Search

Your search keyword '"Yu, Xiaofeng"' showing total 1,195 results
Start Over Author "Yu, Xiaofeng"
1,195 results on '"Yu, Xiaofeng"'

1. Design of the Pole-Climbing Robot Based on Yoshimura Origami Actuator

Author

Liu, Shilong, Tang, Gangqiang, Tan, Kangning, Yu, Xiaofeng, Mei, Dong, An, Shunan, Wang, Yanjie, Goos, Gerhard, Series 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, Lan, Xuguang, editor, Mei, Xuesong, editor, Jiang, Caigui, editor, Zhao, Fei, editor, and Tian, Zhiqiang, editor

Published
2025
Full Text
View/download PDF

2. PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control

Author

Zhong, Yong, Zhao, Min, You, Zebin, Yu, Xiaofeng, Zhang, Changwang, Li, Chongxuan, Goos, Gerhard, Series 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, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor

Published
2025
Full Text
View/download PDF

3. PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control

Author

Zhong, Yong, Zhao, Min, You, Zebin, Yu, Xiaofeng, Zhang, Changwang, and Li, Chongxuan

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

In this paper, we introduce PoseCrafter, a one-shot method for personalized video generation following the control of flexible poses. Built upon Stable Diffusion and ControlNet, we carefully design an inference process to produce high-quality videos without the corresponding ground-truth frames. First, we select an appropriate reference frame from the training video and invert it to initialize all latent variables for generation. Then, we insert the corresponding training pose into the target pose sequences to enhance faithfulness through a trained temporal attention module. Furthermore, to alleviate the face and hand degradation resulting from discrepancies between poses of training videos and inference poses, we implement simple latent editing through an affine transformation matrix involving facial and hand landmarks. Extensive experiments on several datasets demonstrate that PoseCrafter achieves superior results to baselines pre-trained on a vast collection of videos under 8 commonly used metrics. Besides, PoseCrafter can follow poses from different individuals or artificial edits and simultaneously retain the human identity in an open-domain training video. Our project page is available at https://ml-gsai.github.io/PoseCrafter-demo/.

Published
2024

17. An Explicit Form with Continuous Attribute Profile of the Partial Mastery DINA Model

Author

Shu, Tian, Luo, Guanzhong, Luo, Zhaosheng, Yu, Xiaofeng, Guo, Xiaojun, and Li, Yujun

Abstract

Cognitive diagnosis models (CDMs) are the statistical framework for cognitive diagnostic assessment in education and psychology. They generally assume that subjects' latent attributes are dichotomous--mastery or nonmastery, which seems quite deterministic. As an alternative to dichotomous attribute mastery, attention is drawn to the use of a continuous attribute mastery format in recent literature. To obtain subjects' finer-grained attribute mastery for more precise diagnosis and guidance, an equivalent but more explicit form of the partial-mastery-deterministic inputs, noisy "and" gate (DINA) model (termed continuous attribute profile [CAP]-DINA form) is proposed in this article. Its parameters estimation algorithm based on this form using Bayesian techniques with Markov chain Monte Carlo algorithm is also presented. Two simulation studies are conducted then to explore its parameter recovery and model misspecification, and the results demonstrate that the CAP-DINA form performs robustly with satisfactory efficiency in these two aspects. A real data study of the English test also indicates it has a better model fit than DINA.

Published
2023
Full Text
View/download PDF

27. CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data

Author

Zhang, Ke, Fan, Jin, Huang, Shaoli, Qiao, Yongliang, Yu, Xiaofeng, and Qin, Feiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels, which produces additional noise harmful to the performance of networks. Motivated by this, we present a simple yet effective cross ensemble knowledge distillation (CEKD) model for fine-grained feature learning. We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem. The proposed model can be trained in an end-to-end manner, and only requires image-level label supervision. Extensive experiments on widely used fine-grained benchmarks demonstrate the effectiveness of our proposed model. Specifically, with the backbone of ResNet-101, CEKD obtains the accuracy of 89.59%, 95.96% and 94.56% in three datasets respectively, outperforming state-of-the-art API-Net by 0.99%, 1.06% and 1.16%.

