Filters








1,773 Hits in 1.7 sec

Tong Nian Mei Xue: Guan Cha Yu Si Kao/童年 美学: 观察与思考 by Fang Weiping

Hui-Ling Huang
2018 Bookbird: A Journal of International Children's Literature  
SI KAO / 童年 美学: 观察与思考 [The Aesthetics of Childhood: Observations and Reflections] By Fang Weiping.  ...  the collection of essays Rejuvenated Antiquity, were inspired by the intensive reception of antique mythology in twenty-first-century popular culture to study this HUI-LING HUANG MEI XUE: GUAN CHA YU  ... 
doi:10.1353/bkb.2018.0013 fatcat:msu4ncwwo5afjoyu3dnbt3tgde

International Students and U.S. Academic Libraries Revisited

Weiping Zhang
2006 Tushuguanxue yu Zixun Kexue  
Academic Libraries Revisited Weiping Zhang Libraries and Media Services, Kent State University Email: wzhang1@kentvm.kent.edu Keywords International Students; Academic Libraries; Library Skills; Information  ... 
doaj:183ef26689c74438841145abb697f516 fatcat:agzg7ccjn5cpvo2q23iyosho74

Exploring Instance Relations for Unsupervised Feature Embedding [article]

Yifei Zhang, Yu Zhou, Weiping Wang
2021 arXiv   pre-print
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations. In this paper, we explore instance relations including intra-instance multi-view relation and inter-instance interpolation relation for unsupervised feature embedding.
more » ... y, we embed intra-instance multi-view relation by aligning the distribution of the distance between an instance's different augmented samples and negative samples. We explore inter-instance interpolation relation by transferring the ratio of information for image sample interpolation from pixel space to feature embedding space. The proposed approach, referred to as EIR, is simple-yet-effective and can be easily inserted into existing view-invariant contrastive learning based methods. Experiments conducted on public benchmarks for image classification and retrieval report state-of-the-art or comparable performance.
arXiv:2105.03341v1 fatcat:zmd7hz32w5gnjb54elrtapg2ei

Multi-View Correlation Distillation for Incremental Object Detection [article]

Dongbao Yang, Yu Zhou, Weiping Wang
2021 arXiv   pre-print
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data. Fine-tuning the old model with only new data will lead to a well-known phenomenon of catastrophic forgetting, which severely degrades the performance of modern object detectors. In this paper, we propose a novel
more » ... View Correlation Distillation (MVCD) based incremental object detection method, which explores the correlations in the feature space of the two-stage object detector (Faster R-CNN). To better transfer the knowledge learned from the old classes and maintain the ability to learn new classes, we design correlation distillation losses from channel-wise, point-wise and instance-wise views to regularize the learning of the incremental model. A new metric named Stability-Plasticity-mAP is proposed to better evaluate both the stability for old classes and the plasticity for new classes in incremental object detection. The extensive experiments conducted on VOC2007 and COCO demonstrate that MVCD can effectively learn to detect objects of new classes and mitigate the problem of catastrophic forgetting.
arXiv:2107.01787v1 fatcat:o5xgcdrc6fbcngi3lcd6jq6loe

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification [article]

Yucan Zhou, Yu Wang, Jianfei Cai, Yu Zhou, Qinghua Hu, Weiping Wang
2020 arXiv   pre-print
Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have received much attention, which train a meta-learner on massive additional tasks to gain the knowledge to instruct the few-shot classification. Usually, the training tasks are randomly sampled and performed indiscriminately, often making the meta-learner stuck into a bad local optimum. Some works in the optimization of
more » ... p neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better. Inspired by this idea, we propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly, where easy tasks are preferred in the first phase, then, hard tasks are emphasized in the second phase. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task based on the distinguishability of its categories. In addition, we explore multiple hardness measurements including the semantic relation, the pairwise Euclidean distance, the Hausdorff distance, and the Hilbert-Schmidt independence criterion. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.
arXiv:2007.06240v1 fatcat:34qfap2as5bupemk6zdksje3oe

Price Interpretability of Prediction Markets: A Convergence Analysis [article]

Dian Yu, Jianjun Gao, Weiping Wu, Zizhuo Wang
2022 arXiv   pre-print
Prediction markets are long known for prediction accuracy. However, there is still a lack of systematic understanding of how prediction markets aggregate information and why they work so well. This work proposes a multivariate utility (MU)-based mechanism that unifies several existing prediction market-making schemes. Based on this mechanism, we derive convergence results for markets with myopic, risk-averse traders who repeatedly interact with the market maker. We show that the resulting
more » ... ng wealth distribution lies on the Pareto efficient frontier defined by all market participants' utilities. With the help of this result, we establish both analytical and numerical results for the limiting price for different market models. We show that the limiting price converges to the geometric mean of agents' beliefs for exponential utility-based markets. For risk measure-based markets, we construct a risk measure family that meets the convergence requirements and show that the limiting price can converge to a weighted power mean of agent beliefs. For markets based on hyperbolic absolute risk aversion (HARA) utilities, we show that the limiting price is also a risk-adjusted weighted power mean of agent beliefs, even though the trading order will affect the aggregation weights. We further propose an approximation scheme for the limiting price under the HARA utility family. We show through numerical experiments that our approximation scheme works well in predicting the convergent prices.
arXiv:2205.08913v1 fatcat:7iah5vel6zcklgm5xwiiwtb4zu

