Search

Your search keyword '"Liu, Ruixin"' showing total 529 results
Start Over Author "Liu, Ruixin"
529 results on '"Liu, Ruixin"'

1. Flexible 3D Lane Detection by Hierarchical Shape MatchingFlexible 3D Lane Detection by Hierarchical Shape Matching

Author

Guan, Zhihao, Liu, Ruixin, Yuan, Zejian, Liu, Ao, Tang, Kun, Zhou, Tong, Li, Erlong, Zheng, Chao, and Mei, Shuqi

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

As one of the basic while vital technologies for HD map construction, 3D lane detection is still an open problem due to varying visual conditions, complex typologies, and strict demands for precision. In this paper, an end-to-end flexible and hierarchical lane detector is proposed to precisely predict 3D lane lines from point clouds. Specifically, we design a hierarchical network predicting flexible representations of lane shapes at different levels, simultaneously collecting global instance semantics and avoiding local errors. In the global scope, we propose to regress parametric curves w.r.t adaptive axes that help to make more robust predictions towards complex scenes, while in the local vision the structure of lane segment is detected in each of the dynamic anchor cells sampled along the global predicted curves. Moreover, corresponding global and local shape matching losses and anchor cell generation strategies are designed. Experiments on two datasets show that we overwhelm current top methods under high precision standards, and full ablation studies also verify each part of our method. Our codes will be released at https://github.com/Doo-do/FHLD.

Published
2024
Full Text
View/download PDF

2. A brain-to-gut signal controls intestinal fat absorption

Author

Lyu, Qianqian, Xue, Wenzhi, Liu, Ruixin, Ma, Qinyun, Kasaragod, Vikram Babu, Sun, Shan, Li, Qian, Chen, Yanru, Yuan, Mingyang, Yang, Yuying, Zhang, Bing, Nie, Aifang, Jia, Sheng, Shen, Chongrong, Gao, Po, Rong, Weifang, Yu, Chenxi, Bi, Yufang, Zhang, Chunlei, Nan, Fajun, Ning, Guang, Rao, Zihe, Yang, Xiuna, Wang, Jiqiu, and Wang, Weiqing

Published
2024
Full Text
View/download PDF

6. Trusted Personalized Federated Learning Based on Differential Privacy

Author

Liu, Ruixin, Qin, Zhenquan, Cheng, Xi, Zhang, Rui, Zheng, Jianbo, Akan, Ozgur, Editorial Board Member, Bellavista, Paolo, Editorial Board Member, Cao, Jiannong, Editorial Board Member, Coulson, Geoffrey, Editorial Board Member, Dressler, Falko, Editorial Board Member, Ferrari, Domenico, Editorial Board Member, Gerla, Mario, Editorial Board Member, Kobayashi, Hisashi, Editorial Board Member, Palazzo, Sergio, Editorial Board Member, Sahni, Sartaj, Editorial Board Member, Shen, Xuemin, Editorial Board Member, Stan, Mircea, Editorial Board Member, Jia, Xiaohua, Editorial Board Member, Zomaya, Albert Y., Editorial Board Member, Leung, Victor C.M., editor, Li, Hezhang, editor, Hu, Xiping, editor, and Ning, Zhaolong, editor

Published
2024
Full Text
View/download PDF

7. Task Prediction Based Computation Offloading over Multi-UAV MEC Network

Author

Cheng, Xi, Qin, Zhenquan, Liu, Ruixin, Lu, Jiong, Zheng, Jianbo, Akan, Ozgur, Editorial Board Member, Bellavista, Paolo, Editorial Board Member, Cao, Jiannong, Editorial Board Member, Coulson, Geoffrey, Editorial Board Member, Dressler, Falko, Editorial Board Member, Ferrari, Domenico, Editorial Board Member, Gerla, Mario, Editorial Board Member, Kobayashi, Hisashi, Editorial Board Member, Palazzo, Sergio, Editorial Board Member, Sahni, Sartaj, Editorial Board Member, Shen, Xuemin, Editorial Board Member, Stan, Mircea, Editorial Board Member, Jia, Xiaohua, Editorial Board Member, Zomaya, Albert Y., Editorial Board Member, Leung, Victor C.M., editor, Li, Hezhang, editor, Hu, Xiping, editor, and Ning, Zhaolong, editor

