Search

Your search keyword '"Lin, Zhengyu"' showing total 225 results
Start Over Author "Lin, Zhengyu" Publication Year Range Last 3 years
225 results on '"Lin, Zhengyu"'

1. SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters

Author

Jiang, Jianping, Xiao, Weiye, Lin, Zhengyu, Zhang, Huaizhong, Ren, Tianxiang, Gao, Yang, Lin, Zhiqian, Cai, Zhongang, Yang, Lei, and Liu, Ziwei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: (1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal input to drive the character for social interaction. (2) Interactive Multimodal Data: We present SynMSI, a synthetic multimodal social interaction dataset generated by an automatic pipeline using only existing motion datasets to address the issue of data scarcity. (3) Immersive VR Interface: We develop a VR interface that enables users to immersively interact with these characters driven by various architectures. Extensive quantitative experiments and user studies demonstrate that our framework leads to more precise and natural character responses (in both speech and motion) that align with user expectations with lower latency.

Published
2024

2. Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Author

Siyao, Li, Gu, Tianpei, Yang, Zhitao, Lin, Zhengyu, Liu, Ziwei, Ding, Henghui, Yang, Lei, and Loy, Chen Change

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Graphics, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

We introduce a novel task within the field of 3D dance generation, termed dance accompaniment, which necessitates the generation of responsive movements from a dance partner, the "follower", synchronized with the lead dancer's movements and the underlying musical rhythm. Unlike existing solo or group dance generation tasks, a duet dance scenario entails a heightened degree of interaction between the two participants, requiring delicate coordination in both pose and position. To support this task, we first build a large-scale and diverse duet interactive dance dataset, DD100, by recording about 117 minutes of professional dancers' performances. To address the challenges inherent in this task, we propose a GPT-based model, Duolando, which autoregressively predicts the subsequent tokenized motion conditioned on the coordinated information of the music, the leader's and the follower's movements. To further enhance the GPT's capabilities of generating stable results on unseen conditions (music and leader motions), we devise an off-policy reinforcement learning strategy that allows the model to explore viable trajectories from out-of-distribution samplings, guided by human-defined rewards. Based on the collected dataset and proposed method, we establish a benchmark with several carefully designed metrics., Comment: ICLR 2024

Published
2024

3. Digital Life Project: Autonomous 3D Characters with Social Intelligence

Author

Cai, Zhongang, Jiang, Jianping, Qing, Zhongfei, Guo, Xinying, Zhang, Mingyuan, Lin, Zhengyu, Mei, Haiyi, Wei, Chen, Wang, Ruisi, Yin, Wanqi, Fan, Xiangyu, Du, Han, Pan, Liang, Gao, Peng, Yang, Zhitao, Gao, Yang, Li, Jiaqi, Ren, Tianxiang, Wei, Yukun, Wang, Xiaogang, Loy, Chen Change, Yang, Lei, and Liu, Ziwei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Graphics, Computer Science - Human-Computer Interaction
Abstract

In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment. Our framework comprises two primary components: 1) SocioMind: a meticulously crafted digital brain that models personalities with systematic few-shot exemplars, incorporates a reflection process based on psychology principles, and emulates autonomy by initiating dialogue topics; 2) MoMat-MoGen: a text-driven motion synthesis paradigm for controlling the character's digital body. It integrates motion matching, a proven industry technique to ensure motion quality, with cutting-edge advancements in motion generation for diversity. Extensive experiments demonstrate that each module achieves state-of-the-art performance in its respective domain. Collectively, they enable virtual characters to initiate and sustain dialogues autonomously, while evolving their socio-psychological states. Concurrently, these characters can perform contextually relevant bodily movements. Additionally, a motion captioning module further allows the virtual character to recognize and appropriately respond to human players' actions. Homepage: https://digital-life-project.com/, Comment: Homepage: https://digital-life-project.com/

Published
2023

5. Expert consensus on the multidisciplinary diagnosis and treatment of multiple ground glass nodule-like lung cancer (2024 Edition)[sup.∆]

