检索结果-内蒙古大学图书馆

Visual analyses of music history: A user-centric approach

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Jingxian Liu, Dong Media Lab Massachusetts Institute of Technology CambridgeMA02139 United States CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Music history, referring to the records of users' listening or downloading history in online music services, is the primary source for music service providers to analyze users' preferences on music and thus to provide personalized recommendations to users. In order to engage users into the service and to improve user experience, it would be beneficial to provide visual analyses of one user's music history as well as visualized recommendations to that user. In this paper, we take a user-centric approach to the design of such visual analyses. We start by investigating user needs on such visual analyses and recommendations, then propose several different visualization schemes, and perform a pilot study to collect user feedback on the designed schemes. We further conduct user studies to verify the utility of the proposed schemes, and the results not only demonstrate the effectiveness of our proposed visualization, but also provide important insights to guide the visualization design in the future. Copyright © 2017, The Authors. All rights reserved.

关键词： Visualization

DeepEraser: Deep Iterative Context Mining for Generic Text Eraser

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Feng, Hao Wang, Wendi Liu, Shaokai Deng, Jiajun Zhou, Wengang Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The University of Adelaide Australian Institute for Machine Learning Australia

In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative operations. Our idea comes from the process of erasing pencil script, where the text area designated for removal is subject to continuous monitoring and the text is attenuated progressively, ensuring a thorough and clean erasure. Technically, at each iteration, an innovative erasing module is deployed, which not only explicitly aggregates the previous erasing progress but also mines additional semantic context to erase the target text. Through iterative refinements, the text regions are progressively replaced with more appropriate content and finally converge to a relatively accurate status. Furthermore, a custom mask generation strategy is introduced to improve the capability of DeepEraser for adaptive text removal, as opposed to indiscriminately removing all the text in an image. Our DeepEraser is notably compact with only 1.4M parameters and trained in an end-to-end manner. To verify its effectiveness, extensive experiments are conducted on several prevalent benchmarks, including SCUT-Syn, SCUT-EnsText, and Oxford Synthetic text dataset. The quantitative and qualitative results demonstrate the effectiveness of our DeepEraser over the state-of-the-art methods, as well as its strong generalization ability in custom mask text removal. The codes and pre-trained models are available at https://***/fh2019ustc/DeepEraser Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xie, Qiaokang Zhou, Wengang Qi, Guo-Jun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Huawei Cloud EI Product Department Huawei Noah's Ark Laboratory

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal information. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

Multi-Channel Spaceborne SAR Imaging Method for Maritime Scenarios

学校读者我要写书评

暂无评论

Multi-Channel Spaceborne SAR Imaging Method for Maritime Sce...

Sensor Array and Multichannel Signal processing Workshop

作者： Xiaolan Qiu Junying Yang Mingyang Shang Lihua Zhong Chibiao Ding Key Laboratory of Technology in GeoSpatial Information Processing and Application Systems Aerospace Information Research Institute Chinese Academy of Sciences Beijing China National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728119465

ISBN: (纸本)9781728119472

The spaceborne SAR is required to fulfill the increasing demands for improved spatial resolution and wider swath coverage in recent years. The azimuth multi-channel SAR system is a typical technique adopted for realizing high-resolution and wide-swath (HRWS) simultaneously. The flexibility of this system also provides favorable conditions for moving target detection. Aiming at the problems of moving target detection, velocity estimation, and imaging of SAR maritime scenes in the spaceborne multi-channel system, this paper proposes a set of processes based on coarse imaging, detection, velocity estimation and refocusing. The experimental results of the simulation verify the effectiveness of the method.

关键词： Azimuth Conferences Imaging Estimation Object detection Radar polarimetry Doppler effect

A HYBRID NEURAL NETWORK FOR CHROMA INTRA PREDICTION

学校读者我要写书评

暂无评论

A HYBRID NEURAL NETWORK FOR CHROMA INTRA PREDICTION

IEEE International Conference on Image processing

作者： Yue Li Li Li Zhu Li Jianchao Yang Ning Xu Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China University of Missouri Kansas City MO USA Snapchat Inc. CA USA

For chroma intra prediction, previous methods exemplified by the Linear Model method (LM) usually assume a linear correlation between the luma and chroma components in a coding block. This assumption is inaccurate for complex image content or large blocks, and restricts the prediction accuracy. In this paper, we propose a chroma intra prediction method by exploiting both spatial and cross-channel correlations using a hybrid neural network. Specifically, we utilize a convolutional neural network to extract features from the reconstructed luma samples of the current block, as well as utilize a fully connected network to extract features from the neighboring reconstructed luma and chroma samples. The extracted twofold features are then fused to predict the chroma samples-Cb and Cr simultaneously. The proposed chroma intra prediction method is integrated into HEVC. Preliminary results show that, compared with HEVC plus LM, the proposed method achieves on average 0.2%, 3.1% and 2.0% BD-rate reduction on Y, Cb and Cr components, respectively, under All-Intra configuration.

