检索结果-内蒙古大学图书馆

KBGN: Knowledge-bridge graph network for adaptive vision-text reasoning in visual dialogue

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Xiaoze Du, Siyi Qin, Zengchang Sun, Yajing Yu, Jing Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China AI Research Codemao Inc Institute of Information Engineering Chinese Academy of Sciences Beijing China

Visual dialogue is a challenging task that needs to extract implicit information from both visual (image) and textual (dialogue history) contexts. Classical approaches pay more attention to the integration of the current question, vision knowledge and text knowledge, despising the heterogeneous semantic gaps between the cross-modal information. In the meantime, the concatenation operation has become de-facto standard to the cross-modal information fusion, which has a limited ability in information retrieval. In this paper, we propose a novel Knowledge-Bridge Graph Network (KBGN) model by using graph to bridge the cross-modal semantic relations between vision and text knowledge in fine granularity, as well as retrieving required knowledge via an adaptive information selection mode. Moreover, the reasoning clues for visual dialogue can be clearly drawn from intra-modal entities and inter-modal bridges. Experimental results on VisDial v1.0 and VisDial-Q datasets demonstrate that our model outperforms existing models with state-of-the-art results. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

Generalized lab.l enhancement with sample correlations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zheng, Qinghai Zhu, Jihua Tang, Haoyu Liu, Xinyuan Li, Zhongyu Lu, Huimin Lab of Vision Computing and Machine Learning School of Software Engineering Xi'an Jiaotong University Xi'an710049 China Environment Recognition & Intelligent Computation Laboratory Kyushu Institute of Technology Japan

Recently, lab.l distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from lab.lel instances. Different from single-lab.l and multi-lab.l annotations, lab.l distributions describe the instance by multiple lab.ls with different intensities and accommodate to more general scenes. Since most existing machine learning datasets merely provide logical lab.ls, lab.l distributions are unavailab.e in many real-world applications. To handle this problem, we propose two novel lab.l enhancement methods, i.e., lab.l Enhancement with Sample Correlations (LESC) and generalized lab.l Enhancement with Sample Correlations (gLESC). More specifically, LESC employs a low-rank representation of samples in the feature space, and gLESC leverages a tensor multi-rank minimization to further investigate the sample correlations in both the feature space and lab.l space. Benefitting from the sample correlations, the proposed methods can boost the performance of lab.l enhancement. Extensive experiments on 14 benchmark datasets demonstrate the effectiveness and superiority of our methods. Copyright © 2020, The Authors. All rights reserved.

关键词： machine learning

An automatic breast cancer grading method in histopathological images based on pixel-, object-, and semantic-level features

学校读者我要写书评

暂无评论

An automatic breast cancer grading method in histopathologic...

IEEE International Symposium on Biomedical Imaging

作者： Jiajia Cao Zengchang Qin Juan Jing Jianhui Chen Tao Wan Intelligent Computing & Machine Learning Lab Beihang University China School of Biological Science and Medical Engineering Beihang University China No. 91 Central Hospital of PLA Henan China

ISBN: (纸本)9781479923519

We present an automatic breast cancer grading method in histopathological images based on the computer extracted pixel-, object-, and semantic-level features derived from convolutional neural networks (CNN). The multiple level features allow not only characterization of nuclear polymorphism, but also extraction of structural and interpretable information within the images. In this study, a hybrid level set based segmentation method was used to segment nuclei from the images. A quantile normalization approach was utilized to improve image color consistency. The semantic level features are extracted by a CNN approach, which describe the proportions of nuclei belonging to the different grades, in conjunction with pixel-level (texture) and object-level (structure) features, to form an integrated set of attributes. A support vector machine classifier was trained to discriminate the breast cancer between low, intermediate, and high grades. The results demonstrated that our method achieved accuracy of 0.90 (low vs. high), and 0.74 (low vs. intermediate), and 0.76 (intermediate vs. high), suggesting that the present method could play a fundamental role in developing a computer-aided breast cancer grading system.

关键词： Feature extraction Breast cancer Image segmentation Support vector machines Image color analysis Neurons

Semantic modeling of textual relationships in cross-modal retrieval

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, Jing Yang, Chenghao Qin, Zengchang Yang, Zhuoqian Hu, Yue Zhang, Weifeng Institute of Information Engineering Chinese Academy of Sciences China Intelligent Computing and Machine Learning Lab Beihang University China College of Mathematics Physics and Information Engineering Jiaxing University China

Feature modeling of different modalities is a basic problem in current research of cross-modal information retrieval. Existing models typically project texts and images into one embedding space, in which semantically similar information will have a shorter distance. Semantic modeling of textural relationships is notoriously difficult. In this paper, we propose an approach to model texts using a featured graph by integrating multi-view textual relationships including semantic relations, statistical co-occurrence, and prior relations in knowledge base. A dualpath neural network is adopted to learn multi-modal representations of information and cross-modal similarity measure jointly. We use a Graph Convolutional Network (GCN) for generating relation-aware text representations, and use a Convolutional Neural Network (CNN) with nonlinearities for image representations. The cross-modal similarity measure is learned by distance metric learning. Experimental results show that, by leveraging the rich relational semantics in texts, our model can outperform the state-of-the-art models by 3.4% and 6.3% on accuracy on two benchmark datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge graph

EEG-based fatigue classification by using parallel hidden Markov model and pattern classifier combination

学校读者我要写书评

暂无评论

EEG-based fatigue classification by using parallel hidden Ma...

