Zobrazeno 1 - 10
of 142
pro vyhledávání: '"Liu, Xinchen"'
Human motion capture is the foundation for many computer vision and graphics tasks. While industrial motion capture systems with complex camera arrays or expensive wearable sensors have been widely adopted in movie and game production, consumer-affor
Externí odkaz:
http://arxiv.org/abs/2407.16341
We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these approache
Externí odkaz:
http://arxiv.org/abs/2312.02232
Multi-modal human action segmentation is a critical and challenging task with a wide range of applications. Nowadays, the majority of approaches concentrate on the fusion of dense signals (i.e., RGB, optical flow, and depth maps). However, the potent
Externí odkaz:
http://arxiv.org/abs/2311.17428
Binary silhouettes and keypoint-based skeletons have dominated human gait recognition studies for decades since they are easy to extract from video frames. Despite their success in gait recognition for in-the-lab environments, they usually fail in re
Externí odkaz:
http://arxiv.org/abs/2308.16739
Autor:
Liu, Xinchen1 (AUTHOR) liuxinxhen@bjfu.edu, Ning, Xuanwei2 (AUTHOR) nxw981024@126.com, Wu, Chengliang1 (AUTHOR) wubjfu@163.com, Zhang, Yang1 (AUTHOR) zhangyang052012@aliyun.com
Publikováno v:
Energies (19961073). Sep2024, Vol. 17 Issue 18, p4655. 27p.
Autor:
Zheng, Jinkai, Liu, Xinchen, Gu, Xiaoyan, Sun, Yaoqi, Gan, Chuang, Zhang, Jiyong, Liu, Wu, Yan, Chenggang
Existing studies for gait recognition are dominated by in-the-lab scenarios. Since people live in real-world senses, gait recognition in the wild is a more practical problem that has recently attracted the attention of the community of multimedia and
Externí odkaz:
http://arxiv.org/abs/2209.00355
Human motion transfer refers to synthesizing photo-realistic and temporally coherent videos that enable one person to imitate the motion of others. However, current synthetic videos suffer from the temporal inconsistency in sequential frames that sig
Externí odkaz:
http://arxiv.org/abs/2209.00233
Autor:
Yang, Quanwei, Liu, Xinchen, Liu, Wu, Xie, Hongtao, Gu, Xiaoyan, Yu, Lingyun, Zhang, Yongdong
Human Video Motion Transfer (HVMT) aims to, given an image of a source person, generate his/her video that imitates the motion of the driving person. Existing methods for HVMT mainly exploit Generative Adversarial Networks (GANs) to perform the warpi
Externí odkaz:
http://arxiv.org/abs/2209.00475
Recognizing human actions from point cloud videos has attracted tremendous attention from both academia and industry due to its wide applications like automatic driving, robotics, and so on. However, current methods for point cloud action recognition
Externí odkaz:
http://arxiv.org/abs/2209.00407
Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. However, humans live and walk in the unconstrained 3D space, so projecting the 3D human body onto the 2
Externí odkaz:
http://arxiv.org/abs/2204.02569