英向华｜北京大学｜学者主页

2026

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Qi-Xun Wang, Yang Shi, Le-Tian Cheng, Zhuo-Ran Zhang, Yan He, Yu-Qi Tang, Qi Zhang, Xin-Lei Yu, Rui-Zhe Chen, Tianrun Xu, Yuan-Xing Zhang, Peng-Fei Wan, Hao-Tian Wang, Xianghua Ying

arXiv.org

DOI

2025

Improving Bird's Eye View based 3D object detection via Learnable Perspective View

Ruibin Wang, Bowei Xing, Xianghua Ying

Expert Systems With Applications，Vol. 293

DOI

2025

SalienTR: A closer look at multi-modal transformer for RGB-T salient object detection

Ruohao Guo, Wenzhen Yue, Liao Qu, Yanyu Qi, Dantong Niu, Xianghua Ying

Expert Systems With Applications，Vol. 286

DOI

2025

Monet: Reasoning in Latent Visual Space Beyond Images and Language

Qixun Wang, Yang Shi, Yi-Fei Wang, Yuan-Xing Zhang, Peng-Fei Wan, Kun Gai, Xianghua Ying, Yi-Sen Wang

arXiv.org

DOI

2025

MVFormer: Multi-View Point Cloud Transformer for 3D Mechanical Component Recognition

Ruibin Wang, Xianghua Ying, Bowei Xing

International Journal of Computer Vision

DOI

2025

Multi-modal Prompt Alignment with Fine-grained LLM Knowledge for Unsupervised Domain Adaptation

Bowei Xing, Xianghua Ying, Ruibin Wang, Ruohao Guo

International Journal of Computer Vision

DOI

2025

Audio-Visual Instance Segmentation

Ruohao Guo, Xianghua Ying, Yaru Chen, Dantong Niu, Guangyao Li, Liao Qu, Yanyu Qi, Jinxing Zhou, Bowei Xing, Wenzhen Yue, Ji Feng Shi, Qixun Wang, Peiliang Zhang, Buwen Liang

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2025

Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes

Ji Shi, Xianghua Ying, Ruohao Guo, Bowei Xing, Wenzhen Yue

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2024

Can In-context Learning Really Generalize to Out-of-distribution Tasks?

Qixun Wang, Yifei Wang, Yi-Sen Wang, Xianghua Ying

International Conference on Learning Representations

DOI

2024

Dissecting the Failure of Invariant Learning on Graphs

Qixun Wang, Yi-Fei Wang, Yi-Sen Wang, Xianghua Ying

Neural Information Processing Systems

DOI

2024

FPSMix: data augmentation strategy for point cloud classification

Taiyan Chen, Xianghua Ying

Frontiers of Computer Science

DOI

2024

Hierarchical Unsupervised Relation Distillation for Source Free Domain Adaptation

Bowei Xing, Xianghua Ying, Ruibin Wang, Ruohao Guo, Ji Shi, Wenzhen Yue

Lecture notes in computer science

DOI

2024

Open-Vocabulary Audio-Visual Semantic Segmentation

Ruohao Guo, Liao Qu, Dantong Niu, Yanyu Qi, Wenzhen Yue, Ji Shi, Bowei Xing, Xianghua Ying

ACM International Conference on Multimedia (ACM MM)

DOI

2024

Instance-Level Panoramic Audio-Visual Saliency Detection and Ranking

Ruohao Guo, Dantong Niu, Liao Qu, Yanyu Qi, Ji Shi, Wenzhen Yue, Bowei Xing, Taiyan Chen, Xianghua Ying

ACM International Conference on Multimedia (ACM MM)

DOI

2024

Rectifying self-training with neighborhood consistency and proximity for source-free domain adaptation

Bowei Xing, Xianghua Ying, Ruibin Wang

Neurocomputing

DOI

2024

Masked Local-Global Representation Learning for 3D Point Cloud Domain Adaptation

Bowei Xing, Xianghua Ying, Ruibin Wang

Proceedings - IEEE International Conference on Robotics and Automation/Proceedings

DOI

2024

VPDETR: End-to-End Vanishing Point DEtection TRansformers

Taiyan Chen, Xianghua Ying, Jinfa Yang, Ruibin Wang, Ruohao Guo, Bowei Xing, Ji Hong Shi

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2024

UniTR: A Unified TRansformer-Based Framework for Co-Object and Multi-Modal Saliency Detection