Published
2024
Full Text
View/download PDF

16. Interactive Image Inpainting Using Semantic Guidance

Author

Yu, Wangbo, Du, Jinhao, Liu, Ruixin, Li, Yixuan, and zhu, Yuesheng

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

Image inpainting approaches have achieved significant progress with the help of deep neural networks. However, existing approaches mainly focus on leveraging the priori distribution learned by neural networks to produce a single inpainting result or further yielding multiple solutions, where the controllability is not well studied. This paper develops a novel image inpainting approach that enables users to customize the inpainting result by their own preference or memory. Specifically, our approach is composed of two stages that utilize the prior of neural network and user's guidance to jointly inpaint corrupted images. In the first stage, an autoencoder based on a novel external spatial attention mechanism is deployed to produce reconstructed features of the corrupted image and a coarse inpainting result that provides semantic mask as the medium for user interaction. In the second stage, a semantic decoder that takes the reconstructed features as prior is adopted to synthesize a fine inpainting result guided by user's customized semantic mask, so that the final inpainting result will share the same content with user's guidance while the textures and colors reconstructed in the first stage are preserved. Extensive experiments demonstrate the superiority of our approach in terms of inpainting quality and controllability.

Published
2022

18. Structure-aware Image Inpainting with Two Parallel Streams

Author

Huang, Zhilin, Qin, Chujun, Liu, Ruixin, Weng, Zhenyu, and Zhu, Yuesheng

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

Recent works in image inpainting have shown that structural information plays an important role in recovering visually pleasing results. In this paper, we propose an end-to-end architecture composed of two parallel UNet-based streams: a main stream (MS) and a structure stream (SS). With the assistance of SS, MS can produce plausible results with reasonable structures and realistic details. Specifically, MS reconstructs detailed images by inferring missing structures and textures simultaneously, and SS restores only missing structures by processing the hierarchical information from the encoder of MS. By interacting with SS in the training process, MS can be implicitly encouraged to exploit structural cues. In order to help SS focus on structures and prevent textures in MS from being affected, a gated unit is proposed to depress structure-irrelevant activations in the information flow between MS and SS. Furthermore, the multi-scale structure feature maps in SS are utilized to explicitly guide the structure-reasonable image reconstruction in the decoder of MS through the fusion block. Extensive experiments on CelebA, Paris StreetView and Places2 datasets demonstrate that our proposed method outperforms state-of-the-art methods., Comment: 9 pages, 8 figures, rejected by IJCAI 2021

Published
2021

21. Obesity-enriched gut microbe degrades myo-inositol and promotes lipid absorption

Author

Wu, Chao, Yang, Fangming, Zhong, Huanzi, Hong, Jie, Lin, Huibin, Zong, Mingxi, Ren, Huahui, Zhao, Shaoqian, Chen, Yufei, Shi, Zhun, Wang, Xingyu, Shen, Juan, Wang, Qiaoling, Ni, Mengshan, Chen, Banru, Cai, Zhongle, Zhang, Minchun, Cao, Zhiwen, Wu, Kui, Gao, Aibo, Li, Junhua, Liu, Cong, Xiao, Minfeng, Li, Yan, Shi, Juan, Zhang, Yifei, Xu, Xun, Gu, Weiqiong, Bi, Yufang, Ning, Guang, Wang, Weiqing, Wang, Jiqiu, and Liu, Ruixin