Author

Liu, Baodong, Ye, Xin, Fan, Weijun, Zhi, Xiuyi, Ma, Haitao, Wang, Jun, Wang, Peng, Wang, Zhongmin, Wang, Hongwu, Wang, Xiaoping, Niu, Lizhi, Fang, Yong, Gu, Shanzhi, Lu, Qiang, Tian, Hui, Zhu, Yulong, Qiao, Guibin, Zhong, Lou, Wei, Zhigang, Zhuang, Yiping, Liu, Hongxu, Liu, Lingxiao, Liu, Lei, Chi, Jiachang, Sun, Qing, Sun, Jiayuan, Sun, Xichao, Yang, Nuo, Mu, Juwei, Li, Yuliang, Li, Chengli, Li, Chunhai, Li, Xiaoguang, Li, Kang'an, Yang, Po, Yang, Xia, Yang, Fan, Yang, Wuwei, Xiao, Yueyong, Zhang, Chao, Zhang, Kaixian, Zhang, Lanjun, Zhang, Chunfang, Zhang, Linyou, Zhang, Yi, Chen, Shilin, Chen, Jun, Chen, Kezhong, Chen, Weisheng, Chen, Liang, Chen, Haiquan, Fan, Jiang, Lin, Zhengyu, Lin, Dianjie, Xian, Lei, Meng, Zhiqiang, Zhao, Xiaojing, Hu, Jian, Hu, Hongtao, Liu, Chen, Liu, Cheng, Zhong, Wenzhao, Yu, Xinshuang, Jiang, Gening, Jiao, Wenjie, Yao, Weirong, Yao, Feng, Gu, Chundong, Xu, Dong, Xu, Quan, Ling, Dongjin, Tang, Zhe, Huang, Yong, Huang, Guanghui, Peng, Zhongmin, Dong, Liang, Jiang, Lei, Jiang, Junhong, Cheng, Zhaoping, Cheng, Zhigang, Zeng, Qingshi, Jin, Yong, Lei, Guangyan, Liao, Yongde, Tan, Qunyou, Zhai, Bo, and Li, Hailiang

Subjects
Lung cancer -- Diagnosis -- Care and treatment, Health
Abstract

This expert consensus reviews current literature and provides clinical practice guidelines for the diagnosis and treatment of multiple ground glass nodule-like lung cancer. The main contents of this review include the following: ① follow-up strategies, ② differential diagnosis, ③ diagnosis and staging, ④ treatment methods, and ⑤ post-treatment follow-up. Keywords: Multiple ground glass nodule-like lung cancer, multiple primary lung cancer, pulmonary ground glass nodule, Author(s): Baodong Liu (corresponding author) [1]; Xin Ye (corresponding author) [2]; Weijun Fan (corresponding author) [3]; Xiuyi Zhi (corresponding author) [1]; Haitao Ma [4]; Jun Wang [2]; Peng Wang [5]; [...]

Published
2024
Full Text
View/download PDF

6. Guidelines for permanent iodine-125 seed interstitial brachytherapy for pancreatic cancer (2023 edition): The Chinese expert consensus workshop report

Author

Liu, Bin, Huang, Wei, Zhang, Fujun, Wang, Junjie, Guo, Jinhe, Huang, Xuequan, Lei, Guangyan, Wang, Juan, Ye, Xin, Wang, Ruoyu, Gai, Baodong, Hu, Xiaokun, Li, Maoquan, Li, Chengli, Xiao, Yueyong, Lin, Zhengyu, Niu, Lizhi, Zhu, Guangyu, Gao, Fei, Niu, Hongxin, Zhang, Hongtao, Wu, Qing, Yang, Jijin, Zhao, Hong, Zhang, Kaixian, Chen, Zhijin, Chen, Tingsong, Zhang, Haoren, Wang, Zhongmin, and Li, Yuliang

Subjects
Pancreatic cancer -- Care and treatment, Radioisotope brachytherapy -- Methods, Health
Abstract

The incidence of pancreatic cancer is increasing worldwide. Approximately, 60 of patients with pancreatic cancer have distant metastases at the time of diagnosis, of which only 10 can be removed using standard resection. Further, patients derive limited benefits from chemotherapy or radiotherapy. As such, alternative methods to achieve local control have emerged, including permanent iodine-125 seed interstitial brachytherapy. In 2023, the Chinese College of Interventionalists, affiliated with the Chinese Medical Doctor Association, organized a group of multi-disciplinary experts to compose guidelines for this treatment modality. The aim of this conference was to standardize the procedure for permanent iodine-125 seed interstitial brachytherapy, including indications, contraindications, pre-procedural preparation, procedural operations, complications, efficacy evaluation, and follow-up. Keywords: Brachytherapy, guideline, iodine-125, pancreatic cancer, Author(s): Bin Liu [1,2]; Wei Huang [3]; Fujun Zhang [4]; Junjie Wang [5]; Jinhe Guo [6]; Xuequan Huang [7]; Guangyan Lei [8]; Juan Wang [9]; Xin Ye [10]; Ruoyu Wang [...]