Ruohao Guo, Xianghua Ying, Yanyu Qi, Liao Qu

IEEE Transactions on Multimedia

DOI

2023

ECO-3D: Equivariant Contrastive Learning for Pre-training on Perturbed 3D Point Cloud

Rui-Bin Wang, Xianghua Ying, Bo-Wei Xing, Jinfa Yang

AAAI Conference on Artificial Intelligence

DOI

2023

Improving point cloud classification and segmentation via parametric veronese mapping

Rui-Bin Wang, Xianghua Ying, Bo-Wei Xing, Xin Tong, Taiyan Chen, Jinfa Yang, Yongjie Shi

Pattern Recognition

DOI

2023

Cross-Modal Contrastive Learning for Domain Adaptation in 3D Semantic Segmentation

Bo-Wei Xing, Xianghua Ying, Rui-Bin Wang, Jinfa Yang, Taiyan Chen

AAAI Conference on Artificial Intelligence

DOI

2023

Exploiting Temporal Correlations for 3D Human Pose Estimation

Ruibin Wang, Xianghua Ying, Bowei Xing

IEEE Transactions on Multimedia

DOI

2022

Unsupervised Domain Adaptation for Semantic Segmentation of Urban Street Scenes Reflected by Convex Mirrors

Yongjie Shi, Xianghua Ying, H. Zha

IEEE transactions on intelligent transportation systems (Print)

DOI

2022

Transformer Based Line Segment Classifier with Image Context for Real-Time Vanishing Point Detection in Manhattan World

Xin Tong, Xianghua Ying, Yongjie Shi, Rui-Bin Wang, Jinfa Yang

Computer Vision and Pattern Recognition

DOI

2021

Towards Cross-View Consistency in Semantic Segmentation While Varying View Direction

Xin Tong, Xianghua Ying, Yongjie Shi, He Zhao, Rui-Bin Wang

International Joint Conference on Artificial Intelligence

DOI

2021

Position-aware and Symmetry Enhanced GAN for Radial Distortion Correction

Yongjie Shi, Xin Tong, Jingsi Wen, He Zhao, Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2021

G-FAN: Graph-Based Feature Aggregation Network for Video Face Recognition

He Zhao, Yongjie Shi, Xin Tong, Jingsi Wen, Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2020

A Simple Yet Effective Pipeline For Radial Distortion Correction

He Zhao, Yongjie Shi, Xin Tong, Xianghua Ying, H. Zha

International Conference on Information Photonics

DOI

2020

RDCFace: Radial Distortion Correction for Face Recognition

He Zhao, Xianghua Ying, Yongjie Shi, Xin Tong, Jingsi Wen, H. Zha

Computer Vision and Pattern Recognition

DOI

2020

Qamface: Quadratic Additive Angular Margin Loss For Face Recognition

He Zhao, Yongjie Shi, Xin Tong, Xianghua Ying, H. Zha

International Conference on Information Photonics

DOI

2020

3D Orientation Estimation and Vanishing Point Extraction from Single Panoramas Using Convolutional Neural Network

Yongjie Shi, Xin Tong, Jingsi Wen, He Zhao, Xianghua Ying, H. Zha

IEEE International Conference on Robotics and Automation

DOI

2019

Three Orthogonal Vanishing Points Estimation in Structured Scenes Using Convolutional Neural Networks

Yongjie Shi, Danfeng Zhang, Jingsi Wen, Xin Tong, He Zhao, Xianghua Ying, H. Zha

International Conference on Information Photonics

DOI

2018

Radial Lens Distortion Correction by Adding a Weight Layer with Inverted Foveal Models to Convolutional Neural Networks

Yongjie Shi, Danfeng Zhang, Jingsi Wen, Xin Tong, Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2016

Simultaneously vanishing point detection and radial lens distortion correction from single wide-angle images

Sen Yang, Jiangpeng Rong, Shiyao Huang, Z. Shang, Yongjie Shi, Xianghua Ying, H. Zha

IEEE International Conference on Robotics and Biomimetics

DOI

2016

単一広角画像からの同時消滅点検出と半径方向レンズ歪補正【Powered by NICT】

Sen Yang, Jiangpeng Rong, Shiyao Huang, Z. Shang, Yongjie Shi, Xianghua Ying, H. Zha

2016

Radial Lens Distortion Correction Using Convolutional Neural Networks Trained with Synthesized Images