Oxidized phospholipids are ligands for LRP6

Lei Wang, Yu Chai, Changjun Li, Haiyun Liu, Weiping Su, Xiaonan Liu, Bing Yu, Weiqi Lei, Bin Yu, Janet L. Crane, Xu Cao, Mei Wan
2018 Bone Research  
Low-density lipoprotein receptor-related protein 6 (LRP6) is a co-receptor for Wnt signaling and can be recruited by multiple growth factors/hormones to their receptors facilitating intracellular signaling activation. The ligands that bind directly to LRP6 have not been identified. Here, we report that bioactive oxidized phospholipids (oxPLs) are native ligands of LRP6, but not the closely related LRP5. oxPLs are products of lipid oxidation involving in pathological conditions such as
more » ... emia, atherosclerosis, and inflammation. We found that cell surface LRP6 in bone marrow mesenchymal stromal cells (MSCs) decreased rapidly in response to increased oxPLs in marrow microenvironment. LRP6 directly bound and mediated the uptake of oxPLs by MSCs. oxPL-LRP6 binding induced LRP6 endocytosis through a clathrin-mediated pathway, decreasing responses of MSCs to osteogenic factors and diminishing osteoblast differentiation ability. Thus, LRP6 functions as a receptor and molecular target of oxPLs for their adverse effect on MSCs, revealing a potential mechanism underlying atherosclerosis-associated bone loss. (2018) 6:22 ; https://doi.Bone Research (2018) 6:22 1234567890();,: Bone Research Oxidized phospholipids are ligands for LRP6 Wang et al. Oxidized phospholipids are ligands for LRP6 Wang et al.
doi:10.1038/s41413-018-0023-x pmid:30038821 pmcid:PMC6050227 fatcat:n3d5knrilzbb5d6jictgovzu6i

Region Normalization for Image Inpainting [article]

Tao Yu, Zongyu Guo, Xin Jin, Shilin Wu, Zhibo Chen, Weiping Li, Zhizheng Zhang, Sen Liu
2019 arXiv   pre-print
al. 2018) and GC (Yu et al. 2019) .  ...  Recent image inpainting works, such as (Yu et al. 2018; Liu et al. 2018; Yu et al. 2019; Nazeri et al. 2019) , focus on the learningbased methods.  ... 
arXiv:1911.10375v1 fatcat:2z2hcrdi75gjvohb2s2aswxpnq

Secrecy Communication with Security Rate Measure [article]

Lei Yu, Houqiang Li, Weiping Li
2015 arXiv   pre-print
We introduce a new measure on secrecy, which is established based on rate-distortion theory. It is named security rate, which is the minimum (infimum) of the additional rate needed to reconstruct the source within target distortion level with any positive probability for wiretapper. It denotes the minimum distance in information metric (bits) from what wiretapper has received to any decrypted reconstruction (where decryption is defined as reconstruction within target distortion level with some
more » ... ositive possibility). By source coding theorem, it is equivalent to a distortion-based equivocation _p(v^n|s^n,m):Ed(S^n,V^n)< D_E1/nI(S^n;V^n|M) which can be seen as a direct extension of equivocation 1/nH(S^n|M) to lossy decryption case, given distortion level D_E and the received (encrypted) message M of wiretapper. In this paper, we study it in Shannon cipher system with lossless communication, where a source is transmitted from sender to legitimate receiver secretly and losslessly, and also eavesdropped by a wiretapper. We characterize the admissible region of secret key rate, coding rate of the source, wiretapper distortion, and security rate (distortion-based equivocation). Since the security rate equals the distortion-based equivocation, and the equivocation is a special case of the distortion-based equivocation (with Hamming distortion measure and D_E=0), this gives an answer for the meaning of the maximum equivocation.
arXiv:1504.04239v2 fatcat:bgjyv7k62zbfjfhp7ksuraavd4

Video 3D Sampling for Self-supervised Representation Learning [article]

Wei Li, Dezhao Luo, Bo Fang, Yu Zhou, Weiping Wang
2021 arXiv   pre-print
Most of the existing video self-supervised methods mainly leverage temporal signals of videos, ignoring that the semantics of moving objects and environmental information are all critical for video-related tasks. In this paper, we propose a novel self-supervised method for video representation learning, referred to as Video 3D Sampling (V3S). In order to sufficiently utilize the information (spatial and temporal) provided in videos, we pre-process a video from three dimensions (width, height,
more » ... me). As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target. In our implementation, we combine the sampling of the three dimensions and propose the scale and projection transformations in space and time respectively. The experimental results show that, when applied to action recognition, video retrieval and action similarity labeling, our approach improves the state-of-the-arts with significant margins.
arXiv:2107.03578v1 fatcat:4z343fgypjg6dk62s54bv2bkk4

