Zobrazeno 1 - 10
of 1 177
pro vyhledávání: '"YANG, Lixin"'
Autor:
Yang, Lixin, Yan, Li
We revisit the canonical formulation of spin hydrodynamics for Dirac fermions with a general thermal vorticity. The orders of the general thermal vorticity and the corresponding spin variables are considered independently from those of the convention
Externí odkaz:
http://arxiv.org/abs/2410.07583
This work introduces a novel and generalizable multi-view Hand Mesh Reconstruction (HMR) model, named POEM, designed for practical use in real-world hand motion capture scenarios. The advances of the POEM model consist of two main aspects. First, con
Externí odkaz:
http://arxiv.org/abs/2408.10581
Generating natural human grasps necessitates consideration of not just object geometry but also semantic information. Solely depending on object shape for grasp generation confines the applications of prior methods in downstream tasks. This paper pre
Externí odkaz:
http://arxiv.org/abs/2404.03590
Autor:
Zhan, Xinyu, Yang, Lixin, Zhao, Yifei, Mao, Kangrui, Xu, Hanlin, Lin, Zenan, Li, Kailin, Lu, Cewu
We present OAKINK2, a dataset of bimanual object manipulation tasks for complex daily activities. In pursuit of constructing the complex tasks into a structured representation, OAKINK2 introduces three level of abstraction to organize the manipulatio
Externí odkaz:
http://arxiv.org/abs/2403.19417
Radiative heat transfer has been proven to be important during the ignition process in gas turbine. Those radiating gases (CO2, H2O, CO) generated during combustion may display strong spectral, or nongray behavior, which is difficult to both characte
Externí odkaz:
http://arxiv.org/abs/2403.02743
Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage both modal
Externí odkaz:
http://arxiv.org/abs/2310.14216
Autor:
Li, Kailin, Yang, Lixin, Zhen, Haoyu, Lin, Zenan, Zhan, Xinyu, Zhong, Licheng, Xu, Jian, Wu, Kejian, Lu, Cewu
In daily life, humans utilize hands to manipulate objects. Modeling the shape of objects that are manipulated by the hand is essential for AI to comprehend daily tasks and to learn manipulation skills. However, previous approaches have encountered di
Externí odkaz:
http://arxiv.org/abs/2308.10574
The reconstruction of object surfaces from multi-view images or monocular video is a fundamental issue in computer vision. However, much of the recent research concentrates on reconstructing geometry through implicit or explicit methods. In this pape
Externí odkaz:
http://arxiv.org/abs/2308.06962
Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from image-mesh misalignment, resulting
Externí odkaz:
http://arxiv.org/abs/2304.05690
Enable neural networks to capture 3D geometrical-aware features is essential in multi-view based vision tasks. Previous methods usually encode the 3D information of multi-view stereo into the 2D features. In contrast, we present a novel method, named
Externí odkaz:
http://arxiv.org/abs/2304.04038