关键词： Feature extraction Neural networks Kernel Correlation Image reconstruction Encoding Prediction methods

A3Net: Adversarial-and-attention network for machine reading comprehension

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Jiuniu Fu, Xingyu Xu, Guangluan Wu, Yirong Chen, Ziyan Wei, Yang Jin, Li Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics CAS Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

In this paper, we introduce Adversarial-and-attention Network (A3Net) for Machine Reading Comprehension. This model extends existing approaches from two perspectives. First, adversarial training is applied to several target variables within the model, rather than only to the inputs or embeddings. We control the norm of adversarial perturbations according to the norm of original target variables, so that we can jointly add perturbations to several target variables during training. As an effective regularization method, adversarial training improves robustness and generalization of our model. Second, we propose a multi-layer attention network utilizing three kinds of high-efficiency attention mechanisms. Multi-layer attention conducts interaction between question and passage within each layer, which contributes to reasonable representation and understanding of the model. Combining these two contributions, we enhance the diversity of dataset and the information extracting ability of the model at the same time. Meanwhile, we construct A3Net for the WebQA dataset. Results show that our model outperforms the state-of-the-art models (improving Fuzzy Score from 73.50% to 77.0%). Copyright © 2018, The Authors. All rights reserved.

关键词： Network layers

Prior-enlightened and motion-robust video deblurring

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhou, Ya Xu, Jianfeng Tasaka, Kazuyuki Chena, Zhibo Li, Weiping CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230026 China KDDI Research Inc. Fujimino-shi Saitama356-8502 Japan

Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalization ability in handling challenging scenarios, like blur in low contrast or severe motion areas, and non-uniform blur. Therefore, we propose a PRiOr-enlightened and MOTION-robust video deblurring model (PROMOTION) suitable for challenging blurs. On the one hand, we use 3D group convolution to efficiently encode heterogeneous prior information, explicitly enhancing the scenes’ perception while mitigating the output’s artifacts. On the other hand, we design the priors representing blur distribution, to better handle non-uniform blur in spatio-temporal domain. Besides the classical camera shake caused global blurry, we also prove the generalization for the downstream task suffering from local blur. Extensive experiments demonstrate we can achieve the state-of-the-art performance on well-known REDS and GoPro datasets, and bring machine task gain. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion estimation

One-shot Generative Domain Adaptation in 3D GANs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Ziqiang Wu, Yi Wang, Chaoyue Rui, Xue Li, Bin Nanjing University of Information Science and Technology Nanjing China University of Science and Technology of China Hefei China University of Sydney Australia CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

3D-aware image generation necessitates extensive training data to ensure stable training and mitigate the risk of overfitting. This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at transferring a pre-trained 3D generator from one domain to a new one, relying solely on a single reference image. One-shot 3D GDA is characterized by the pursuit of specific attributes, namely, high fidelity, large diversity, cross-domain consistency, and multi-view consistency. Within this paper, we introduce 3D-Adapter, the first one-shot 3D GDA method, for diverse and faithful generation. Our approach begins by judiciously selecting a restricted weight set for fine-tuning, and subsequently leverages four advanced loss functions to facilitate adaptation. An efficient progressive fine-tuning strategy is also implemented to enhance the adaptation process. The synergy of these three technological components empowers 3D-Adapter to achieve remarkable performance, substantiated both quantitatively and qualitatively, across all desired properties of 3D GDA. Furthermore, 3D-Adapter seamlessly extends its capabilities to zero-shot scenarios, and preserves the potential for crucial tasks such as interpolation, reconstruction, and editing within the latent space of the pre-trained generator. Code will be available at https://***/iceli1007/3D-Adapter. © 2024, CC BY.

关键词： Generative adversarial networks

AUV dead-reckoning navigation based on neural network using a single accelerometer 11

学校读者我要写书评

暂无评论

AUV dead-reckoning navigation based on neural network using ...

11th ACM International Conference on Underwater Networks and systems, WUWNet 2016

作者： Xie, Yan-Xin Liu, Jun Hu, Cheng-Quan Cui, Jun-Hong Xu, Hongli State Key Laboratory of Robotics CAS No. 114 Nanta Street Shenhe District Shenyang China College of Computer Science and Technology Jilin University Changchun China Underwater Sensor Network Lab. University of Connecticut StorrsCT06269 United States Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (纸本)9781450346375

The accuracy of the Autonomous Underwater Vehicles (AUVs) navigation system determines whether they can safely operate and return. Traditional Dead-reckoning (DR) relies on the inertial sensors such as gyroscope and accelerometer. A major challenge for DR navigation is from measurement error of the inertial sensors (gyroscope, accelerometer, etc.), especially when the AUV is near or at the ocean surface. The AUV's motion is affected by ocean waves, and its pitch angle changes rapidly with the waves. This rapid change and the measurement errors will cause great noise to the direction measured by gyroscopes, and then lead to a large error to the DR navigation. To address this problem, a novel DR method based on neural network (DR-N) is proposed to explore the time-varying relationship between acceleration measurement and orientation measurement, which leverages acoustic localization and neural network estimate timely pitch angle through the explored time-varying relationship. This method enables AUV's DR navigation with a single acceleration, without relying on both acceleration and gyroscope. Most importantly, we can improve the accuracy of AUV navigation through avoiding DR errors caused by gyroscope noise at the sea surface. Simulations show DR-N significantly improves navigation accuracy.

关键词： Accelerometers