检索结果-内蒙古大学图书馆

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 labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like disgusted are relatively rare comparing to other labels 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

An Evolutionary Model for Efficient Transportation Networks

学校读者我要写书评

暂无评论

An Evolutionary Model for Efficient Transportation Networks

International Conference on intelligent Human-machine Systems and Cybernetics, IHMSC

作者： Ian Huang Mei Chen William Yang Zengchang Qin International School of Beijing Baijing China Department of Electrical Engineering University of Southern California USA Intelligent Computing and Machine Learning Lab School of Automation Science and Electrical Engineering Beihang University China

In this paper, we present a model to automatically generate efficient transportation networks given a simulated urban environment with predefined population distributions and other physical constraints. Based on the empirical analysis of different topological structures of networks, we found that that the efficiency of transportation networks heavily depends on the layout of the stations. The model uses the genetic algorithm to optimize the spatial distribution of stations. Then, the Minimum Spanning Tree is constructed upon which extra network routes are built to minimize average travel time within the constraint of a network length. Experimental studies of a simulated Beijing subway system showed that our model can generate a network that is 14% more efficient than the current subway system based on the Beijing population distribution and geography. This study can be extended to other transportation systems designs, and other communication networks.

关键词： Sociology Statistics Public transportation Computational modeling Cities and towns Optimization

Auto-painter: Cartoon image generation from sketch by using conditional generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liu, Yifan Qin, Zengchang Luo, Zhenbo Wang, Hua Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing100191 China Samsung RandD Institute China Beijing 18F TaiTangGong Plaza Beijing100028 China

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Images can be generated at the pixel level by learning from a large collection of images. learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a potential application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose the auto-painter model which can automatically generate compatible colors for a sketch. The new model is not only capable of painting hand-draw sketch with proper colors, but also allowing users to indicate preferred colors. Experimental results on two sketch datasets show that the auto-painter performs better that existing image-to-image methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

A sequential guiding network with attention for image captioning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Sow, Daouda Qin, Zengchang Niasse, Mouhamed Wan, Tao Intelligent Computing and Machine Learning Lab School of ASEE Beihang University China Keep Labs Keep Inc. Beijing China School of EEE North China Electric Power University China

The recent advances of deep learning in both computer vision (CV) and natural language processing (NLP) provide us a new way of understanding semantics, by which we can deal with more challenging tasks such as automatic description generation from natural images. In this challenge, the encoder-decoder framework has achieved promising performance when a convolutional neural network (CNN) is used as image encoder and a recurrent neural network (RNN) as decoder. In this paper, we introduce a sequential guiding network that guides the decoder during word generation. The new model is an extension of the encoder-decoder framework with attention that has an additional guiding long short-term memory (LSTM) and can be trained in an end-to-end manner by using image/descriptions pairs. We validate our approach by conducting extensive experiments on a benchmark dataset, i.e., MS COCO Captions. The proposed model achieves significant improvement comparing to the other state-of-the-art deep learning models. Copyright © 2018, The Authors. All rights reserved.

关键词： Long short-term memory

Motif iteration model for network representation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Lv, Lintao Qin, Zengchang Wan, Tao Intelligent Computing and Machine Learning Lab School of Automation Science and Electrical Engineering Beihang University Beijing Beijing100191 China School of Biological Science and Medical Engineering Beihang University Beijing Beijing100191 China

Social media mining has become one of the most popular research areas in Big Data with the explosion of social networking information from Facebook, Twitter, LinkedIn,Weibo and so on. Understanding and representing the structure of a social network is a key in social media mining. In this paper, we propose the Motif Iteration Model (MIM) to represent the structure of a social network. As the name suggested, the new model is based on iteration of basic network motifs. In order to better show the properties of the model, a heuristic and greedy algorithm called Vertex Reordering and Arranging (VRA) is proposed by studying the adjacency matrix of the three-vertex undirected network motifs. The algorithm is for mapping from the adjacency matrix of a network to a binary image, it shows a new perspective of network structure visualization. In summary, this model provides a useful approach towards building link between images and networks and offers a new way of representing the structure of a social network. Copyright © 2017, The Authors. All rights reserved.

关键词： Social networking (online)

DualVD: An adaptive dual encoding model for deep visual understanding in visual dialogue

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Xiaoze Yu, Jing Qin, Zengchang Zhuang, Yingying Zhang, Xingxing Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China Microsoft Research Asia Beijing China University of Adelaide Australia

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects, relationships or semantics. The key challenge in Visual Dialogue task is thus to learn a more comprehensive and semantic-rich image representation which may have adaptive attentions on the image for variant questions. In this research, we propose a novel model to depict an image from both visual and semantic perspectives. Specifically, the visual view helps capture the appearance-level information, including objects and their relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Futhermore, on top of such multiview image features, we propose a feature selection framework which is able to adaptively capture question-relevant information hierarchically in fine-grained level. The proposed method achieved state-of-the-art results on benchmark Visual Dialogue datasets. More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values. It gives us insights in understanding of human cognition in Visual Dialogue. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

CogTree: Cognition tree loss for unbiased scene graph generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yu, Jing Chai, Yuan Wang, Yujing Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China Key Laboratory of Machine Perception MOE School of EECS Peking University Beijing China University of Adelaide Australia

Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional debiasing research mainly studies from the view of balancing data distribution or learning unbiased models and representations, ignoring the correlations among the biased classes. In this work, we analyze this problem from a novel cognition perspective: automatically building a hierarchical cognitive structure from the biased predictions and navigating that hierarchy to locate the relationships, making the tail relationships receive more attention in a coarse-to-fine mode. To this end, we propose a novel debiasing Cognition Tree (CogTree) loss for unbiased SGG. We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model. The CogTree distinguishes remarkably different relationships at first and then focuses on a small portion of easily confused ones. Then, we propose a debiasing loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships. The loss is model-agnostic and consistently boosting the performance of several state-of-the-art models. The code is available at: https://***/CYVincent/Scene-Graph-Transformer-CogTree. Copyright © 2020, The Authors. All rights reserved.

关键词： Forestry

Modeling Text with Graph Convolutional Network for Cross-Modal Information Retrieval

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, Jing Lu, Yuhang Qin, Zengchang Liu, Yanbing Tan, Jianlong Guo, Li Zhang, Weifeng Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Intelligent Computing and Machine Learning Lab School of Asee Beihang University China Hangzhou Dianzi University China

Cross-modal information retrieval aims to find heterogeneous data of various modalities from a given query of one modality. The main challenge is to map different modalities into a common semantic space, in which distance between concepts in different modalities can be well modeled. For crossmodal information retrieval between images and texts, existing work mostly uses off-the-shelf Convolutional Neural Network (CNN) for image feature extraction. For texts, word-level features such as bag-of-words or word2vec are employed to build deep learning models to represent texts. Besides word-level semantics, the semantic relations between words are also informative but less explored. In this paper, we model texts by graphs using similarity measure based on word2vec. A dual-path neural network model is proposed for couple feature learning in cross-modal information retrieval. One path utilizes Graph Convolutional Network (GCN) for text modeling based on graph representations. The other path uses a neural network with layers of nonlinearities for image modeling based on off-the-shelf features. The model is trained by a pairwise similarity loss function to maximize the similarity of relevant text-image pairs and minimize the similarity of irrelevant pairs. Experimental results show that the proposed model outperforms the state-of-the-art methods significantly, with 17% improvement on accuracy for the best case. Copyright © 2018, The Authors. All rights reserved.

关键词： Information retrieval