Zobrazeno 1 - 10
of 169
pro vyhledávání: '"LIU Yunze"'
Publikováno v:
Cailiao gongcheng, Vol 51, Iss 10, Pp 13-26 (2023)
Ga2O3 is an ultra-wide band semiconductor corresponding to the deep ultraviolet(UV) spectrum, which can be used to prepare solar-blind UV detectors. The solar-blind ultraviolet detectors are widely used in military and aerospace fields dueto strong a
Externí odkaz:
https://doaj.org/article/e5886ac55f3949f492b4ade2634ce330
Autor:
Liu, Yunze, Yi, Li
Mamba has achieved significant advantages in long-context modeling and autoregressive tasks, but its scalability with large parameters remains a major limitation in vision applications. pretraining is a widely used strategy to enhance backbone model
Externí odkaz:
http://arxiv.org/abs/2410.00871
Inconsistent responses of X-ray detector elements lead to stripe artifacts in the sinogram data, which manifest as ring artifacts in the reconstructed CT images, severely degrading image quality. This paper proposes a method for correcting stripe art
Externí odkaz:
http://arxiv.org/abs/2409.15731
The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion fo
Externí odkaz:
http://arxiv.org/abs/2405.11481
Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live, work, and communicate. However, it is difficult to learn the diverse intera
Externí odkaz:
http://arxiv.org/abs/2404.01081
Publikováno v:
ICRA2024
This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data
Externí odkaz:
http://arxiv.org/abs/2401.09057
Autor:
Liu, Yunze, Tinmaz, Hasan
Publikováno v:
Library Hi Tech News, 2024, Vol. 41, Issue 8, pp. 1-6.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/LHTN-12-2023-0221
We focus on the human-humanoid interaction task optionally with an object. We propose a new task named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The previous work only focuses o
Externí odkaz:
http://arxiv.org/abs/2312.08983
Understanding 4D point cloud sequences online is of significant practical value in various scenarios such as VR/AR, robotics, and autonomous driving. The key goal is to continuously analyze the geometry and dynamics of a 3D scene as unstructured and
Externí odkaz:
http://arxiv.org/abs/2310.08326
Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning
Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. Howev
Externí odkaz:
http://arxiv.org/abs/2212.05330