Search Results - "Zhu, Haoyi"

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time by Fang, Hao-Shu, Li, Jiefeng, Tang, Hongyang, Xu, Chao, Zhu, Haoyi, Xiu, Yuliang, Li, Yong-Lu, Lu, Cewu

“…Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans…”
Get full text

AlphaTracker: a multi-animal tracking and behavioral analysis tool by Chen, Zexin, Zhang, Ruihan, Fang, Hao-Shu, Zhang, Yu E, Bal, Aneesh, Zhou, Haowen, Rock, Rachel R, Padilla-Coreano, Nancy, Keyes, Laurel R, Zhu, Haoyi, Li, Yong-Lu, Komiyama, Takaki, Tye, Kay M, Lu, Cewu

“…Computer vision has emerged as a powerful tool to elevate behavioral research. This protocol describes a computer vision machine learning pipeline called…”
Get full text

X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360° Insufficient RGB-D Views by Zhu, Haoyi

“…Neural Radiance Fields (NeRFs), despite their outstanding performance on novel view synthesis, often need dense input views. Many papers train one model for…”
Get full text

Unlocking the dual role of LSD1 in tumor immunity: innate and adaptive pathways by Zhang, Yu, Guo, Ningjie, Zhu, Haoyi, Liu, Mengyang, Hao, Jiahui, Wang, Shoukai, Guo, Ting, Mamun, MAA, Pang, Jingru, Liu, Qi, Zheng, Yichao, Liu, Hongmin, Si, Pilei, Zhao, Lijuan

Get full text

Unsupervised Multi-Task Learning for 3D Subtomogram Image Alignment, Clustering and Segmentation by Zhu, Haoyi, Wang, Chuting, Wang, Yuanxin, Fan, Zhaoxin, Uddin, Mostofa Rafid, Gao, Xin, Zhang, Jing, Zeng, Xiangrui, Xu, Min

“…3D subtomogram image alignment, clustering, and segmentation are vital to macromolecular structure recognition in cryo-electron tomography (cryo-ET). However,…”
Get full text

X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views by Zhu, Haoyi, Fang, Hao-Shu, Lu, Cewu

“…Neural Radiance Fields (NeRFs), despite their outstanding performance on novel view synthesis, often need dense input views. Many papers train one model for…”
Get full text

Application of Virtual Reality Technology Based on Fast Filtering Algorithm in Switching Operation of Substation by Zhu, Haoyi, Qiao, Shi, Lu, Yi, Zhao, Xiaolin

“…At present, VR(Virtual Reality) technology is widely used in various fields, and its effective integration with power system can realize the application of the…”
Get full text

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation by Zhu, Haoyi, Yang, Honghui, Wang, Yating, Yang, Jiange, Wang, Limin, He, Tong

“…In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach…”
Get full text

Research and application of substation operation auxiliary command technology by Zhu, Haoyi, Qiao, Shi, Lu, Yi, Zhao, Xiaolin

“…Based on the application of MR technology in the power system, mainly focusing on the three-dimensional display of the whole resources of the power grid, this…”
Get full text

Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning by Zhu, Haoyi, Wang, Yating, Huang, Di, Ye, Weicai, Ouyang, Wanli, He, Tong

“…In robot learning, the observation space is crucial due to the distinct characteristics of different modalities, which can potentially become a bottleneck…”
Get full text

Multi-Person Full Body Pose Estimation by Zhu, Haoyi, Jie, Cheng, Jiang, Shaofei

“…Multi-person pose estimation plays an important role in many fields. Although previous works have researched a lot on different parts of human pose estimation,…”
Get full text

RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot by Fang, Hao-Shu, Fang, Hongjie, Tang, Zhenyu, Liu, Jirong, Wang, Chenxi, Wang, Junbo, Zhu, Haoyi, Lu, Cewu

“…A key challenge for robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent progress in one-shot imitation…”
Get full text

Distributed generation cluster partition method considering the flexible inertia supporting capability by Wang, Yinhua, Liu, Ziwen, Jiang, Jiamei, Zhu, Haoyi, Yang, Jinyuan, Li, Di

“…As the scale of distributed generations (DGs) connected to the power network increases, the system inertia significantly decreases, and bring threat to the…”
Get full text

UniPAD: A Universal Pre-Training Paradigm for Autonomous Driving by Yang, Honghui, Zhang, Sha, Huang, Di, Wu, Xiaoyang, Zhu, Haoyi, He, Tong, Tang, Shixiang, Zhao, Hengshuang, Qiu, Qibo, Lin, Binbin, He, Xiaofei, Ouyang, Wanli

“…In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pretraining…”
Get full text

RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot by Fang, Hao-Shu, Fang, Hongjie, Tang, Zhenyu, Liu, Jirong, Wang, Chenxi, Wang, Junbo, Zhu, Haoyi, Lu, Cewu

“…A key challenge in robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent research in one-shot imitation…”
Get full text

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving by Yang, Honghui, Zhang, Sha, Huang, Di, Wu, Xiaoyang, Zhu, Haoyi, He, Tong, Tang, Shixiang, Zhao, Hengshuang, Qiu, Qibo, Lin, Binbin, He, Xiaofei, Ouyang, Wanli

“…In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pre-training…”
Get full text

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm by Zhu, Haoyi, Yang, Honghui, Wu, Xiaoyang, Huang, Di, Zhang, Sha, He, Xianglong, Zhao, Hengshuang, Shen, Chunhua, Qiao, Yu, He, Tong, Ouyang, Wanli

“…In contrast to numerous NLP and 2D vision foundational models, learning a 3D foundational model poses considerably greater challenges. This is primarily due to…”
Get full text

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time by Fang, Hao-Shu, Li, Jiefeng, Tang, Hongyang, Xu, Chao, Zhu, Haoyi, Xiu, Yuliang, Li, Yong-Lu, Lu, Cewu

“…Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans…”
Get full text

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge by Fan, Linxi, Wang, Guanzhi, Jiang, Yunfan, Mandlekar, Ajay, Yang, Yuncong, Zhu, Haoyi, Tang, Andrew, Huang, De-An, Zhu, Yuke, Anandkumar, Anima

“…Autonomous agents have made great strides in specialist domains like Atari games and Go. However, they typically learn tabula rasa in isolated environments…”
Get full text

The research on fault restoration and refactoring for Active Distribution Network by Zhu, Haoyi, Yu, Yong, Qi, Weifu, Liu, Shusen, Weng, Yueying, Yuan, Ting, Li, Hongpeng

“…Active Distribution Network (ADN) recovery reconstruction is a complex combinatorial optimization problem, which is multi-objective, multi-period, nonlinear,…”
Get full text