multimedia Modeling Conference

作者： Yang, Jingjing Li, Yuanning Tian, Yonghong Duan, Lingyu Gao, Wen Chinese Acad Sci Inst Comp Technol Beijing 100080 Peoples R China Chinese Acad Sci Grad Sch Beijing 100039 Peoples R China Peking Univ Sch EE & CS Inst Digital Med Beijing 100871 Peoples R China

ISBN: (纸本)9783540928911

In this paper, we present a novel multiple kernel method to learn the optimal classification function for visual concept. Although many carefully designed kernels have been proposed in the literature to measure the visual similarity, few works have been done on how these kernels really affect the learning performance. We propose a Per-Sample Based Multiple Kernel learning method (PS-MKL) to investigate the discriminative power of each training sample in different basic kernel spaces. The optimal, sample-specific kernel is learned as a linear combination of a set of basic kernels, which leads to a convex optimization problem with a unique global optimum. As illustrated in the experiments on the Caltech 101 and the Wikipedia MM dataset, the proposed PS-MKL outperforms the traditional Multiple Kernel learning methods (MKL) and achieves comparable results with the state-of-the-art methods of learning visual concepts.

关键词： visual concept learning Support Vector Machine Multiple Kernel learning

来源：评论

学校读者我要写书评

暂无评论

Cost-sensitive learning in social image tagging: review, new ideas and evaluation

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2012年第4期1卷 205-222页

作者： Li, Zhenyang Lew, Michael S. Univ Amsterdam Amsterdam Netherlands Leiden Univ Leiden Netherlands

visual concept learning typically requires a set of expert labeled, manual training images. However, acquiring a sufficient number of reliable annotations can be time-consuming or impractical. Therefore, in many situations it is preferable to perform unsupervised learning on user contributed tags from abundant sources such as social Internet communities and websites. Cost-sensitive learning is a natural approach toward unsupervised visual concept learning because it fundamentally optimizes the learning system accuracy regarding the cost of an error. This paper reviews the problem of cost-sensitive unsupervised learning of visual concepts from social images, presents the new ideas, and gives a comparative evaluation of representative approaches from the research literature.

关键词： visual concept learning Unsupervised learning Social images Social tagging Tag relevance learning Cost-sensitive learning Importance weighted classification

来源：评论

学校读者我要写书评

暂无评论

Population-based incremental interactive concept learning for image retrieval by stochastic string segmentations

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2004年第6期23卷 676-689页

作者： Ghebreab, S Jaffe, CC Smeulders, AWM Erasmus MC Dept Radiol Biomed Imaging Grp Rotterdam NL-3015 GE Rotterdam Netherlands Yale Univ Sch Med Cardiovasc Med Sect New Haven CT 06510 USA Univ Amsterdam Fac Sci Inst Informat Intelligent Sensory Informat Syst NL-1098 SJ Amsterdam Netherlands

We propose a method for concept-based medical image retrieval that is a superset of existing semantic-based image retrieval methods. We conceive of a concept as an incremental and interactive formalization of the user's conception of an object in an image. The premise is that such a concept is closely related to a user's specific preferences and subjectivity and, thus, allows to deal with the complexity and content-dependency of medical image content. We describe an object in terms of multiple continuous boundary features and represent an object concept by the stochastic characteristics of an object population. A population-based incrementally learning technique, in combination with relevance feedback, is then used for concept customization. The user determines the speed and direction of concept customization using a single parameter that defines the degree of exploration and exploitation of the search space. Images are retrieved from a database in a limited number of steps based upon the customized concept. To demonstrate our method we have performed concept-based image retrieval on a database of 292 digitized X-ray images of cervical vertebrae with a variety of abnormalities. The results show that our method produces precise and accurate results when doing a direct search. In an open-ended search our method efficiently and effectively explores the search space.

关键词： content-based image retrieval multifeature object description population-based incremental learning relevance feedback visual concept learning

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：