Jiangpeng Rong, Shiyao Huang, Z. Shang, Xianghua Ying

Asian Conference on Computer Vision

DOI

2016

Camera Calibration from Periodic Motion of a Pedestrian

Shiyao Huang, Xianghua Ying, Jiangpeng Rong, Z. Shang, H. Zha

Computer Vision and Pattern Recognition

DOI

2015

Radial lens distortion correction using cascaded one-parameter division model

Xiang Mei, Sen Yang, Jiangpeng Rong, Xianghua Ying, Shiyao Huang, H. Zha

International Conference on Information Photonics

DOI

2015

Ellipse-specific fitting by relaxing the 3L constraints with semidefinite programming

Jiangpeng Rong, Sen Yang, Xiang Mei, Xianghua Ying, Shiyao Huang, H. Zha

International Conference on Information Photonics

DOI

2014

Radial distortion correction from a single image of a planar calibration pattern using convex optimization

Xianghua Ying, Xiang Mei, Sen Yang, G. Wang, H. Zha

International Conference on Information Photonics

DOI

2014

A direct method for the extrinsic calibration of a camera and a line scan LIDAR

Xianghua Ying, G. Wang, Xiang Mei, Sen Yang, Jiangpeng Rong, H. Zha

IEEE International Conference on Mechatronics and Automation

DOI

2014

Imposing Differential Constraints on Radial Distortion Correction

Xianghua Ying, Xiang Mei, Sen Yang, G. Wang, Jiangpeng Rong, H. Zha

Asian Conference on Computer Vision

DOI

2014

The Perspective-3-Point Problem When Using a Planar Mirror

Xianghua Ying, G. Wang, Xiang Mei, Sen Yang, H. Zha

International Conference on Pattern Recognition

DOI

2013

Canonicalized central absolute moment for edge-based color constancy

Xianghua Ying, Lulu Hou, Yongbo Hou, Jing Kong, H. Zha

2013 IEEE International Conference on Image Processing

DOI

2013

Self-Calibration of Catadioptric Camera with Two Planar Mirrors from Silhouettes

Xianghua Ying, Kun Peng, Yongbo Hou, Sheng Guan, Jing Kong, H. Zha

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2013

Automatic Object Cosegmentation in Sparse Multiview Images

Songtao Pu, Jing Kong, Xianghua Ying, H. Zha

2013 2nd IAPR Asian Conference on Pattern Recognition

DOI

2012

A Fast Algorithm for Multidimensional Ellipsoid-Specific Fitting by Minimizing a New Defined Vector Norm of Residuals Using Semidefinite Programming

Xianghua Ying, Li Yang, H. Zha

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2012

Direct least square fitting of ellipsoids

Xianghua Ying, Li Yang, Jing Kong, Yongbo Hou, Sheng Guan, H. Zha

International Conference on Pattern Recognition

2012

Camera Calibration Using Vertical Lines

Jing Kong, Xianghua Ying, Songtao Pu, Yongbo Hou, Sheng Guan, G. Wang, H. Zha

ACCV Workshops

DOI

2012

Vanishing point detection using cascaded 1D Hough Transform from single images

Bo Li, Kun Peng, Xianghua Ying, H. Zha

Pattern Recognition Letters

DOI

2011

3D tracking using rectangular regions in structured scenes

Kun Peng, Lulu Hou, Jing Kong, Ren Ren, Xianghua Ying, H. Zha

2011 IEEE International Conference on Information and Automation

DOI

2011

Camera Resectioning from Image Edges with the L∞-Norm Using Linear Programming

Li Yang, Xianghua Ying, Lulu Hou, Jing Kong, H. Zha

British Machine Vision Conference

DOI

2011

Appling semantic method to windows detection in façade

Xi Wang, Kun‐Li Wen, Xianghua Ying, Huo-Cheng Chen

IEEE/SICE International Symposium on System Integration (SII)

DOI

2010

Simultaneous Vanishing Point Detection and Camera Calibration from Single Images

Bo Li, Kun Peng, Xianghua Ying, H. Zha

International Symposium on Visual Computing

DOI

2010

Single View Metrology Along Orthogonal Directions

Kun Peng, Lulu Hou, Ren Ren, Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2010

Geometric properties of multiple reflections in catadioptric camera with two planar mirrors

Xianghua Ying, Kun Peng, Ren Ren, H. Zha

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

2009

Combining Laser-Scanning Data and Images for Target Tracking and Scene Modeling

H. Zha, Huijing Zhao, Jinshi Cui, Xuan Song, Xianghua Ying

International Symposium of Robotics Research

DOI

2009

Walkthrough in large environments using concatenated panoramas

Xianghua Ying, Kun Peng, H. Zha

IEEE International Conference on Robotics and Biomimetics

DOI

2008

Efficient detection of projected concentric circles using four intersection points on a secant line

Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2008

Identical Projective Geometric Properties of Central Catadioptric Line Images and Sphere Images with Applications to Calibration

Xianghua Ying, H. Zha

International Journal of Computer Vision

DOI

2008

Method for recovering three-dimensional geometric information from image

Renju Li, Hong-Bin Cha, Xianghua Ying, Xiang-Yin Ma

2007

Camera Calibration Using Principal-Axes Aligned Conics

Xianghua Ying, H. Zha

Asian Conference on Computer Vision

DOI

2007

Camera calibration from a circle and a coplanar point at infinity with applications to sports scenes analyses

Xianghua Ying, H. Zha

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems

DOI

2007

An Efficient Method for the Detection of Projected Concentric Circles

Xianghua Ying, H. Zha

2007 IEEE International Conference on Image Processing

DOI

2006

Fisheye Lenses Calibration Using Straight-Line Spherical Perspective Projection Constraint

Xianghua Ying, Zhan-Yi Hu, H. Zha

Asian Conference on Computer Vision

DOI

2006

Interpreting Sphere Images Using the Double-Contact Theorem

Xianghua Ying, H. Zha

Asian Conference on Computer Vision

DOI

2006

Geometric Interpretations of the Relation between the Image of the Absolute Conic and Sphere Images

Xianghua Ying, H. Zha

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2006

A Novel Linear Approach to Camera Calibration from Sphere Images

Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2006

Using Sphere Images for Calibrating Fisheye Cameras under the Unified Imaging Model of the Central Catadioptric and Fisheye Cameras

Xianghua Ying, H. Zha

International Conference on Pattern Recognition

DOI

2005

Linear approaches to camera calibration from sphere images or active intrinsic calibration using vanishing points

Xianghua Ying, H. Zha

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1

DOI

2005

Camera pose determination from a single view of parallel lines

Xianghua Ying, H. Zha

IEEE International Conference on Image Processing 2005

DOI

2005

Simultaneously calibrating catadioptric camera and detecting line features using Hough transform

Xianghua Ying, H. Zha

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems

DOI

2004

Catadioptric line features detection using Hough transform

Xianghua Ying, Zhan-Yi Hu

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.

DOI

2004

Spherical objects based motion estimation for catadioptric cameras

Xianghua Ying, Zhan-Yi Hu

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.

DOI

2004

Can We Consider Central Catadioptric Cameras and Fisheye Cameras within a Unified Imaging Model

Xianghua Ying, Zhan-Yi Hu

European Conference on Computer Vision

DOI

2003

一种基于球面透视投影约束的鱼眼镜头校正方法

英向华，胡占义

《计算机学报》

2003

Catadioptric camera calibration using geometric invariants

Xianghua Ying, Zhanyi Hu

Proceedings Ninth IEEE International Conference on Computer Vision

DOI

精选作品

期刊论文

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Improving Bird's Eye View based 3D object detection via Learnable Perspective View

SalienTR: A closer look at multi-modal transformer for RGB-T salient object detection

Monet: Reasoning in Latent Visual Space Beyond Images and Language

MVFormer: Multi-View Point Cloud Transformer for 3D Mechanical Component Recognition

Multi-modal Prompt Alignment with Fine-grained LLM Knowledge for Unsupervised Domain Adaptation

Audio-Visual Instance Segmentation

Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes

Can In-context Learning Really Generalize to Out-of-distribution Tasks?

Dissecting the Failure of Invariant Learning on Graphs

FPSMix: data augmentation strategy for point cloud classification

Hierarchical Unsupervised Relation Distillation for Source Free Domain Adaptation

Open-Vocabulary Audio-Visual Semantic Segmentation

Instance-Level Panoramic Audio-Visual Saliency Detection and Ranking

Rectifying self-training with neighborhood consistency and proximity for source-free domain adaptation

Masked Local-Global Representation Learning for 3D Point Cloud Domain Adaptation

VPDETR: End-to-End Vanishing Point DEtection TRansformers

UniTR: A Unified TRansformer-Based Framework for Co-Object and Multi-Modal Saliency Detection

ECO-3D: Equivariant Contrastive Learning for Pre-training on Perturbed 3D Point Cloud