Published
2022
Full Text
View/download PDF

37. Synthesis of a novel water-soluble pyridine dicarboxylate and its application in fluorescence cell imaging

Author

Wei Zhengyou, Qi Yanan, Ji Qilin, Song Liujun, and Yu Xiaofeng

Subjects
pyridine dicarboxylic acid, two-photon absorption, fluorescent cell imaging, quaternary ammonium ions, Organic chemistry, QD241-441
Abstract

A novel water-soluble substituted pyridine dicarboxylate containing a quaternary ammonium ion with potential applications in fluorescence cell imaging was synthesized and characterized. Remarkably, this compound exhibited water solubility in the absence of additional solubilizers, enabling direct dissolution in phosphate-buffered saline for cell studies. No obvious cytotoxicity was observed in 4T1 cells (mouse breast cancer cells) within the concentration range of 0.2–25 μmol L−1, with a cell survival rate above 89%. Furthermore, the compound exhibited a maximum two-photon absorption cross-section of 86 GM at an excitation wavelength of 780 nm, demonstrating high cell permeability, effective distribution in the cytoplasm, and preferential targeting of organelles. Single- and two-photon fluorescence imaging of cells revealed a distinctive blue emission and strong bright green emission, respectively. The newly synthesized substituted pyridine dicarboxylate exhibited low cytotoxicity and strong fluorescence imaging properties, demonstrating its potential in cell imaging applications.

Published
2024
Full Text
View/download PDF

43. Diffusion Limit of Poisson Limit-Order Book Models

Author

Almost, Christopher, Lehoczky, John, Shreve, Steven, and Yu, Xiaofeng

Subjects
Mathematics - Probability, Primary 60F17, 91G80, Secondary 60J55, 60G55
Abstract

This ia a companion paper to Almost, Lehoczky, Shreve & Yu \cite{ALSY}, where the rationale for studying the diffusion limit of Poisson limit-order book models is explained and the results of a particular "representative" model are detailed. This paper contains the proofs and technical details cited in that work., Comment: 89 pages

Published
2020

44. Limits of Limit-Order Books

Author

Almost, Christopher, Lehoczky, John, Shreve, Steven, Yu, Xiaofeng, Morel, Jean-Michel, Editor-in-Chief, Teissier, Bernard, Editor-in-Chief, Baur, Karin, Series Editor, Brion, Michel, Series Editor, Huber, Annette, Series Editor, Khoshnevisan, Davar, Series Editor, Kontoyiannis, Ioannis, Series Editor, Kunoth, Angela, Series Editor, Mézard, Ariane, Series Editor, Podolskij, Mark, Series Editor, Policott, Mark, Series Editor, Serfaty, Sylvia, Series Editor, Székelyhidi, László, Series Editor, Vezzosi, Gabriele, Series Editor, and Wienhard, Anna, Series Editor

Published
2023
Full Text
View/download PDF

47. m6A methylation reader IGF2BP2 activates endothelial cells to promote angiogenesis and metastasis of lung adenocarcinoma

Author

Fang, Han, Sun, Qi, Zhou, Jin, Zhang, Huijuan, Song, Qiong, Zhang, Hua, Yu, Guohua, Guo, Ying, Huang, Chengyu, Mou, Yakui, Jia, Chuanliang, Song, Yingjian, Liu, Aina, Song, Kaiyu, Lu, Congxian, Tian, Ruxian, Wei, Shizhuang, Yang, Dengfeng, Chen, Yixuan, Li, Ting, Wang, Kejian, Yu, Yilan, Lv, Yufeng, Mo, Ke, Sun, Ping, Yu, Xiaofeng, and Song, Xicheng

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results