Personal information

Biography

Dr. Xiaojuan Qi is currently an assistant professor at the University of Hong Kong and a member of the Deep Vision Lab. Her research lies in the broad areas of Computer Vision, Deep Learning, and Artificial Intelligence. We aim at endowing machines with the capability to perceive, understand, and reconstruct the visual world with the following focuses: 1) developing label-efficient and computation-efficient deep learning algorithms for natural and medical image analysis; 2) designing effective techniques for 3D scene understanding and reconstruction; and 3) building lifelong learning machines that can learn continuously, transfer previous knowledge and discover novel concepts (through interaction).

She obtained my Ph.D. degree in the Computer Science and Engineering Department, The Chinese University of Hong Kong (CUHK), supervised by Prof. Jiaya Jia in 2018. Before that, she got the B.Eng. degree in Electronic Science and Technology at Shanghai Jiao Tong University (SJTU) supervised by Prof. Ya Zhang in 2014.

Activities

Employment (2)

The University of Hong Kong: Hong Kong, 香港島, HK

2020-02-01 to present | Assistant Professor (Electrical and Electronic Engineering)
Employment
Source: Self-asserted source
Qi Xiaojuan

University of Oxford Department of Engineering Science: Oxford, Oxfordshire, GB

2018-12-12 to 2020-01-30
Employment
Source: Self-asserted source
Qi Xiaojuan

Education and qualifications (1)

Chinese University of Hong Kong: New Territories, HK

2014-08-01 to 2018-11-29 (Computer Science and Engineering)
Qualification
Source: Self-asserted source
Qi Xiaojuan

Works (50 of 130)

Items per page:
Page 1 of 3

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features

IEEE Access
2024 | Journal article
Contributors: Song Wang; Zhu Wang; Can Li; Xiaojuan Qi; Hayden Kwok-Hay So
Source: check_circle
Crossref

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence
2024-12 | Journal article
Contributors: Runyu Ding; Jihan Yang; Chuhui Xue; Wenqing Zhang; Song Bai; Xiaojuan Qi
Source: check_circle
Crossref

Object-Centric Representation Learning for Video Scene Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence
2024-12 | Journal article
Contributors: Yi Zhou; Hui Zhang; Seung-In Park; ByungIn Yoo; Xiaojuan Qi
Source: check_circle
Crossref

3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting

ACM Transactions on Graphics
2024-12-19 | Journal article
Contributors: Xiaoyang Lyu; Yang-Tian Sun; Yi-Hua Huang; Xiuzhe Wu; Ziyi Yang; Yilun Chen; Jiangmiao Pang; Xiaojuan Qi
Source: check_circle
Crossref

TEXGen: a Generative Diffusion Model for Mesh Textures

ACM Transactions on Graphics
2024-12-19 | Journal article
Contributors: Xin Yu; Ze Yuan; Yuan-Chen Guo; Ying-Tian Liu; Jianhui Liu; Yangguang Li; Yan-Pei Cao; Ding Liang; Xiaojuan Qi
Source: check_circle
Crossref

High-dimensional anticounterfeiting nanodiamonds authenticated with deep metric learning

Nature Communications
2024-12-05 | Journal article
Contributors: Lingzhi Wang; Xin Yu; Tongtong Zhang; Yong Hou; Dangyuan Lei; Xiaojuan Qi; Zhiqin Chu
Source: check_circle
Crossref

Debiasing Text-to-Image Diffusion Models

2024-10-28 | Conference paper
Contributors: Ruifei He; Chuhui Xue; Haoru Tan; Wenqing Zhang; Yingchen Yu; Song Bai; Xiaojuan Qi
Source: check_circle
Crossref

Diffusion-based deep learning method for augmenting ultrastructural imaging and volume electron microscopy

Nature Communications
2024-06-01 | Journal article
Contributors: Chixiang Lu; Kai Chen; Heng Qiu; Xiaojun Chen; Gu Chen; Xiaojuan Qi; Haibo Jiang
Source: check_circle
Crossref

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
2024-03 | Journal article
Contributors: Jin Gao; Yan Lu; Xiaojuan Qi; Yutong Kou; Bing Li; Liang Li; Shan Yu; Weiming Hu
Source: check_circle
Crossref

MEN: Mutual Enhancement Networks for Sign Language Recognition and Education

IEEE Transactions on Neural Networks and Learning Systems
2024-01 | Journal article
Contributors: Zhengzhe Liu; Lei Pang; Xiaojuan Qi
Source: check_circle
Crossref

You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding

World Scientific Annual Review of Artificial Intelligence
2024-01 | Journal article
Contributors: Zhengzhe Liu; Xiaojuan Qi; Chi-Wing Fu
Source: check_circle
Crossref

CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Advances in Neural Information Processing Systems (NeurIPS)
2023 | Journal article
Contributors: Ma, Chuofan; Jiang, Yi; Wen, Xin; Yuan, Zehuan; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Command-Driven Articulated Object Understanding and Manipulation

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Chu, Ruihang; Liu, Zhengzhe; Ye, Xiaoqing; Tan, Xiao; Qi, Xiaojuan; Fu, Chi-Wing; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

arXiv preprint arXiv:2303.14893
2023 | Journal article
Contributors: Qian, Xiaoyan; Liu, Chang; Qi, Xiaojuan; Tan, Siew-Chong; Lam, Edmund; Wong, Ngai
Source: Self-asserted source
Qi Xiaojuan

Data Pruning via Moving-one-Sample-out

Advances in Neural Information Processing Systems (NeurIPS)
2023 | Journal article
Contributors: Tan, Haoru; Wu, Sitong; Du, Fei; Chen, Yukang; Wang, Zhibin; Wang, Fan; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Decoupled Kullback-Leibler Divergence Loss

arXiv preprint arXiv:2305.13948
2023 | Journal article
Contributors: Cui, Jiequan; Tian, Zhuotao; Zhong, Zhisheng; Qi, Xiaojuan; Yu, Bei; Zhang, Hanwang
Source: Self-asserted source
Qi Xiaojuan

DPACS: Hardware Accelerated Dynamic Neural Network Pruning through Algorithm-Architecture Co-design

Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2
2023 | Conference paper
Contributors: Gao, Yizhao; Zhang, Baoheng; Qi, Xiaojuan; So, Hayden Kwok-Hay
Source: Self-asserted source
Qi Xiaojuan

DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation

IEEE Transactions on Pattern Analysis and Machine Intelligence
2023 | Journal article
Contributors: Liu, Zhengzhe; