Search

Your search keyword '"Wang, Xueping"' showing total 1,323 results
Start Over "Wang, Xueping"

Refine your results

more »

more »

more »

more »

more »

more »
1,323 results on '"Wang, Xueping"'

1. Wang, Xueping

Author

Wang, Xueping and Wang, Xueping

Published
2020

2. Learning to Learn Transferable Generative Attack for Person Re-Identification

Author

Bian, Yuan, Liu, Min, Wang, Xueping, Ma, Yunfeng, and Wang, Yaonan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model\&dataset\&test black-box meta attack tasks. Specifically, cross-model\&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model\&dataset and cross-model\&dataset\&test attacks, our MTGA outperforms the SOTA methods by 21.5\% and 11.3\% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted.

Published
2024

20. Comparative Analysis of Sensory Evaluation Methods for Qingzhuan Tea

Author

LIU Panpan, FENG Lin, ZHENG Lin, XUE Jinjin, WANG Shengpeng, WANG Xueping, YE Fei, TENG Jing, GUI Anhui, HAN Yanna, CHEN Junhai, ZHU Peng, GAO Shiwei, ZHENG Pengcheng

Subjects
qingzhuan tea, sensory evaluation, compressed tea, water extract, Food processing and manufacture, TP368-456
Abstract

To propose a sensory evaluation method suitable for Qingzhuan tea, a representative Qingzhuan tea produced in Hubei was soak or spray boiled in order to analyze the effects of different boiling conditions on the sensory quality and the leaching rate of major chemical components of Qingzhuan tea. The sensory quality and chemical components of the tea infusions were compared with those of tea infusion obtained by the brewing method specified in the Chinese national standard. The results showed that the sensory quality of the boiled tea infusion was significantly better than that of the brewed tea infusion; the leaching rates of major quality components such as water extract, tea polyphenols, amino acids, soluble sugars and tea pigments were much higher in the former than in the latter. From the perspectives of sensory quality and the leaching rate of major quality components, tea infusion prepared by boiling for 2 min with a tea/water ratio of 1:80 and then standing for 2–4 min tasted moderate and had good internal quality. Further correlation analysis showed high correlation coefficients between the leaching rates of soluble sugars, theabrownine and water extract and taste quality. The results of this study provide a reference for the objective evaluation of the sensory quality of Qingzhuan tea and other types of compressed tea.

Published
2024
Full Text
View/download PDF

26. Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency

Author

Wang, Xueping, Li, Shasha, Liu, Min, Wang, Yaonan, and Roy-Chowdhury, Amit K.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID). However, ReID systems inherit the vulnerability of DNNs to malicious attacks of visually inconspicuous adversarial perturbations. Detection of adversarial attacks is, therefore, a fundamental requirement for robust ReID systems. In this work, we propose a Multi-Expert Adversarial Attack Detection (MEAAD) approach to achieve this goal by checking context inconsistency, which is suitable for any DNN-based ReID systems. Specifically, three kinds of context inconsistencies caused by adversarial attacks are employed to learn a detector for distinguishing the perturbed examples, i.e., a) the embedding distances between a perturbed query person image and its top-K retrievals are generally larger than those between a benign query image and its top-K retrievals, b) the embedding distances among the top-K retrievals of a perturbed query image are larger than those of a benign query image, c) the top-K retrievals of a benign query image obtained with multiple expert ReID models tend to be consistent, which is not preserved when attacks are present. Extensive experiments on the Market1501 and DukeMTMC-ReID datasets show that, as the first adversarial attack detection approach for ReID, MEAAD effectively detects various adversarial attacks and achieves high ROC-AUC (over 97.5%)., Comment: Accepted at IEEE ICCV 2021

Published
2021

31. Modified Brain Storm Optimization Algorithm for Solving Multimodal Multiobjective Optimization Problems

Author

Liu, Yue, Cheng, Shi, Wang, Xueping, Shan, Yuyuan, Lu, Hui, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Tan, Ying, editor, Shi, Yuhui, editor, and Luo, Wenjian, editor

Published
2023
Full Text
View/download PDF

32. Null-Space-Based Collaborative Guidance Strategy for Spacecraft Rendezvous and Docking with Non-cooperative Target

Author

Li, Qi, Song, Shuo, Niu, Zhiqi, Gou, QiuXiong, Wang, Xueping, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Yan, Liang, editor, and Deng, Yimin, editor

Published
2023
Full Text
View/download PDF

33. Small-molecule agents for cancer immunotherapy

Author

Wang, Fang, Fu, Kai, Wang, Yujue, Pan, Can, Wang, Xueping, Liu, Zeyu, Yang, Chuan, Zheng, Ying, Li, Xiaopeng, Lu, Yu, To, Kenneth Kin Wah, Xia, Chenglai, Zhang, Jianye, Shi, Zhi, Hu, Zeping, Huang, Min, and Fu, Liwu

Published
2024
Full Text
View/download PDF

42. Learning Person Re-identification Models from Videos with Weak Supervision

Author

Wang, Xueping, Paul, Sujoy, Raychaudhuri, Dripta S., Liu, Min, Wang, Yaonan, and Roy-Chowdhury, Amit K.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised alternatives. In order to cope with this issue, we introduce the problem of learning person re-identification models from videos with weak supervision. The weak nature of the supervision arises from the requirement of video-level labels, i.e. person identities who appear in the video, in contrast to the more precise framelevel annotations. Towards this goal, we propose a multiple instance attention learning framework for person re-identification using such video-level labels. Specifically, we first cast the video person re-identification task into a multiple instance learning setting, in which person images in a video are collected into a bag. The relations between videos with similar labels can be utilized to identify persons, on top of that, we introduce a co-person attention mechanism which mines the similarity correlations between videos with person identities in common. The attention weights are obtained based on all person images instead of person tracklets in a video, making our learned model less affected by noisy annotations. Extensive experiments demonstrate the superiority of the proposed method over the related methods on two weakly labeled person re-identification datasets.

Published
2020

50. Learning Person Re-Identification Models From Videos With Weak Supervision

Author

Wang, Xueping, Liu, Min, Raychaudhuri, Dripta S, Paul, Sujoy, Wang, Yaonan, and Roy-Chowdhury, Amit K

Subjects
Machine Learning, Information and Computing Sciences, Computer Vision and Multimedia Computation, Behavioral and Social Science, Basic Behavioral and Social Science, Videos, Annotations, Labeling, Task analysis, Feature extraction, Training, Reliability, Video person re-identification, weak supervision, co-person attention mechanism, cs.CV, Artificial Intelligence and Image Processing, Electrical and Electronic Engineering, Cognitive Sciences, Artificial Intelligence & Image Processing, Computer vision and multimedia computation, Graphics, augmented reality and games
Abstract

Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised alternatives. In order to cope with this issue, we introduce the problem of learning person re-identification models from videos with weak supervision. The weak nature of the supervision arises from the requirement of video-level labels, i.e. person identities who appear in the video, in contrast to the more precise frame-level annotations. Towards this goal, we propose a multiple instance attention learning framework for person re-identification using such video-level labels. Specifically, we first cast the video person re-identification task into a multiple instance learning setting, in which person images in a video are collected into a bag. The relations between videos with similar labels can be utilized to identify persons, on top of that, we introduce a co-person attention mechanism which mines the similarity correlations between videos with person identities in common. The attention weights are obtained based on all person images instead of person tracklets in a video, making our learned model less affected by noisy annotations. Extensive experiments demonstrate the superiority of the proposed method over the related methods on two weakly labeled person re-identification datasets.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results