Filters








151 Hits in 1.7 sec

Learning Entity Linking Features for Emerging Entities [article]

Chenwei Ran, Wei Shen, Jianbo Gao, Yuhan Li, Jianyong Wang, Yantao Jia
2022 arXiv   pre-print
Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL
more » ... odels will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.
arXiv:2208.03877v1 fatcat:zy3owcj4prfa7gvxtsb5knxlru

Deep Group-shuffling Random Walk for Person Re-identification [article]

Yantao Shen, Hongsheng Li, Tong Xiao, Shuai Yi, Dapeng Chen, Xiaogang Wang
2018 arXiv   pre-print
Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images. It is generally treated as a retrieval problem, where the affinities between the probe image and gallery images (P2G affinities) are used to rank the retrieved gallery images. However, most existing methods only consider P2G affinities but ignore the affinities between all the gallery images (G2G affinity). Some frameworks incorporated G2G
more » ... inities into the testing process, which is not end-to-end trainable for deep neural networks. In this paper, we propose a novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes. The proposed approach aims at end-to-end refining the P2G affinities based on G2G affinity information with a simple yet effective matrix operation, which can be integrated into deep neural networks. Feature grouping and group shuffle are also proposed to apply rich supervisions for learning better person features. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by large margins, which demonstrate the effectiveness of our approach.
arXiv:1807.11178v1 fatcat:6n5ilferrrfrxckljx3cv6iulq

Person Re-identification with Deep Similarity-Guided Graph Neural Network [article]

Yantao Shen, Hongsheng Li, Shuai Yi, Dapeng Chen, Xiaogang Wang
2018 arXiv   pre-print
Shen et al. [57] utilized kronecker-product matching for person feature maps alignment. For metric learning, Paisitkriangkrai et al.  ... 
arXiv:1807.09975v1 fatcat:vgicyisilnhvxeqswge4w3kyp4

Disturbance observer-based hysteresis compensation for piezoelectric actuators

Steven Chang, Jingang Yi, Yantao Shen
2009 2009 American Control Conference  
We present a novel hysteresis compensation method for piezoelectric actuators. Instead of using any particular mathematical model of hysteresis, we consider the hysteresis nonlinearity as a disturbance over a linear system. A disturbance observer (DOB) is then utilized to estimate and compensate for the hysteresis nonlinearity. In contrast to the existing inverse model-based approaches, the DOBbased hysteresis compensation does not rely on any particular hysteresis model, and therefore provides
more » ... a simple and effective compensation mechanism. Experimental validation of the proposed hysteresis compensation is performed on a PMN-PT cantilever piezoelectric actuator. S. Chang is with the
doi:10.1109/acc.2009.5160703 dblp:conf/amcc/ChangYS09 fatcat:zczc6dth2vf7he6ic7ke2j4vaq

Towards Backward-Compatible Representation Learning [article]

Yantao Shen, Yuanjun Xiong, Wei Xia, Stefano Soatto
2021 arXiv   pre-print
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the
more » ... bedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.
arXiv:2003.11942v3 fatcat:xluhgshifbehnjvjuavopr574y

End-to-End Deep Kronecker-Product Matching for Person Re-identification [article]

Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang
2018 arXiv   pre-print
Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re-identification. The spatial layout and correspondences between query person images are vital information for tackling this problem but are ignored by most state-of-the-art methods. In this paper, we propose a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable
more » ... deep neural network. A novel feature soft warping scheme is designed for aligning the feature maps based on matching results, which is shown to be crucial for achieving superior accuracy. The multi-scale features based on hourglass-like networks and self-residual attention are also exploited to further boost the re-identification performance. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach.
arXiv:1807.11182v1 fatcat:fj6de6vusbesjl7bndbvvttium

Analyzing the Perceptual Attributes of Electro-tactile Stimuli as Function of Various Signal Properties [article]

Mehdi Rahimi, Fang Jiang, Yantao Shen,
2021 bioRxiv   pre-print
Shen are with the Department of Electrical and Biomedical Engineering, University of Nevada, Reno, Reno, NV, 89557 USA e-mails: mrahimi@samic.org, ytshen@unr.edu.  ... 
doi:10.1101/2021.08.08.455590 fatcat:f657i7gxjnardevjbafz7qoqzq

Progressive multi-atlas label fusion by dictionary evolution

Yantao Song, Guorong Wu, Khosro Bahrami, Quansen Sun, Dinggang Shen
2017 Medical Image Analysis  
Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the
more » ... onding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-bylayer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary. Keywords Brain MRI; sparse representation; hippocampus; label fusion; multi-atlas Sabuncu et al. (2010) . Apparently, the above point-wise label fusion strategies are highly dependent on the accuracy of image registration. To address the potential issue of inaccurate registration, Song et al.
doi:10.1016/j.media.2016.11.005 pmid:27914302 pmcid:PMC5239730 fatcat:2xptdcbgyfh5xh6zhhqa2mprrq