Published
2024
Full Text
View/download PDF

7. Investigating the accuracy of machine vision and augmented reality in percutaneous computed tomography-guided interventions: A phantom study

Author

Huang, Bingyu, Wei, Yizhi, Zhang, Bing, Chen, Jin, Guo, Rui, Zhou, Steven Zhiying, Lin, Zhigang, and Lin, Zhengyu

Subjects
Augmented Reality -- Methods -- Evaluation, Machine vision -- Methods -- Evaluation, CT imaging -- Methods -- Evaluation, Health
Abstract

Objectives: This study aimed to evaluate the accuracy of percutaneous computed tomography (CT)-guided puncture based on machine vision and augmented reality in a phantom. Materials and Methods: The surgical space coordinate system was established, and accurate registration was ensured using the hierarchical optimization framework. Machine vision tracking and augmented reality display technologies were used for puncture navigation. CT was performed on a phantom, and puncture paths with three different lengths were planned from the surface of the phantom to the metal ball. Puncture accuracy was evaluated by measuring the target positioning error (TPE), lateral error (LE), angular error (AE), and first success rate (FSR) based on the obtained CT images. Results: A highly qualified attending interventional physician performed a total of 30 punctures using puncture navigation. For the short distance (4.5-5.5 cm), the TPE, LE, AE, and FSR were 1.90 ± 0.62 mm, 1.23 ± 0.70 mm, 1.39 ± 0.86°, and 60, respectively. For the medium distance (9.5-10.5 cm), the TPE, LE, AE, and FSR were 2.35 ± 0.95 mm, 2.00 ± 1.07 mm, 1.20 ± 0.62°, and 40, respectively. For the long distance (14.5-15.5 cm), the TPE, LE, AE, and FSR were 2.81 ± 1.17 mm, 2.33 ± 1.34 mm, 0.99 ± 0.55°, and 30, respectively. Conclusion: The augmented reality and machine vision-based CT-guided puncture navigation system allows for precise punctures in a phantom. Further studies are needed to explore its clinical applicability. Keywords: Augmented reality, computed tomography, interventional radiology, machine vision, percutaneous puncture, Author(s): Bingyu Huang [1,2]; Yizhi Wei [3]; Bing Zhang [1,2]; Jin Chen [1,2]; Rui Guo [1,2]; Steven Zhiying Zhou (corresponding author) [3]; Zhigang Lin (corresponding author) [4,5]; Zhengyu Lin (corresponding [...]

Published
2024
Full Text
View/download PDF

8. DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering

Author

Cheng, Wei, Chen, Ruixiang, Yin, Wanqi, Fan, Siming, Chen, Keyu, He, Honglin, Luo, Huiwen, Cai, Zhongang, Wang, Jingbo, Gao, Yang, Yu, Zhengming, Lin, Zhengyu, Ren, Daxuan, Yang, Lei, Liu, Ziwei, Loy, Chen Change, Qian, Chen, Wu, Wayne, Lin, Dahua, Dai, Bo, and Lin, Kwan-Yee