Gaussian Constrained Attention Network for Scene Text Recognition [article]

Zhi Qiao, Xugong Qin, Yu Zhou, Fei Yang, Weiping Wang
2020 arXiv   pre-print
Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem of attention diffusion, in which the model may not focus on a certain character area. In this paper, we propose Gaussian Constrained Attention Network to deal with this problem. It is a 2D attention-based method integrated with a novel Gaussian Constrained
more » ... finement Module, which predicts an additional Gaussian mask to refine the attention weights. Different from adopting an additional supervision on the attention weights simply, our proposed method introduces an explicit refinement. In this way, the attention weights will be more concentrated and the attention-based recognition network achieves better performance. The proposed Gaussian Constrained Refinement Module is flexible and can be applied to existing attention-based methods directly. The experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. Our code has been available at https://github.com/Pay20Y/GCAN.
arXiv:2010.09169v1 fatcat:kdtlsnjxlrc7lf3aaurilzobfa

Self-Training for Domain Adaptive Scene Text Detection [article]

Yudi Chen, Wei Wang, Yu Zhou, Fei Yang, Dongbao Yang, Weiping Wang
2020 arXiv   pre-print
Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the detector in the target domain. However, data collection and annotation are expensive and time-consuming. To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images. To
more » ... ce the noise of hard examples, a novel text mining module is implemented based on the fusion of detection and tracking results. Then, an image-to-video generation method is designed for the tasks that videos are unavailable and only images can be used. Experimental results on standard benchmarks, including ICDAR2015, MSRA-TD500, ICDAR2017 MLT, demonstrate the effectiveness of our self-training method. The simple Mask R-CNN adapted with self-training and fine-tuned on real data can achieve comparable or even superior results with the state-of-the-art methods.
arXiv:2005.11487v1 fatcat:osfdmip3lfeujgxe5gyyesbiku

MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification [article]

Xiaoni Li, Yucan Zhou, Yu Zhou, Weiping Wang
2021 arXiv   pre-print
Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes. As the label structure decides its performance, many existing approaches attempt to construct an excellent label structure for promoting the classification results. In this paper, we consider that different label structures provide a variety of prior knowledge for category recognition, thus fusing them is helpful to achieve better hierarchical classification
more » ... ts. Furthermore, we propose a multi-task multi-structure fusion model to integrate different label structures. It contains two kinds of branches: one is the traditional classification branch to classify the common subclasses, the other is responsible for identifying the heterogeneous superclasses defined by different label structures. Besides the effect of multiple label structures, we also explore the architecture of the deep model for better hierachical classification and adjust the hierarchical evaluation metrics for multiple label structures. Experimental results on CIFAR100 and Car196 show that our method obtains significantly better results than using a flat classifier or a hierarchical classifier with any single label structure.
arXiv:2107.00808v1 fatcat:2trbaaf7nrenfh6hqe6xbuug5q

UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection [article]

Youhui Guo, Yu Zhou, Xugong Qin, Enze Xie, Weiping Wang
2022 arXiv   pre-print
Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However, there are obvious domain discrepancies between synthetic data and real-world data. It may lead to sub-optimal performance to directly adopt the model initialized by synthetic data in the fine-tuning stage. In this paper, we propose a new training paradigm for scene text detection, which introduces an UNsupervised
more » ... ermediate Training Stage (UNITS) that builds a buffer path to real-world data and can alleviate the gap between the pre-training stage and fine-tuning stage. Three training strategies are further explored to perceive information from real-world data in an unsupervised way. With UNITS, scene text detectors are improved without introducing any parameters and computations during inference. Extensive experimental results show consistent performance improvements on three public datasets.
arXiv:2205.04683v1 fatcat:omey6alyczh6vezqkx3lxjsw5u

An Environmentally-Adaptive Hawkes Process with An Application to COVID-19 [article]

Tingnan Gong, Yu Chen, Weiping Zhang
2021 arXiv   pre-print
We proposed a new generalized model based on the classical Hawkes process with environmental multipliers, which is called an environmentally-adaptive Hawkes (EAH) model. Compared to the classical self-exciting Hawkes process, the EAH model exhibits more flexibility in a macro environmentally temporal sense, and can model more complex processes by using dynamic branching matrix. We demonstrate the well-definedness of this EAH model. A more specified version of this new model is applied to model
more » ... OVID-19 pandemic data through an efficient EM-like algorithm. Consequently, the proposed model consistently outperforms the classical Hawkes process.
arXiv:2101.09942v1 fatcat:ayz7pwuetrg5rdvrzwvzeepmtq
« Previous Showing results 1 — 15 out of 1,773 results