Zobrazeno 1 - 10
of 366
pro vyhledávání: '"Fu, Dongmei"'
Autor:
Song, Guangxuan, Fu, Dongmei, Qiu, Zhongwei, Yang, Zijiang, Dai, Jiaxin, Ma, Lingwei, Zhang, Dawei
Using machine learning (ML) techniques to predict material properties is a crucial research topic. These properties depend on numerical data and semantic factors. Due to the limitations of small-sample datasets, existing methods typically adopt ML al
Externí odkaz:
http://arxiv.org/abs/2312.09744
Autor:
Ren, Zhongwei, Huang, Zhicheng, Wei, Yunchao, Zhao, Yao, Fu, Dongmei, Feng, Jiashi, Jin, Xiaojie
While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a challenge. To bridge this gap, we introduce PixelLM, an effective and effic
Externí odkaz:
http://arxiv.org/abs/2312.02228
3D style transfer aims to render stylized novel views of 3D scenes with the specified style, which requires high-quality rendering and keeping multi-view consistency. Benefiting from the ability of 3D representation from Neural Radiance Field (NeRF),
Externí odkaz:
http://arxiv.org/abs/2309.13607
Autor:
Qiu, Zhongwei, Yang, Qiansheng, Wang, Jian, Wang, Xiyu, Xu, Chang, Fu, Dongmei, Yao, Kun, Han, Junyu, Ding, Errui, Wang, Jingdong
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vi
Externí odkaz:
http://arxiv.org/abs/2306.17074
Autor:
He, Xingjian, Chen, Sihan, Ma, Fan, Huang, Zhicheng, Jin, Xiaojie, Liu, Zikang, Fu, Dongmei, Yang, Yi, Liu, Jing, Feng, Jiashi
Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. However, there is limited research on learning video-text representations for general video mul
Externí odkaz:
http://arxiv.org/abs/2305.13167
Autor:
Qiu, Zhongwei, Qiansheng, Yang, Wang, Jian, Feng, Haocheng, Han, Junyu, Ding, Errui, Xu, Chang, Fu, Dongmei, Wang, Jingdong
Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the global spati
Externí odkaz:
http://arxiv.org/abs/2303.09187
Video Super-Resolution (VSR) aims to restore high-resolution (HR) videos from low-resolution (LR) videos. Existing VSR techniques usually recover HR frames by extracting pertinent textures from nearby frames with known degradation processes. Despite
Externí odkaz:
http://arxiv.org/abs/2212.14046
Modeling dynamics in the form of partial differential equations (PDEs) is an effectual way to understand real-world physics processes. For complex physics systems, analytical solutions are not available and numerical solutions are widely-used. Howeve
Externí odkaz:
http://arxiv.org/abs/2211.13944
Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although existing methods
Externí odkaz:
http://arxiv.org/abs/2211.11983
Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the contextual depth fe
Externí odkaz:
http://arxiv.org/abs/2208.03431