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverished in terms of diversity, which are crucial for rendering effect. Researchers are usually constrained to explore and evaluate a small set of rendering problems on current datasets, while real-world applications require methods to be robust across different scenarios. In this work, we present DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering. DNA-Rendering presents several alluring attributes. First, our dataset contains over 1500 human subjects, 5000 motion sequences, and 67.5M frames' data volume. Second, we provide rich assets for each subject -- 2D/3D human body keypoints, foreground masks, SMPLX models, cloth/accessory materials, multi-view images, and videos. These assets boost the current method's accuracy on downstream rendering tasks. Third, we construct a professional multi-view system to capture data, which contains 60 synchronous cameras with max 4096 x 3000 resolution, 15 fps speed, and stern camera calibration steps, ensuring high-quality resources for task training and evaluation. Along with the dataset, we provide a large-scale and quantitative benchmark in full-scale, with multiple tasks to evaluate the existing progress of novel view synthesis, novel pose animation synthesis, and novel identity rendering methods. In this manuscript, we describe our DNA-Rendering effort as a revealing of new observations, challenges, and future directions to human-centric rendering. The dataset, code, and benchmarks will be publicly available at https://dna-rendering.github.io/, Comment: This paper is accepted by ICCV2023. Project page: https://dna-rendering.github.io/

Published
2023

10. Tumor burden with AFP improves survival prediction for TACE-treated patients with HCC: An international observational study☆

Author

Xia, Dongdong, Bai, Wei, Wang, Qiuhe, Chung, Jin Wook, Adhoute, Xavier, Kloeckner, Roman, Zhang, Hui, Zeng, Yong, Sripongpun, Pimsiri, Nie, Chunhui, Kim, Seung Up, Huang, Ming, Hu, Wenhao, Ding, Xiangchun, Yin, Guowen, Li, Hailiang, Zhao, Hui, Bronowicki, Jean-Pierre, Li, Jing, Li, Jiaping, Zhu, Xiaoli, Wu, Jianbing, Zhang, Chunqing, Gong, Weidong, Li, Zixiang, Lin, Zhengyu, Xu, Tao, Yin, Tao, Anty, Rodolphe, Song, Jinlong, Shi, Haibin, Shao, Guoliang, Ren, Weixin, Zhang, Yongjin, Yang, Shufa, Zheng, Yanbo, Xu, Jian, Wang, Wenhui, Zhu, Xu, Fu, Ying, Liu, Chang, Kaewdech, Apichat, Ding, Rong, Zheng, Jie, Liu, Shuaiwei, Yu, Hui, Zheng, Lin, You, Nan, Fan, Wenzhe, Zhang, Shuai, Feng, Long, Wang, Guangchuan, Zhang, Peng, Li, Xueda, Chen, Jian, Zhang, Feng, Shao, Wenbo, Zhou, Weizhong, Zeng, Hui, Cao, Gengfei, Huang, Wukui, Jiang, Wenjin, Zhang, Wen, Li, Lei, Feng, Aiwei, Wang, Enxin, Wang, Zhexuan, Han, Dandan, Lv, Yong, Sun, Jun, Ren, Bincheng, Xia, Linying, Li, Xiaomei, Yuan, Jie, Wang, Zhengyu, Luo, Bohan, Li, Kai, Guo, Wengang, Yin, Zhanxin, Zhao, Yan, Xia, Jielai, Fan, Daiming, Wu, Kaichun, Bettinger, Dominik, Vogel, Arndt, and Han, Guohong

Published
2025
Full Text
View/download PDF

12. HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling

Author

Cai, Zhongang, Ren, Daxuan, Zeng, Ailing, Lin, Zhengyu, Yu, Tao, Wang, Wenjia, Fan, Xiangyu, Gao, Yang, Yu, Yifan, Pan, Liang, Hong, Fangzhou, Zhang, Mingyuan, Loy, Chen Change, Yang, Lei, and Liu, Ziwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets. In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. HuMMan has several appealing properties: 1) multi-modal data and annotations including color images, point clouds, keypoints, SMPL parameters, and textured meshes; 2) popular mobile device is included in the sensor suite; 3) a set of 500 actions, designed to cover fundamental movements; 4) multiple tasks such as action recognition, pose estimation, parametric human recovery, and textured mesh reconstruction are supported and evaluated. Extensive experiments on HuMMan voice the need for further study on challenges such as fine-grained action recognition, dynamic human mesh reconstruction, point cloud-based parametric human recovery, and cross-device domain gaps., Comment: Homepage: https://caizhongang.github.io/projects/HuMMan/

Published
2022

18. Microwave ablation for the treatment of peripheral ground-glass nodule-like lung cancer: Long-term results from a multi-center study

Author

Yang, Xia, Jin, Yong, Lin, Zhengyu, Li, Xiaoguang, Huang, Guanghui, Ni, Yang, Li, Wenhong, Han, Xiaoying, Meng, Min, Chen, Jin, Lin, Qingfeng, Bie, Zhixin, Wang, Chuntang, Li, Yuliang, and Ye, Xin

Subjects
Ablation (Surgery) -- Methods -- Patient outcomes, Microwaves -- Usage, Lung cancer -- Care and treatment
Abstract

ABSTRACT Introduction: Microwave ablation (MWA) is an effective and safe approach for the treatment of ground-glass nodule (GGN)-like lung cancer, but long-term follow-up is warranted. Therefore, this multi-center retrospective study aimed to evaluate the results of MWA for the treatment of peripheral GGN-like lung cancer with a long-term follow-up. Materials and Methods: From June 2013 to January 2018, a total of 87 patients (47 males and 40 females, mean age 64.6 ± 10.2 years) with 87 peripheral lung cancer lesions showing GGN (mean long axis diameter, 17 ± 5 mm) underwent computed tomography (CT)-guided percutaneous MWA. All GGN-like lung cancers were histologically verified. The primary endpoints were local progression-free survival (LPFS) and overall survival (OS). The secondary endpoints were cancer-specific survival (CSS) and complications. Results: During a median follow-up of 65 months, both the 3-year and 5-year LPFS rates were 96.6 and 96.6. The OS rate was 94.3 at 3 years and 84.9 at 5 years, whereas the 3-year and 5-year CSS rates were 100 and 100, respectively. No periprocedural deaths were observed. Complications were observed in 49 patients (51.6). Grade 3 or higher complications included pneumothorax, pleural effusion, hemorrhage, and pulmonary infection, which were identified in ten (10.5), two (2.1), two (2.1), and one (1.1) patient, respectively. Conclusions: CT-guided percutaneous MWA is an effective, safe, and potentially curative treatment regimen for GGN-like lung cancer. Keywords: Complications, Ground-glass nodules, Lung cancer, Microwave ablation, Survival, Author(s): Xia Yang [1]; Yong Jin [2]; Zhengyu Lin [3]; Xiaoguang Li [4]; Guanghui Huang [1]; Yang Ni [1]; Wenhong Li [1]; Xiaoying Han [1]; Min Meng [1]; Jin Chen [...]

Published
2023
Full Text
View/download PDF

19. Application of respiratory sensing technique in CT-guided radiofrequency ablation of liver malignancies

Author

You, Xiang, Huang, Bingyu, Chen, Jin, and Lin, Zhengyu

Subjects
Radiofrequency ablation -- Methods, Sensors -- Usage, Liver cancer -- Care and treatment, CT imaging -- Methods
Abstract

ABSTRACT Objective: This study aimed to examine the effectiveness and safety of respiratory sensing methods in nonvascular interventional therapy of liver tumors. Materials and Methods: In this study, 64 patients with primary liver cancer or liver metastasis were retrospectively analyzed. According to two widely used clinical techniques to limit respiratory movement--breath holding and respiratory sensing technology--they were randomly allocated into two groups: respiratory gated and respiratory training. We aimed to compare the application and effect of these two techniques in the nonvascular interventional therapy of liver tumors. Results: The puncture times of the respiratory-gated and respiratory training groups were 5.34 ± 2.47 and 8.41 ± 3.63 min, respectively. Puncture errors were 10.00 ± 2.65 and 12.81 ± 8.57 mm, respectively. Puncture adjustment times were 3.06 ± 1.26 and 4.87 ± 1.69 times, respectively, and the differences were statistically significant (P < 0.01). Conclusions: Respiratory sensing technology has been effectively used to assist in puncturing liver malignant tumors using a radiofrequency (RF) ablation (RFA) system that is guided by computed tomography (CT) scans. It is superior to the classical breath-holding step puncture technique in terms of puncture time, puncture error, and puncture needle adjustment times. Keywords: Liver tumors, nonvascular interventional therapy, radiofrequency ablation, respiratory sensing technique, Author(s): Xiang You [1,2]; Bingyu Huang [1,2]; Jin Chen [1,2]; Zhengyu Lin (corresponding author) [1,2] INTRODUCTION Radiofrequency (RF) ablation (RFA) is a treatment modality for liver malignancies because it is [...]

Published
2023
Full Text
View/download PDF

21. Crude extract of J1 fermentation promotes apoptosis of cervical cancer cells

Author

Yu Xia, He Qing, Zhao Wei, Zhang Shuo, Du Haixia, Lin Zhengyu, Han Xiaohui, and Peng Jingjun

Subjects
j1, cervical carcinoma, ginkgo biloba, apoptosis, Organic chemistry, QD241-441
Abstract

Cervical cancer is a typical cancer characterized by abnormal cell growth in the cervical area. Ginkgo biloba L. is a deciduous tree of the genus Ginkgo, possessing anti-cancer effects. The aim of this study was to explore the effect of strain J1 from Ginkgo biloba L. on apoptosis of cervical cancer cells. Bacteriostatic activity test, MTT assay and Flow cytometry were used in this study. Crude extract of J1 fermentation reduced cell growth in cervical cancer. The crude extract of the fermentation broth of strain J1 had a good inhibitory effect on Staphylococcus aureus. The crude extract of the J1 fermentation had no toxic effect on normal WISH cells in the range of anti-cervical cancer concentration. Crude extract of J1 fermentation induced apoptosis and regulated cell cycle in cervical cancer. The active compounds were separated and identified by preparative chromatography, and more than ten compounds were obtained. Our study suggests that the crude extract of J1 fermentation from Endophytic fungi of Ginkgo biloba reduced cell growth, and promoted apoptosis of cervical cancer, and is a potential therapeutic strategy for the treatment of cervical carcinoma.

Published
2023
Full Text
View/download PDF

23. DC networks

Author

Lin, Zhengyu, primary, Li, Fulong, additional, and Wang, Fei, additional

Published
2023
Full Text
View/download PDF

27. THU-475 Tumor burden incorporating AFP improves survival prediction for patients with HCC undergoing TACE: an international multicentre observational study

Author

Xia, Dongdong, primary, Bai, Wei, additional, Wang, Qiuhe, additional, Chung, Jin Wook, additional, Adhoute, Xavier, additional, Kloeckner, Roman, additional, Zhang, Hui, additional, Zeng, Yong, additional, Sripongpun, Pimsiri, additional, Nie, Chunhui, additional, Kim, Seung Up, additional, Huang, Ming, additional, Hu, Wenhao, additional, Ding, Xiangchun, additional, Yin, Guowen, additional, Li, Hailiang, additional, Zhao, Hui, additional, Li, Jing, additional, Li, Jiaping, additional, Zhu, Xiaoli, additional, Wu, Jianbing, additional, Zhang, Chunqing, additional, Gong, Weidong, additional, Li, Zixiang, additional, Lin, Zhengyu, additional, Xu, Tao, additional, Yin, Tao, additional, Song, Jinlong, additional, Shi, Haibin, additional, Shao, Guoliang, additional, Ren, Weixin, additional, Zhang, Yongjin, additional, Yang, Shufa, additional, Zheng, Yanbo, additional, Xu, Jian, additional, Wang, Wenhui, additional, Zhu, Xu, additional, Bettinger, Dominik, additional, Vogel, Arndt, additional, and Han, Guohong, additional

Published
2024
Full Text
View/download PDF

30. Playing for 3D Human Recovery

Author

Cai, Zhongang, Zhang, Mingyuan, Ren, Jiawei, Wei, Chen, Ren, Daxuan, Lin, Zhengyu, Zhao, Haiyu, Yang, Lei, Loy, Chen Change, and Liu, Ziwei

Abstract

Image- and video-based 3D human recovery (i.e., pose and shape estimation) have achieved substantial progress. However, due to the prohibitive cost of motion capture, existing datasets are often limited in scale and diversity. In this work, we obtain massive human sequences by playing the video game with automatically annotated 3D ground truths. Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios. More importantly, we study the use of game-playing data and obtain five major insights. First, game-playing data is surprisingly effective. A simple frame-based baseline trained on GTA-Human outperforms more sophisticated methods by a large margin. For video-based methods, GTA-Human is even on par with the in-domain training set. Second, we discover that synthetic data provides critical complements to the real data that is typically collected indoor. We highlight that our investigation into domain gap provides explanations for our data mixture strategies that are simple yet useful, which offers new insights to the research community. Third, the scale of the dataset matters. The performance boost is closely related to the additional data available. A systematic study on multiple key factors (such as camera angle and body pose) reveals that the model performance is sensitive to data density. Fourth, the effectiveness of GTA-Human is also attributed to the rich collection of strong supervision labels (SMPL parameters), which are otherwise expensive to acquire in real datasets. Fifth, the benefits of synthetic data extend to larger models such as deeper convolutional neural networks (CNNs) and Transformers, for which a significant impact is also observed. We hope our work could pave the way for scaling up 3D human recovery to the real world.

Published
2024
Full Text
View/download PDF

31. HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

Author

Cai, Zhongang, primary, Ren, Daxuan, additional, Zeng, Ailing, additional, Lin, Zhengyu, additional, Yu, Tao, additional, Wang, Wenjia, additional, Fan, Xiangyu, additional, Gao, Yang, additional, Yu, Yifan, additional, Pan, Liang, additional, Hong, Fangzhou, additional, Zhang, Mingyuan, additional, Loy, Chen Change, additional, Yang, Lei, additional, and Liu, Ziwei, additional

Published
2022
Full Text
View/download PDF

32. Remote levodopa challenge test in Parkinson's disease: Feasibility, reliability, validity and economic value.

Author

Zeng, Zhitong, Lin, Zhengyu, Chen, Zhonglue, Wan, Xiaonan, Zhou, Haiyan, Zhang, Chencheng, Sun, Bomin, Ren, Kang, and Li, Dianyou

Subjects
*DEEP brain stimulation, *PARKINSON'S disease, *INTRACLASS correlation, *PEARSON correlation (Statistics), *MOVEMENT disorders
Abstract

Background and purpose: The aim was to demonstrate the feasibility, reliability and validity of an in‐home remote levodopa challenge test (LCT), as delivered through an online platform, for patients with Parkinson's disease (PwPD). Methods: Patients with Parkinson's disease eligible for deep brain stimulation surgery screening were enrolled. Participants sequentially received an in‐home remote LCT and an in‐hospital standard LCT (separated by 2.71 weeks). A modified Movement Disorder Society Unified Parkinson's Disease Rating Scale Part III omitting rigidity and postural stability items was used in the remote LCT. The reliability of the remote LCT was evaluated using the intraclass correlation coefficient and the concurrent validity was evaluated using the Pearson's correlation coefficient r between the levodopa responsiveness of the remote and standard LCT. Results: Out of 106 PwPD screened, 80 (75.5%) completed both the remote and standard LCT. There was a good reliability (intraclass correlation coefficient 0.81, 95% confidence interval 0.69–0.88) and a strong correlation (r = 0.84, 95% confidence interval 0.77–0.90) between the levodopa responsiveness of the remote and standard LCT. The mean cost for PwPD was estimated to be reduced by 91% by using the remote LCT. Conclusion: The remote LCT is feasible, reliable and valid and may reduce healthcare‐related costs for PwPD and their caregivers. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

37. Guest Editorial: Energy storage for green transition of electrical grids

Author

Bayati, Navid, Ebel, Thomas, Savaghebi, Mehdi, Lin, Zhengyu, Zhao, Haoran, Marzband, Mousa, Dehghanian, Payman, Bayati, Navid, Ebel, Thomas, Savaghebi, Mehdi, Lin, Zhengyu, Zhao, Haoran, Marzband, Mousa, and Dehghanian, Payman

Abstract

Energy storage systems (ESSs) are needed in the smart grids both at the generation, transmission, and distribution levels, and different types of ESSs have widely different characteristics and are suitable for different tasks and situations. In recent years, the smart grid concept has been dramatically developed in different applications, such as islands, shipboards, aircraft, microgrids and grid integration of renewables. With the wide application of ESS in smart grids, significant technical challenges remain along with the enhancement of smart grid operations and services. These challenges can be categorised as control of ESS, optimal operation, and energy management systems, optimal design of hybrid ESS, protection of ESS, and power electronics for ESS connections. This necessitates suitable design and control of the interfaces between ESSs in smart grids, as well as consideration of different applications of smart grid systems. This special issue of IET smart grid is focused on research ideas, articles, and experimental studies related to ‘Energy Storage for Green Transition of Electrical Grids’ from contributors in universities, industries, and research laboratories to develop and propose novel solutions on applications of ESS in smart grids.

