检索结果-内蒙古大学图书馆

Transactions on Edutainment IV 1

学校读者我要写书评

暂无评论

丛书名： Lecture Notes in computer Science

1000年

作者： Zhigeng Pan Adrian David Cheok Wolfgang Müller Xiaopeng Zhang Kevin Wong

ISBN: (数字)9783642144844

ISBN: (纸本)9783642144837

E-learning and digital entertainment techniques, tools and systems are becoming popular and can be found in many real-world educational applications in many co- tries. The driving force behind these technologies is the rapidly growing requirements of edutainment, especially from the perspective of the users. This has led to the increasing interest of researchers in this area. The articles in this issue give a rich overview of how edutainment technologies can be creatively used for training and education purposes. The first 12 articles of this issue represent a selection of outstanding contributions from Edutainment 2010, the 5th International Conference on E-learning and Games, held in Changchun, China, in August 2010. The main purpose of this event is to faci- tate the discussion, presentation, and information exchange on the scientific and te- nological developments in the emerging field of digital entertainment techniques and systems for education. These 12 papers concentrated on three aspects: e-learning s- tem and applications, game techniques for learning, and virtual reality techniques for entertainment. They are closely related to the topics of this journal.

关键词： Educational Technology computers and Education

Beyond bag of words: Image representation in sub-semantic space 13

学校读者我要写书评

暂无评论

Beyond bag of words: Image representation in sub-semantic sp...

21st ACM International Conference on Multimedia, MM 2013

作者： Zhang, Chunjie Wang, Shuhui Liang, Chao Liu, Jing Huang, Qingming Li, Haojie Tian, Qi School of Computer and Control Engineering University of Chinese Academy of Sciences 100049 Beijing China Key Lab of Intell. Info. Process Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Computer National Engineering Research Center for Multimedia Software Wuhan University 430072 Wuhan China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Software Dalian University of Technology Liaoning China Department of Computer Sciences University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9781450324045

Due to the semantic gap, the low-level features are not able to semantically represent images well. Besides, traditional semantic related image representation may not be able to cope with large inter class variations and are not very ro- bust to noise. To solve these problems, in this paper, we propose a novel image representation method in the sub- semantic space. First, examplar classifiers are trained by separating each training image from the others and serve as the weak semantic similarity measurement. Then a graph is constructed by combining the visual similarity and weak se- mantic similarity of these training images. We partition this graph into visually and semantically similar sub-sets. Each sub-set of images are then used to train classifiers in order to separate this sub-set from the others. The learned sub-set classifiers are then used to construct a sub-semantic space based representation of images. This sub-semantic space is not only more semantically meaningful but also more reli- Able and resistant to noise. Finally, we make categorization of images using this sub-semantic space based representation on several public datasets to demonstrate the e®ectiveness of the proposed method. Copyright © 2013 ACM.

关键词： Image representation

Fine-grained image classification using color exemplar classifiers

学校读者我要写书评

暂无评论

Fine-grained image classification using color exemplar class...

14th Pacific-Rim Conference on Multimedia, PCM 2013

作者： Zhang, Chunjie Xiong, Wei Liu, Jing Zhang, Yifan Liang, Chao Huang, Qingming School of Computer and Control Engineering University of Chinese Academy of Sciences 100049 Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences P.O. Box 2728 Beijing China National Engineering Research Center for Multimedia Software Wuhan University 430072 Wuhan China Key Lab of Intell. Info. Process Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783319037301

The use of local features has demonstrated its effectiveness for many visual applications. However, local features are often extracted with gray images. This ignores the useful information within different color channels which eventually hinders the final performance, especially for fine-grained image classification. Besides, the semantic information of local features is too weak to be applied for high-level visual applications. To cope with these problems, in this paper, we propose a novel fine-grained image classification method by using color exemplar classifiers. For each image, we first decompose it into multiple color channels to take advantage of the color information. For each color channel, we represent each image with a response histogram which is generated by exemplar classifiers. Experiments on several public image datasets demonstrate the effectiveness of the proposed color exemplar classifier based image classification method. © Springer International Publishing Switzerland 2013.

关键词： Image classification

Unsupervised detection of small hyperreflective features in ultrahigh resolution optical coherence tomography

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Reimann, Marcel Won, Jungeun Takahashi, Hiroyuki Yaghy, Antonio Hwang, Yunchan Ploner, Stefan Lin, Junhong Girgis, Jessica Lam, Kenneth Chen, Siyu Waheed, Nadia K. Maier, Andreas Fujimoto, James G. Department of Electrical Engineering and Computer Science Research Laboratory of Electronics Massachusetts Institute of Technology United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany New England Eye Center Tufts Medical Center United States

Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume. © 2023, CC BY-NC-SA.

关键词： Optical tomography

Word segmentation in handwritten Korean text lines based on gap clustering techniques

学校读者我要写书评

暂无评论

Word segmentation in handwritten Korean text lines based on ...

