Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Xu, Xuemiao"'
Autor:
Yang, Haoxin, Xu, Xuemiao, Xu, Cheng, Zhang, Huaidong, Qin, Jing, Wang, Yi, Heng, Pheng-Ann, He, Shengfeng
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as en
Externí odkaz:
http://arxiv.org/abs/2408.09458
Autor:
Jiang, Xinjie, Zheng, Chenxi, Xu, Xuemiao, Liu, Bangzhen, Zheng, Weiying, Zhang, Huaidong, He, Shengfeng
Video Visual Relation Detection (VidVRD) focuses on understanding how entities interact over time and space in videos, a key step for gaining deeper insights into video scenes beyond basic visual tasks. Traditional methods for VidVRD, challenged by i
Externí odkaz:
http://arxiv.org/abs/2408.09408
Autor:
Huang, Zikai, Xu, Xuemiao, Xu, Cheng, Zhang, Huaidong, Zheng, Chenxi, Qin, Jing, He, Shengfeng
Dance, as an art form, fundamentally hinges on the precise synchronization with musical beats. However, achieving aesthetically pleasing dance sequences from music is challenging, with existing methods often falling short in controllability and beat
Externí odkaz:
http://arxiv.org/abs/2407.07554
We propose a novel optimization-based human mesh recovery method from a single image. Given a test exemplar, previous approaches optimize the pre-trained regression network to minimize the 2D re-projection loss, which however suffer from over-/under-
Externí odkaz:
http://arxiv.org/abs/2401.14121
Autor:
Lin, Jiatai, Han, Guoqiang, Xu, Xuemiao, Liang, Changhong, Wong, Tien-Tsin, Chen, C. L. Philip, Liu, Zaiyi, Han, Chu
Class activation mapping~(CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation~(WSSS) and object localization~(WSOL). It is the weighted aggregation of the feature map
Externí odkaz:
http://arxiv.org/abs/2309.03509
Publikováno v:
Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023,16006-16015
Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective knowledge imita
Externí odkaz:
http://arxiv.org/abs/2303.09230
Autor:
Zhou, Yan, Qian, Jiechang, Zhang, Huaidong, Xu, Xuemiao, Sun, Huajie, Zeng, Fanzhi, Zhou, Yuexia
Publikováno v:
In Pattern Recognition August 2024 152
Autor:
Cai, Weiwei, Xu, Xuemiao, Xu, Jiajia, Zhang, Huaidong, Yang, Haoxin, Zhang, Kun, He, Shengfeng
Publikováno v:
In Information Fusion July 2024 107
Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of them clearly cannot realize real image editing. In this paper, we reso
Externí odkaz:
http://arxiv.org/abs/2107.13812
Autor:
Zhou, Yan, Sun, Huajie, Zhang, Huaidong, Xu, Xuemiao, Yi, Chang’an, Ye, Dewang, Zhou, Yuexia, Liu, Xiangyu
Publikováno v:
In Pattern Recognition May 2024 149