Published
2024

39. A Hybrid Beat Frequency Oscillation Suppression Strategy for DC Microgrids †.

Author

Xu, Haoge and Lin, Zhengyu

Subjects
*FREQUENCIES of oscillating systems, *MICROGRIDS, *RELIABILITY in engineering, *NOISE
Abstract

In DC microgrids, parallel-connected power converters are commonly used to integrate distributed energy sources. However, interactions of power switching noises among these power converters could lead to large low-frequency beat frequency oscillations under certain conditions, which degrades system performance and reliability, especially for DC microgrids with parallel connected Boost converters. In this research, the output impedance model for multiple parallel-connected Boost converters is developed for beat frequency oscillation analysis, and then a hybrid method is proposed to address this issue. The proposed method includes separated switching frequency channels and additional line inductors. Experimental results validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. Phrenic nerve injury after the percutaneous microwave ablation of lung tumors: A single-center analysis

Author

Zhong, Junsheng, Chen, Jin, Lin, Ruixiang, Yan, Yuan, Lin, Qingfeng, Chen, Jian, and Lin, Zhengyu

Subjects
Lung tumors -- Diagnosis -- Care and treatment, Ablation (Surgery) -- Patient outcomes, Phrenic nerve -- Injuries, Health
Abstract

Byline: Junsheng. Zhong, Jin. Chen, Ruixiang. Lin, Yuan. Yan, Qingfeng. Lin, Jian. Chen, Zhengyu. Lin Objective: This study aimed to analyze the cases of phrenic nerve injury caused by the [...]

Published
2022

43. Clinical practice guidelines on image-guided thermal ablation of primary and metastatic lung tumors (2022 edition)

Author

Ye, Xin, Fan, Weijun, Wang, Zhongmin, Wang, Junjie, Wang, Hui, Niu, Lizhi, Fang, Yong, Gu, Shanzhi, Liu, Lingxiao, Liu, Baodong, Zhuang, Yiping, Wei, Zhigang, Li, Xiao, Li, Xiaoguang, Li, Yuliang, Li, Chunhai, Yang, Xia, Yang, Wuwei, Yang, Po, Lin, Zhengyu, Meng, Zhiqiang, Hu, Kaiwen, Liu, Chen, Huang, Yong, Huang, Guanghui, Huang, Kaiwen, Peng, Zhongmin, Han, Yue, Jin, Yong, Lei, Guangyan, Zhai, Bo, Li, Hailiang, Pan, Jie, Filippiadis, Dimitris, Kelekis, Alexis, Pua, Uei, Futacsi, Balazs, Yumchinserchin, N., Iezzi, Roberto, Tang, Alex, and Roy, Shuvro

Subjects
Metastasis -- Care and treatment, Practice guidelines (Medicine), Ablation (Surgery) -- Methods, Computer-assisted surgery -- Methods, Lung cancer -- Care and treatment, Health
Abstract

Byline: Xin. Ye, Weijun. Fan, Zhongmin. Wang, Junjie. Wang, Hui. Wang, Lizhi. Niu, Yong. Fang, Shanzhi. Gu, Lingxiao. Liu, Baodong. Liu, Yiping. Zhuang, Zhigang. Wei, Xiao. Li, Xiaoguang. Li, Yuliang. [...]

Published
2022

44. Experimental study on the accuracy of non-invasive temperature measurement by magnetic resonance in microwave ablation

Author

Guo, Rui, Wang, Xianjian, Liu, Jie, Chen, Jin, Chen, Jian, Lin, Qingfeng, Yan, Yuan, Liang, Ping, and Lin, Zhengyu

Subjects
Tumors -- Care and treatment, Proton magnetic resonance -- Usage, Ablation (Surgery) -- Methods, Temperature measurements -- Methods, Patient monitoring -- Methods, Health
Abstract

Byline: Rui. Guo, Xianjian. Wang, Jie. Liu, Jin. Chen, Jian. Chen, Qingfeng. Lin, Yuan. Yan, Ping. Liang, Zhengyu. Lin Aims: This study aimed to explore the accuracy of non-invasive temperature [...]

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results