Published
2024
Full Text
View/download PDF

22. Association of circulating long-chain free fatty acids and incident diabetes risk among normoglycemic Chinese adults: a prospective nested case–control study

Author

Wang, Shuangyuan, Hu, Chunyan, Lin, Hong, Jia, Xiaojing, Hu, Ruying, Zheng, Ruizhi, Li, Mian, Xu, Yu, Xu, Min, Zheng, Jie, Zhao, Xinjie, Li, Yanli, Chen, Lulu, Zeng, Tianshu, Ye, Zhen, Shi, Lixin, Su, Qing, Chen, Yuhong, Yu, Xuefeng, Yan, Li, Wang, Tiange, Zhao, Zhiyun, Qin, Guijun, Wan, Qin, Chen, Gang, Dai, Meng, Zhang, Di, Qiu, Bihan, Zhu, Xiaoyan, Liu, Ruixin, Wang, Xiao, Tang, Xulei, Gao, Zhengnan, Shen, Feixia, Gu, Xuejiang, Luo, Zuojie, Qin, Yingfen, Chen, Li, Hou, Xinguo, Huo, Yanan, Li, Qiang, Wang, Guixia, Zhang, Yinfei, Liu, Chao, Wang, Youmin, Wu, Shengli, Yang, Tao, Deng, Huacong, Zhao, Jiajun, Mu, Yiming, Xu, Guowang, Lai, Shenghan, Li, Donghui, Ning, Guang, Wang, Weiqing, Bi, Yufang, and Lu, Jieli

Published
2024
Full Text
View/download PDF

37. Fast Search on Binary Codes by Weighted Hamming Distance

Author

Weng, Zhenyu, Zhu, Yuesheng, and Liu, Ruixin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Weighted Hamming distance, as a similarity measure between binary codes and binary queries, provides superior accuracy in search tasks than Hamming distance. However, how to efficiently and accurately find $K$ binary codes that have the smallest weighted Hamming distance to the query remains an open issue. In this paper, a fast search algorithm is proposed to perform the non-exhaustive search for $K$ nearest binary codes by weighted Hamming distance. By using binary codes as direct bucket indices in a hash table, the search algorithm generates a sequence to probe the buckets based on the independence characteristic of the weights for each bit. Furthermore, a fast search framework based on the proposed search algorithm is designed to solve the problem of long binary codes. Specifically, long binary codes are split into substrings and multiple hash tables are built on them. Then, the search algorithm probes the buckets to obtain candidates according to the generated substring indices, and a merging algorithm is proposed to find the nearest binary codes by merging the candidates. Theoretical analysis and experimental results demonstrate that the search algorithm improves the search accuracy compared to other non-exhaustive algorithms and provides orders-of-magnitude faster search than the linear scan baseline., Comment: 12 pages

Published
2020

38. Bidirectional Loss Function for Label Enhancement and Distribution Learning

Author

Liu, Xinyuan, Zhu, Jihua, Zheng, Qinghai, Li, Zhongyu, Liu, Ruixin, and Wang, Jun

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Label distribution learning (LDL) is an interpretable and general learning paradigm that has been applied in many real-world applications. In contrast to the simple logical vector in single-label learning (SLL) and multi-label learning (MLL), LDL assigns labels with a description degree to each instance. In practice, two challenges exist in LDL, namely, how to address the dimensional gap problem during the learning process of LDL and how to exactly recover label distributions from existing logical labels, i.e., Label Enhancement (LE). For most existing LDL and LE algorithms, the fact that the dimension of the input matrix is much higher than that of the output one is alway ignored and it typically leads to the dimensional reduction owing to the unidirectional projection. The valuable information hidden in the feature space is lost during the mapping process. To this end, this study considers bidirectional projections function which can be applied in LE and LDL problems simultaneously. More specifically, this novel loss function not only considers the mapping errors generated from the projection of the input space into the output one but also accounts for the reconstruction errors generated from the projection of the output space back to the input one. This loss function aims to potentially reconstruct the input data from the output data. Therefore, it is expected to obtain more accurate results. Finally, experiments on several real-world datasets are carried out to demonstrate the superiority of the proposed method for both LE and LDL.

