Loading [MathJax]/extensions/MathMenu.js
Xiao-Ding Cai - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Xiao-Ding Cai

Publications
13
Citations
112
Publications by Year
20142025
Co-Authors:
Show All Co-Authors (42)
Headshot silhouette indicating that no photo is available for this author

Xiao-Ding Cai

Affiliation

Cisco Systems
Inc.
San Jose, CA, USA

Publication Topics

Biography

Xiao-Ding Cai (Member, IEEE) received the Ph.D. degree in electrical engineering from the University of Ottawa, Ottawa, ON, Canada, in 1995.,He is currently a Technical Leader in systems groups with Cisco Systems, San Jose, CA, USA.(Based on document published on 26 September 2022).
Publications
13
Citations
112
Publications by Year
20142025
Co-Authors:
Show All Co-Authors (42)
Author's Published Works

Showing 1-22 of 22 results

  • Sort

Filter Results

Show

Sort By

Results

Distributed Bundle Adjustment Based on Penalty Function Method

Qixuan Sun;Guanghui Zhang;Dongchen Zhu;Lei Wang;Xiaolin Zhang;Jiamao Li

IEEE Robotics and Automation Letters
Year: 2025 | Volume: 10, Issue: 6 | Journal Article |
Bundle Adjustment (BA) aims to estimate the camera poses and build maps utilizing the nonlinear optimization algorithm. The update step of the optimization is obtained by solving a linear system, which is the bottleneck of the BA efficiency. Many works perform bundle adjustment in a distributed manner to reduce the computational cost of solving the linear system and achieve outstanding performance...Show More

Distributed Bundle Adjustment Based on Penalty Function Method

Qixuan Sun;Guanghui Zhang;Dongchen Zhu;Lei Wang;Xiaolin Zhang;Jiamao Li

Year: 2025 | Volume: 10, Issue: 6 | Journal Article |

Points and Patches in Textures by Exploring in Monocular Depth Estimation

Deming Wu;Guanghui Zhang;Wei Ming;Wenhao Wang;Xiaochen Jing;Dongchen Zhu

2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)
Year: 2024 | Conference Paper |
Rich texture information is sometimes not good for deep learning, and can introduce unwanted noise information, especially for monocular depth learning. In order to solve the phenomenon of ‘messy textures’ caused by rich texture in monocular depth estimation, this paper exploits the property of intra-patch disparity consistency to reconstruct the image to mitigate this phenomenon. The joint traini...Show More

Points and Patches in Textures by Exploring in Monocular Depth Estimation

Deming Wu;Guanghui Zhang;Wei Ming;Wenhao Wang;Xiaochen Jing;Dongchen Zhu

Year: 2024 | Conference Paper |

Improving Panoptic Segmentation in Occlusion with a Local-aware Decoder

Yue Xu;Guanghui Zhang;Deming Wu;Xingyuan Deng;Wenhao Wang;Xiaochen Jing;Dongchen Zhu;Xiaolin Zhang

2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)
Year: 2024 | Conference Paper |
Panoptic segmentation, a unifying computer vision task combining semantic and instance segmentation, plays a crucial role in autonomous driving and robot navigation applications. With advancements in deep learning technology, particularly the introduction of the Transformer model, panoptic segmentation achieved significant progress. However, existing methods still struggle with performance in occl...Show More

Improving Panoptic Segmentation in Occlusion with a Local-aware Decoder

Yue Xu;Guanghui Zhang;Deming Wu;Xingyuan Deng;Wenhao Wang;Xiaochen Jing;Dongchen Zhu;Xiaolin Zhang

Year: 2024 | Conference Paper |

BEE-Net: Bridging Semantic and Instance with Gated Encoding and Edge Constraint for Efficient Panoptic Segmentation

Xinyang Huang;Guanghui Zhang;Dongchen Zhu;Yunpeng Sun;Wenjun Shi;Gang Ye;Yang Xiao;Lei Wang;Xiaolin Zhang;Bo Li;Jiamao Li

2024 IEEE International Conference on Robotics and Automation (ICRA)
Year: 2024 | Conference Paper |
Panoptic segmentation is a challenging perception task, which can help robots to comprehensively perceive the surrounding environment. In the task, we notice that semantic, instance, and panoptic have rich relations, however, which are rarely explored. In this work, we propose a novel panoptic, instance, and semantic bridged network to delve into the reciprocal relation. To make semantic and insta...Show More

BEE-Net: Bridging Semantic and Instance with Gated Encoding and Edge Constraint for Efficient Panoptic Segmentation

Xinyang Huang;Guanghui Zhang;Dongchen Zhu;Yunpeng Sun;Wenjun Shi;Gang Ye;Yang Xiao;Lei Wang;Xiaolin Zhang;Bo Li;Jiamao Li

Year: 2024 | Conference Paper |

CVFormer: Learning Circum-View Representation and Consistency for Vision-Based Occupancy Prediction via Transformers

Zhengqi Bai;Wenjun Shi;Dongchen Zhu;Hanlong Kang;Guanghui Zhang;Gang Ye;Yang Xiao;Lei Wang;Xiaolin Zhang;Bo Li;Jiamao Li

2024 IEEE International Conference on Robotics and Automation (ICRA)
Year: 2024 | Conference Paper |
With the increasing demands for perception accuracy in autonomous driving, there is a growing focus on fine-grained 3D semantic occupancy prediction. Effectively representing detailed three-dimensional scenes has become a significant challenge in the development of this task. In this paper, we present a novel transformer-based framework named CVFormer, which leverages two-dimensional circum-views ...Show More

CVFormer: Learning Circum-View Representation and Consistency for Vision-Based Occupancy Prediction via Transformers

Zhengqi Bai;Wenjun Shi;Dongchen Zhu;Hanlong Kang;Guanghui Zhang;Gang Ye;Yang Xiao;Lei Wang;Xiaolin Zhang;Bo Li;Jiamao Li

Year: 2024 | Conference Paper |

Self-supervised Scale Recovery for Decoupled Visual-inertial Odometry

Tianyu Zhang;Dongchen Zhu;Wenjun Shi;Yanqing Liu;Guanghui Zhang;Xiaolin Zhang;Jiamao Li

IEEE Robotics and Automation Letters
Year: 2024 | Volume: 9, Issue: 2 | Journal Article |
Cited by: Papers (1)
Accurate localization for intelligent robots remains a significant challenge, and self-supervised visual-inertial odometry (VIO) has emerged as a promising solution. However, existing self-supervised VIO works consider inertial information as the ordinary data input, losing its ability to recover absolute scales and ignoring the modality difference of acceleration and angular velocity in inertial ...Show More

Self-supervised Scale Recovery for Decoupled Visual-inertial Odometry

Tianyu Zhang;Dongchen Zhu;Wenjun Shi;Yanqing Liu;Guanghui Zhang;Xiaolin Zhang;Jiamao Li

Year: 2024 | Volume: 9, Issue: 2 | Journal Article |

Efficient Solution to PnP Problem Based on Vision Geometry

Qixuan Sun;Tianyu Zhang;Guanghui Zhang;Kaifang Wang;Dongchen Zhu;Jiamao Li;Xiaolin Zhang

IEEE Robotics and Automation Letters
Year: 2024 | Volume: 9, Issue: 4 | Journal Article |
Cited by: Papers (3)
Perspective-n-Point (PnP) problem aims to estimate pose from known 3D map points and their projections. Efficient PnP (EPnP), one of the classical PnP solvers, represents camera pose with control points, which are easier to estimate utilizing the least square (LS) formulation. However, the geometry refinement procedure performed by most EPnP-based methods is separated from the solution of LS formu...Show More

Efficient Solution to PnP Problem Based on Vision Geometry

Qixuan Sun;Tianyu Zhang;Guanghui Zhang;Kaifang Wang;Dongchen Zhu;Jiamao Li;Xiaolin Zhang

Year: 2024 | Volume: 9, Issue: 4 | Journal Article |

FeatDANet: Feature-level Domain Adaptation Network for Semantic Segmentation

Jiao Li;Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Xiaolin Zhang;Jiamao Li

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Year: 2023 | Conference Paper |
Cited by: Papers (1)
Unsupervised domain adaptation (UDA) is proposed to better adapt the network trained on labeled synthetic data to unlabeled real-world data for addressing the annotation cost. However, most of these methods pay more attention to domain distributions in input and output stages while ignoring the important differences in semantic expressions and local details in middle feature stages. Therefore, a n...Show More

FeatDANet: Feature-level Domain Adaptation Network for Semantic Segmentation

Jiao Li;Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Xiaolin Zhang;Jiamao Li

Year: 2023 | Conference Paper |

SGM-based Refined Hints for Stereo Matching Generalization Improvement leveraging Gaussian Policy

Haolong Zhou;Guanghui Zhang;Dongchen Zhu;Xin Wang;Xiaolin Zhang;Jiamao Li

2023 International Conference on Frontiers of Robotics and Software Engineering (FRSE)
Year: 2023 | Conference Paper |
Stereo matching has been a hot research topic in 3D reconstruction. Although great progress has been made thanks to deep learning technique, the performance still suffers a significant drop when dealing with a new domain. Recently, LiDAR and Radar guidance strategies are explored to alleviate the generalization problem. However, they rely on extra depth sensor cues. In this paper, a novel SGM-base...Show More

SGM-based Refined Hints for Stereo Matching Generalization Improvement leveraging Gaussian Policy

Haolong Zhou;Guanghui Zhang;Dongchen Zhu;Xin Wang;Xiaolin Zhang;Jiamao Li

Year: 2023 | Conference Paper |

CM-CS: Cross-Modal Common-Specific Feature Learning For Audio-Visual Video Parsing

Hongbo Chen;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Xiaolin Zhang;Jiamao Li

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Cited by: Papers (4)
The weakly-supervised audio-visual video parsing (AVVP) task aims to parse duration and categories of each snippet when only the video-level event labels are provided. Most methods either leverage attention mechanisms to explore cross-modal and cross-video event semantics or alleviate label noise to improve performance. However, the distributional modality discrepancy caused by the heterogeneity o...Show More

CM-CS: Cross-Modal Common-Specific Feature Learning For Audio-Visual Video Parsing

Hongbo Chen;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Xiaolin Zhang;Jiamao Li

Year: 2023 | Conference Paper |

SD-Pose: Structural Discrepancy Aware Category-Level 6D Object Pose Estimation

Guowei Li;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Tianyu Zhang;Xiaolin Zhang;Jiamao Li

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2023 | Conference Paper |
Cited by: Papers (4)
Category-level 6D object pose estimation aims to predict the full pose and size information for previously unseen instances from known categories, which is an essential portion of robot grasping and augmented reality. However, the core challenge of this task still is the enormous shape variation within each category. With regard to the challenge, we propose a novel framework SD-Pose, which utilize...Show More

SD-Pose: Structural Discrepancy Aware Category-Level 6D Object Pose Estimation

Guowei Li;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Tianyu Zhang;Xiaolin Zhang;Jiamao Li

Year: 2023 | Conference Paper |

MFCFlow: A Motion Feature Compensated Multi-Frame Recurrent Network for Optical Flow Estimation

Yonghu Chen;Dongchen Zhu;Wenjun Shi;Guanghui Zhang;Tianyu Zhang;Xiaolin Zhang;Jiamao Li

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2023 | Conference Paper |
Cited by: Papers (6)
Occlusions have long been a hard nut to crack in optical flow estimation due to ambiguous pixels matching between abutting images. Current methods only take two consecutive images as input, which is challenging to capture temporal coherence and reason about occluded regions. In this paper, we propose a novel optical flow estimation framework, namely MFCFlow, which attempts to compensate for the in...Show More

MFCFlow: A Motion Feature Compensated Multi-Frame Recurrent Network for Optical Flow Estimation

Yonghu Chen;Dongchen Zhu;Wenjun Shi;Guanghui Zhang;Tianyu Zhang;Xiaolin Zhang;Jiamao Li

Year: 2023 | Conference Paper |

Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation

Minghong Chen;Guanghui Zhang;Wenjun Shi;Dongchen Zhu;Xiaolin Zhang;Jiamao Li

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)
Year: 2022 | Conference Paper |
Neighborhood construction plays a key role in point cloud processing. However, existing models only use a single neighborhood construction method to extract neighborhood features, which limits their scene understanding ability. In this paper, we propose a learnable Dual-Neighborhood Feature Aggregation (DNFA) module embedded in the encoder that builds and aggregates comprehensive surrounding knowl...Show More

Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation

Minghong Chen;Guanghui Zhang;Wenjun Shi;Dongchen Zhu;Xiaolin Zhang;Jiamao Li

Year: 2022 | Conference Paper |

J-RR: Joint Monocular Depth Estimation and Semantic Edge Detection Exploiting Reciprocal Relations

Deming Wu;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Xiaolin Zhang;Jiamao Li

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Depth estimation and semantic edge detection are two key tasks in computer vision, which have made great progress. To date, how to associatively predict the depth and the semantic edge is rarely explored. In this work, we first propose a flexible two-branch framework that can make the two tasks take advantage of each other, achieving a win-win situation. Specifically, for the semantic edge detecti...Show More

J-RR: Joint Monocular Depth Estimation and Semantic Edge Detection Exploiting Reciprocal Relations

Deming Wu;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Xiaolin Zhang;Jiamao Li

Year: 2022 | Conference Paper |

Spatiotemporally Enhanced Photometric Loss for Self-Supervised Monocular Depth Estimation

Tianyu Zhang;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Yanqing Liu;Xiaolin Zhang;Jiamao Li

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Recovering depth information from a single image is a long-standing challenge, and self-supervised depth estimation methods have gradually attracted attention due to not relying on high-cost ground truth. Constructing an accurate photometric loss based on photometric consistency is crucial for these self-supervised methods to obtain high-quality depth maps. However, the photometric loss in most st...Show More

Spatiotemporally Enhanced Photometric Loss for Self-Supervised Monocular Depth Estimation

Tianyu Zhang;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Yanqing Liu;Xiaolin Zhang;Jiamao Li

Year: 2022 | Conference Paper |

SRNet: Structural Relation-aware Network for Head Pose Estimation

Zhaoxiang Zeng;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Lei Wang;Xiaolin Zhang;Jiamao Li

2022 26th International Conference on Pattern Recognition (ICPR)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Estimating head pose from a single RGB image has recently attracted considerable research attention. Prior arts employ a CNN backbone to process face images and then directly output Euler angles. We argue that they may ignore essential features that are highly correlated to head pose due to the non-global perspective, and the ambiguity and discontinuity issues of Euler angles representation could ...Show More

SRNet: Structural Relation-aware Network for Head Pose Estimation

Zhaoxiang Zeng;Dongchen Zhu;Guanghui Zhang;Wenjun Shi;Lei Wang;Xiaolin Zhang;Jiamao Li

Year: 2022 | Conference Paper |

RGB-D Semantic Segmentation and Label-Oriented Voxelgrid Fusion for Accurate 3D Semantic Mapping

Wenjun Shi;Jingwei Xu;Dongchen Zhu;Guanghui Zhang;Xianshun Wang;Jiamao Li;Xiaolin Zhang

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2022 | Volume: 32, Issue: 1 | Journal Article |
Cited by: Papers (45)
The 3D semantic map plays an increasingly important role in a wide variety of applications, especially for many kinds of task-driven robots. In this paper, we present a semantic mapping methodology for 3D semantic map obtaining from RGB-D scans. In contrast to existing methods that use 3D annotated information as supervisory, we focus on accurate 2D frame labeling and combine labels in 3D space us...Show More

RGB-D Semantic Segmentation and Label-Oriented Voxelgrid Fusion for Accurate 3D Semantic Mapping

Wenjun Shi;Jingwei Xu;Dongchen Zhu;Guanghui Zhang;Xianshun Wang;Jiamao Li;Xiaolin Zhang

Year: 2022 | Volume: 32, Issue: 1 | Journal Article |

RegionNet: Region-feature-enhanced 3D Scene Understanding Network with Dual Spatial-aware Discriminative Loss

Guanghui Zhang;Dongchen Zhu;Xiaoqing Ye;Wenjun Shi;Minghong Chen;Jiamao Li;Xiaolin Zhang

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Year: 2020 | Conference Paper |
Neural networks have recently achieved impressive success in semantic and instance segmentation on 2D images. However, their capabilities have not been fully explored to address semantic instance segmentation on unstructured 3D point cloud data. Digging into the regional feature representation to boost point cloud comprehension, we propose a region-feature-enhanced structure consisting of adaptive...Show More