Improving point cloud classification and segmentation via parametric veronese mapping

Cross-Modal Contrastive Learning for Domain Adaptation in 3D Semantic Segmentation

Exploiting Temporal Correlations for 3D Human Pose Estimation

Unsupervised Domain Adaptation for Semantic Segmentation of Urban Street Scenes Reflected by Convex Mirrors

Transformer Based Line Segment Classifier with Image Context for Real-Time Vanishing Point Detection in Manhattan World

Towards Cross-View Consistency in Semantic Segmentation While Varying View Direction

Position-aware and Symmetry Enhanced GAN for Radial Distortion Correction

G-FAN: Graph-Based Feature Aggregation Network for Video Face Recognition

A Simple Yet Effective Pipeline For Radial Distortion Correction

RDCFace: Radial Distortion Correction for Face Recognition

Qamface: Quadratic Additive Angular Margin Loss For Face Recognition

3D Orientation Estimation and Vanishing Point Extraction from Single Panoramas Using Convolutional Neural Network

Three Orthogonal Vanishing Points Estimation in Structured Scenes Using Convolutional Neural Networks

Radial Lens Distortion Correction by Adding a Weight Layer with Inverted Foveal Models to Convolutional Neural Networks

Simultaneously vanishing point detection and radial lens distortion correction from single wide-angle images

単一広角画像からの同時消滅点検出と半径方向レンズ歪補正【Powered by NICT】

Radial Lens Distortion Correction Using Convolutional Neural Networks Trained with Synthesized Images

Camera Calibration from Periodic Motion of a Pedestrian

Radial lens distortion correction using cascaded one-parameter division model

Ellipse-specific fitting by relaxing the 3L constraints with semidefinite programming

Radial distortion correction from a single image of a planar calibration pattern using convex optimization

A direct method for the extrinsic calibration of a camera and a line scan LIDAR

Imposing Differential Constraints on Radial Distortion Correction

The Perspective-3-Point Problem When Using a Planar Mirror

Canonicalized central absolute moment for edge-based color constancy

Self-Calibration of Catadioptric Camera with Two Planar Mirrors from Silhouettes

Automatic Object Cosegmentation in Sparse Multiview Images

A Fast Algorithm for Multidimensional Ellipsoid-Specific Fitting by Minimizing a New Defined Vector Norm of Residuals Using Semidefinite Programming

Direct least square fitting of ellipsoids

Camera Calibration Using Vertical Lines

Vanishing point detection using cascaded 1D Hough Transform from single images

3D tracking using rectangular regions in structured scenes

Camera Resectioning from Image Edges with the L∞-Norm Using Linear Programming

Appling semantic method to windows detection in façade

Simultaneous Vanishing Point Detection and Camera Calibration from Single Images

Single View Metrology Along Orthogonal Directions

Geometric properties of multiple reflections in catadioptric camera with two planar mirrors

Combining Laser-Scanning Data and Images for Target Tracking and Scene Modeling

Walkthrough in large environments using concatenated panoramas

Efficient detection of projected concentric circles using four intersection points on a secant line

Identical Projective Geometric Properties of Central Catadioptric Line Images and Sphere Images with Applications to Calibration

Method for recovering three-dimensional geometric information from image

Camera Calibration Using Principal-Axes Aligned Conics

Camera calibration from a circle and a coplanar point at infinity with applications to sports scenes analyses

An Efficient Method for the Detection of Projected Concentric Circles

Fisheye Lenses Calibration Using Straight-Line Spherical Perspective Projection Constraint

Interpreting Sphere Images Using the Double-Contact Theorem

Geometric Interpretations of the Relation between the Image of the Absolute Conic and Sphere Images

A Novel Linear Approach to Camera Calibration from Sphere Images

Using Sphere Images for Calibrating Fisheye Cameras under the Unified Imaging Model of the Central Catadioptric and Fisheye Cameras

Linear approaches to camera calibration from sphere images or active intrinsic calibration using vanishing points

Camera pose determination from a single view of parallel lines

Simultaneously calibrating catadioptric camera and detecting line features using Hough transform

Catadioptric line features detection using Hough transform

Spherical objects based motion estimation for catadioptric cameras

Can We Consider Central Catadioptric Cameras and Fisheye Cameras within a Unified Imaging Model

一种基于球面透视投影约束的鱼眼镜头校正方法

Catadioptric camera calibration using geometric invariants

研究方向