Published
2020

42. Efficacy of metformin targets on cardiometabolic health in the general population and non-diabetic individuals: a Mendelian randomization study

Author

Zheng, Jie, Xu, Min, Yang, Qian, Hu, Chunyan, Walker, Venexia, Lu, Jieli, Wang, Jiqiu, Liu, Ruixin, Xu, Yu, Wang, Tiange, Zhao, Zhiyun, Yuan, Jinqiu, Burgess, Stephen, Au Yeung, Shiu Lun, Luo, Shan, Anderson, Emma L., Holmes, Michael V., Smith, George Davey, Ning, Guang, Wang, Weiqing, Gaunt, Tom R., and Bi, Yufang

Published
2023
Full Text
View/download PDF

48. Amino acids, microbiota-related metabolites, and the risk of incident diabetes among normoglycemic Chinese adults: Findings from the 4C study

Author

Wang, Shuangyuan, Li, Mian, Lin, Hong, Wang, Guixia, Xu, Yu, Zhao, Xinjie, Hu, Chunyan, Zhang, Yi, Zheng, Ruizhi, Hu, Ruying, Shi, Lixin, Du, Rui, Su, Qing, Wang, Jiqiu, Chen, Yuhong, Yu, Xuefeng, Yan, Li, Wang, Tiange, Zhao, Zhiyun, Liu, Ruixin, Wang, Xiaolin, Li, Qi, Qin, Guijun, Wan, Qin, Chen, Gang, Xu, Min, Dai, Meng, Zhang, Di, Tang, Xulei, Gao, Zhengnan, Shen, Feixia, Luo, Zuojie, Qin, Yingfen, Chen, Li, Huo, Yanan, Li, Qiang, Ye, Zhen, Zhang, Yinfei, Liu, Chao, Wang, Youmin, Wu, Shengli, Yang, Tao, Deng, Huacong, Zhao, Jiajun, Lai, Shenghan, Mu, Yiming, Chen, Lulu, Li, Donghui, Xu, Guowang, Ning, Guang, Wang, Weiqing, Bi, Yufang, and Lu, Jieli

Published
2022
Full Text
View/download PDF

50. Investigation of Adsorption and Young's Modulus of Epoxy Resin–Sand Interfaces Using Molecular Dynamics Simulation.

Author

Shen, Dejian, Pi, Xueran, Cai, Lili, Wang, Xin, Wu, Chunying, and Liu, Ruixin

Abstract

Epoxy resins exhibit outstanding curability, durability, and environmental compatibility, rendering them extensively utilized in the realm of engineering curing. Nevertheless, the current curing mechanism of epoxy-based resins in cohesion with sand remains inadequately elucidated, significantly impeding their applicability within the domain of soil curing. This study employed molecular dynamics simulations to investigate the adsorption behavior of three distinct types of epoxy resins on the sand surface: diglycidyl ether of bisphenol-A epoxy resin (DGEBA), diglycidyl ether 4,4′-dihydroxy diphenyl sulfone (DGEDDS), and aliphatic epoxidation of olefin resin (AEOR). The objective was to gain insights into the interactions between the sand surface and the epoxy resin polymers. The results demonstrated that DGEDDS formed a higher number of hydrogen bonds on the sand surface, leading to stronger intermolecular interactions compared to the other two resins. Furthermore, the mechanical properties of the adsorbed models of the three epoxy resins with sand were found to be relatively similar. This similarity can be attributed to their comparable chemical structures. Finally, analysis of the radius of gyration for the adsorbed epoxy resins revealed that AEOR exhibited a rigid structure due to strong molecular interactions, while DGEDDS displayed a flexible structure owing to weaker interactions. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results