RegionNet: Region-feature-enhanced 3D Scene Understanding Network with Dual Spatial-aware Discriminative Loss

Guanghui Zhang;Dongchen Zhu;Xiaoqing Ye;Wenjun Shi;Minghong Chen;Jiamao Li;Xiaolin Zhang

Year: 2020 | Conference Paper |

Multilevel Cross-Aware RGBD Indoor Semantic Segmentation for Bionic Binocular Robot

Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Jingwei Xu;Xianshun Wang;Lili Chen;Jiamao Li;Xiaolin Zhang

IEEE Transactions on Medical Robotics and Bionics
Year: 2020 | Volume: 2, Issue: 3 | Journal Article |
Cited by: Papers (7)
Scene understanding is one of the foundations for robots to achieve true artificial intelligence. Semantic segmentation that imitates the mechanism of human visual system can effectively promote the correctness of scene understanding. It conforms to the basic principle of human environment perception and enables robots to better serve human society. In this paper, we propose a multilevel cross-awa...Show More

Multilevel Cross-Aware RGBD Indoor Semantic Segmentation for Bionic Binocular Robot

Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Jingwei Xu;Xianshun Wang;Lili Chen;Jiamao Li;Xiaolin Zhang

Year: 2020 | Volume: 2, Issue: 3 | Journal Article |

Multilevel Cross-Aware RGBD Semantic Segmentation of Indoor Environments

Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Lili Chen;Lei Wang;Jiamao Li;Xiaolin Zhang

2019 IEEE International Conference on Cyborg and Bionic Systems (CBS)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
Semantic segmentation is the main step towards scene understanding which is one of the most important tasks of computer vision. As the depth and color information are independent, the combination of depth and RGB images can improve the quality of semantic labeling. In this paper, we proposed a multilevel cross-aware network (MCA-Net) for RGBD semantic segmentation to jointly reason about 2D appear...Show More

Multilevel Cross-Aware RGBD Semantic Segmentation of Indoor Environments

Wenjun Shi;Dongchen Zhu;Guanghui Zhang;Lili Chen;Lei Wang;Jiamao Li;Xiaolin Zhang

Year: 2019 | Conference Paper |

A Hierarchical Attention Fused Descriptor for 3D Point Matching

Wenjun Shi;Dongchen Zhu;Liang Du;Guanghui Zhang;Jiamao Li;Xiaolin Zhang

IEEE Access
Year: 2019 | Volume: 7 | Journal Article |
Cited by: Papers (1)
Motivated by recent successes on learning 3D feature representations, we present a Siamese network to generate representative 3D descriptors for 3D point matching in point cloud registration. Our system, dubbed HAF-Net, consists of feature extraction module, hierarchical feature reweighting and recalibration module (HRR), as well as feature aggregation and compression module. The HRR module is pro...Show More

A Hierarchical Attention Fused Descriptor for 3D Point Matching

Wenjun Shi;Dongchen Zhu;Liang Du;Guanghui Zhang;Jiamao Li;Xiaolin Zhang

Year: 2019 | Volume: 7 | Journal Article |

Multi-Dimensional Residual Dense Attention Network for Stereo Matching

Guanghui Zhang;Dongchen Zhu;Wenjun Shi;Xiaoqing Ye;Jiamao Li;Xiaolin Zhang

IEEE Access
Year: 2019 | Volume: 7 | Journal Article |
Cited by: Papers (16)
Very deep convolutional neural networks (CNNs) have recently achieved great success in stereo matching. It is still highly desirable to learn a robust feature map to improve ill-posed regions, such as weakly textured regions, reflective surfaces, and repetitive patterns. Therefore, we propose an end-to-end multi-dimensional residual dense attention network (MRDA-Net) in this paper, focusing on mor...Show More

Multi-Dimensional Residual Dense Attention Network for Stereo Matching

Guanghui Zhang;Dongchen Zhu;Wenjun Shi;Xiaoqing Ye;Jiamao Li;Xiaolin Zhang

Year: 2019 | Volume: 7 | Journal Article |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.