International Conference on Document Analysis and recognition

作者： S.H. Kim S. Jeong Guee-Sang Lee C.Y. Suen Center for Pattern Recognition and Machine Intelligence Concordia University Montreal QUE Canada Postal Technology Development Department Electronics and Telecommunications Research Institute Daejeon South Korea Department of Computer Science Chonnam National University Gwangju South Korea

We propose a word segmentation method for handwritten Korean text lines. It uses gap information to separate a text line into word units, where the gap is defined as a white-run obtained after a vertical projection of the line image. Each gap is classified into a between-word gap or a within-word gap using a clustering technique. We take up three gap metrics - the bounding box (BB), run-length/Euclidean (RLE) and convex hull (CH) distances - which are known to have superior performance in Roman-style word segmentation, and three clustering techniques - the average linkage method, the modified MAX method and sequential clustering. An experiment with 498 text-line images extracted from live mail pieces has shown that the best performance is obtained by the sequential clustering technique using all three gap metrics.

关键词： Image segmentation Couplings Handwriting recognition Text recognition pattern recognition Machine intelligence computer science Postal services Character recognition Humans

Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Ling Mao, Qirong Huang, Xiaohua Zhang, Feifei Zhang, Zhihong School of Computer Science and Communication Engineering Jiangsu University ZhenjiangJiangsu212013 China School of Computer Engineering Nanjing Institute of Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Xiamen University Xiamen China Center for Machine Vision and Signal Analysis University of Oulu Finland

Micro-Expression recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for micro-expression recognition. However, they do not reveal the specific discriminative characteristics, which lead to sub-optimal performance. This paper proposes a novel Feature Refinement (FR) with expression-specific feature learning and fusion for micro-expression recognition. It aims to obtain salient and discriminative features for specific expressions and also predict expression by fusing the expression-specific features. FR consists of an expression proposal module with attention mechanism and a classification branch. First, an inception module is designed based on optical flow to obtain expression-shared features. Second, in order to extract salient and discriminative features for specific expression, expression-shared features are fed into an expression proposal module with attention factors and proposal loss. Last, in the classification branch, labels of categories are predicted by a fusion of the expression-specific features. Experiments on three publicly available databases validate the effectiveness of FR under different protocol. Results on public benchmarks demonstrate that our FR provides salient and discriminative information for micro-expression recognition. The results also show our FR achieves better or competitive performance with the existing state-of-the-art methods on micro-expression recognition. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Multiple domain experts collaborative learning: Multi-source domain generalization for person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Shijie Zhu, Feng Chen, Dapeng Zhao, Rui Chen, Haobin Zhu, Jinguo Tang, Shixiang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China SenseTime Group Limited Shanghai AI Lab Shanghai China Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China

Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when unseen testing domains exhibit different characteristics from the source training ones, known as the domain generalization problem. Given multiple source training domains, previous Domain Generalizable ReID (DG-ReID) methods usually learn all domains together using a shared network, which can't learn sufficient knowledge from each domain. In this paper, we propose a novel Multiple Domain Experts Collaborative Learning (MECL) framework for better exploiting all training domains, which benefits from the proposed Domain-Domain Collaborative Learning (DDCL) and Universal-Domain Collaborative Learning (UDCL). DDCL utilizes domain-specific experts for fully exploiting each domain, and prevents experts from over-fitting the corresponding domain using a meta-learning strategy. In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts. Note, only the universal expert will be used for inference. Extensive experiments on DG-ReID benchmarks demonstrate the effectiveness of DDCL and UDCL, and show that the whole MECL framework significantly outperforms state-of-the-arts. Experimental results on DG-classification benchmarks also reveal the great potential of applying MECL to other DG tasks. Code will be released. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Session-based recommendation with graph neural networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Shu Tang, Yuyuan Zhu, Yanqiao Wang, Liang Xie, Xing Tan, Tieniu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences School of Computer and Communication Engineering University of Science and Technology Beijing School of Software Engineering Tongji University Microsoft Research Asia

The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user vectors in sessions and neglect complex transitions of items. To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are modeled as graph-structured data. Based on the session graph, GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods. Each session is then represented as the composition of the global preference and the current interest of that session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods consistently. Copyright © 2018, The Authors. All rights reserved.

关键词： Graph neural networks

The Devil is in the Conflict: Disentangled Information Graph Neural Networks For Fraud Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zhixun Chen, Dingshuo Liu, Qiang Wu, Shu School of Computer Science and Technology Beijing Institute of Technology China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

Graph-based fraud detection has heretofore received considerable attention. Owning to the great success of Graph Neural Networks (GNNs), many approaches adopting GNNs for fraud detection has been gaining momentum. However, most existing methods are based on the strong inductive bias of homophily, which indicates that the context neighbors tend to have same labels or similar features. In real scenarios, fraudsters often engage in camouflage behaviors in order to avoid detection system. Therefore, the homophilic assumption no longer holds, which is known as the inconsistency problem. In this paper, we argue that the performance degradation is mainly attributed to the inconsistency between topology and attribute. To address this problem, we propose to disentangle the fraud network into two views, each corresponding to topology and attribute respectively. Then we propose a simple and effective method that uses the attention mechanism to adaptively fuse two views which captures data-specific preference. In addition, we further improve it by introducing mutual information constraints for topology and attribute. To this end, we propose a Disentangled Information Graph Neural Network (DIGNN) model, which utilizes variational bounds to find an approximate solution to our proposed optimization objective function. Extensive experiments demonstrate that our model can significantly outperform state-of-the-art baselines on real-world fraud detection datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Information theory