Non-Linearity of Skin Properties in Electrotactile Applications: Identification and Mitigation

Mehdi Rahimi, Fang Jiang, Yantao Shen
2019 IEEE Access  
YANTAO SHEN is currently an Associate Professor with the Department of Electrical and Biomedical Engineering, University of Nevada at Reno.  ... 
doi:10.1109/access.2019.2955648 pmid:33747667 pmcid:PMC7970715 fatcat:47pgdm62ajbppgoayqemeaoz4m

U1 snRNP regulates chromatin retention of noncoding RNAs [article]

Yafei Yin, Jinlong Yuyang Lu, Xuechun Zhang, Wen Shao, Yanhui Xu, Pan Li, Yantao Hong, Qiangfeng Cliff Zhang, Xiaohua Shen
2018 bioRxiv   pre-print
., and Shen, X. (2017) . Cis-and trans-acting lncRNAs in pluripotency and reprogramming. Curr Opin Genet Dev 46, 170-178.  ...  Tripathi, V., Ellis, J.D., Shen, Z., Song, D.Y., Pan, Q., Watt, A.T., Freier, S.M., Bennett, C.F., Sharma, A., Bubulya, P.A., et al. (2010).  ... 
doi:10.1101/310433 fatcat:krlm3x44kzc5raws36vi2bx2z4

Determining driver phone use leveraging smartphone sensors

Yantao Li, Gang Zhou, Yue Li, Du Shen
2015 Multimedia tools and applications  
Driver distraction by mobile phones has been a huge threat that leads to unnecessary accidents and human casualties, especially in hazardous road conditions. In this paper, we address a fundamental but critical issue of phone use during the driver behind the wheel. We propose, design and implement SafeDrive which achieves the goal of automatically determining driver phone use leveraging built-in smartphone sensors sensing driving conditions. We explore GPS and accelerometer sensors on
more » ... s to collect data, which can sufficiently capture driving conditions. With inputs of these data, we provide an accurate driving condition classification algorithm, that classifies driving conditions into five categories. Based on the classified driving conditions, SafeDrive makes a flexible control of driver phone use. We excessively evaluate the classification accuracy of our SafeDrive in local, highway, traffic jam, and complex conditions, respectively, and the results demonstrate that it can achieve up to 87 % classification accuracy in complex conditions.
doi:10.1007/s11042-015-2969-7 fatcat:g4263m2pxff45kwu33wouh7hny

Long-Time Behavior of Solution for a Reactor Model

Yantao Guo, Jianwei Shen, Qianqian Zheng
2015 Advances in Mathematical Physics  
In this paper, we would consider the dynamical behaviors of the chemical model represented by Satnoianu et al. (2001). Using the Kuratowski measure of noncompactness method, we prove the existence of global attractor for the weak solution semiflow of system. Finally, several numerical experiments confirm the theoretical results.
doi:10.1155/2015/547363 fatcat:eckrqxn7bbhqhoal3wibhwpqoq

Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals [article]

Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang
2017 arXiv   pre-print
Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recent advances of person re-identification techniques. However, unlike person re-identification, the visual differences between pairs of vehicle images are usually subtle and even challenging for humans to distinguish. Incorporating additional spatio-temporal information is vital for solving the challenging
more » ... on task. Existing vehicle re-identification methods ignored or used over-simplified models for the spatio-temporal relations between vehicle images. In this paper, we propose a two-stage framework that incorporates complex spatio-temporal information for effectively regularizing the re-identification results. Given a pair of vehicle images with their spatio-temporal information, a candidate visual-spatio-temporal path is first generated by a chain MRF model with a deeply learned potential function, where each visual-spatio-temporal state corresponds to an actual vehicle image with its spatio-temporal information. A Siamese-CNN+Path-LSTM model takes the candidate path as well as the pairwise queries to generate their similarity score. Extensive experiments and analysis show the effectiveness of our proposed method and individual components.
arXiv:1708.03918v1 fatcat:3rfxnsfcezamzbgnio2z5y74pq

Towards Universal Backward-Compatible Representation Learning [article]

Binjie Zhang, Yixiao Ge, Yantao Shen, Shupeng Su, Fanzi Wu, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan
2022 arXiv   pre-print
. ‡ Work done when Binjie and Yantao are at ARC Lab. of offline "backfilling" * the gallery is always necessary for conventional model upgrades in retrieval systems, which is computationally expensive  ...  As shown in Table 4 , we compare with BCT [Shen et al., 2020] and AML [Budnik and Avrithis, 2020] .  ... 
arXiv:2203.01583v2 fatcat:wilqpv2pozflbbicips33nulqm

Towards Backward-Compatible Representation Learning

Yantao Shen, Yuanjun Xiong, Wei Xia, Stefano Soatto
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the
more » ... bedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.
doi:10.1109/cvpr42600.2020.00640 dblp:conf/cvpr/ShenXXS20 fatcat:sq4jpmpzhbc2jh5rqq6dtfmjpy
« Previous Showing results 1 — 15 out of 151 results