19th International Conference on Neural Information Processing, ICONIP 2012

作者： Sun, Hui Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China MOE Key Laboratory of Systems Biomedicine Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9783642344770

Fatigue is the most important reason leading to traffic accidents. In order to ensure traffic safety, various methods based on electroencephalogram (EEG) are proposed. But most of them, either regression or classification, are focused on the relationship between feature space and observation values, so the changing patterns of features are ignored or discarded. In this paper, we propose a new fatigue classification method by using parallel hidden-Markov-model and pattern classifier combination techniques, where each model represents a particular fatigue-high-related feature. In the experiment, subjects are asked to accomplish some simple tasks, and both their fatigue states and their EEG signals are recorded simultaneously. Experimental results indicate that the mean error rate obtained by using our new method are 11.15% for classifying 3 states and 16.91% for classifying 4 states, respectively, while the existing approach can only reach 16.45% and 23.55% under the same condition. © 2012 Springer-Verlag.

关键词： Electroencephalography

Online vigilance analysis combining video and electrooculography features

学校读者我要写书评

暂无评论

Online vigilance analysis combining video and electrooculogr...

19th International Conference on Neural Information Processing, ICONIP 2012

作者： Du, Ruo-Fei Liu, Ren-Jie Wu, Tian-Xiang Lu, Bao-Liang Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China MOE Key Laboratory of Systems Biomedicine Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9783642344992

In this paper, we propose a novel system to analyze vigilance level combining both video and Electrooculography (EOG) features. For one thing, the video features extracted from an infrared camera include percentage of closure (PERCLOS) and eye blinks, slow eye movement (SEM), rapid eye movement (REM) are also extracted from EOG signals. For another, other features like yawn frequency, body posture and face orientation are extracted from the video by using Active Shape Model (ASM). The results of our experiments indicate that our approach outperforms the existing approaches based on either video or EOG merely. In addition, the prediction offered by our model is in close proximity to the actual error rate of the subject. We firmly believe that this method can be widely applied to prevent accidents like fatigued driving in the future. © 2012 Springer-Verlag.

关键词： Eye movements

Logical parsing from natural language based on a neural translation model

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Li, Liang Li, Pengyu Liu, Yifan Wan, Tao Qin, Zengchang Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing100191 China Biomedical Imaging and Informatics Lab School of Biological Science and Medical Engineering Beihang University Beijing100191 China

Semantic parsing has emerged as a significant and powerful paradigm for natural language interface and question answering systems. Traditional methods of building a semantic parser rely on high-quality lexicons, hand-crafted grammars and linguistic features which are limited by applied domain or representation. In this paper, we propose a general approach to learn from denotations based on Seq2Seq model augmented with attention mechanism. We encode input sequence into vectors and use dynamic programming to infer candidate logical forms. We utilize the fact that similar utterances should have similar logical forms to help reduce the searching space. Under our learning policy, the Seq2Seq model can learn mappings gradually with noises. Curriculum learning is adopted to make the learning smoother. We test our method on the arithmetic domain which shows our model can successfully infer the correct logical forms and learn the word meanings, compositionality and operation orders simultaneously. Copyright © 2017, The Authors. All rights reserved.

关键词： Dynamic programming

Followmeup sports: new benchmark for 2D human keypoint recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Ying Sun, Bin Kan, Haipeng Zhuang, Jiankai Qin, Zengchang Alibaba Business School Hangzhou Normal University Hangzhou China Keep Inc. Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China

Human pose estimation has made significant advancement in recent years. However, the existing datasets are limited in their coverage of pose variety. In this paper, we introduce a novel benchmark"FollowMeUp Sports" that makes an important advance in terms of specific postures, self-occlusion and class balance, a contribution that we feel is required for future development in human body models. This comprehensive dataset was collected using an established taxonomy of over 200 standard workout activities with three different shot angles. The collected videos cover a wider variety of specific workout activities than previous datasets including push-up, squat and body moving near the ground with severe self-occlusion or occluded by some sport equipment and outfits. Given these rich images, we perform a detailed analysis of the leading human pose estimation approaches gaining insights for the success and failures of these methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Sports

Emotion classification with data augmentation using generative adversarial networks 22nd

学校读者我要写书评

暂无评论

Emotion classification with data augmentation using generati...

22nd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2018

作者： Zhu, Xinyue Liu, Yifan Li, Jiahong Wan, Tao Qin, Zengchang Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China School of Electronic Engineering Bejing University of Posts and Telecommunications Beijing China Beijing San Kuai Yun Technology Co. Ltd. Beijing China School of Biological Science and Medical Engineering Beijing Advanced Innovation Centre for Biomedical Engineering Beihang University Beijing China

ISBN: (纸本)9783319930398

It is a difficult task to classify images with multiple class lab.ls using only a small number of lab.led examples, especially when the lab.l (class) distribution is imbalanced. Emotion classification is such an example of imbalanced lab.l distribution, because some classes of emotions like disgusted are relatively rare comparing to other lab.ls like happy or sad. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework using a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN’s performance. Empirical results show that we can obtain 5%–10% increase in the classification accuracy after employing the GAN-based data augmentation techniques. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Generative adversarial networks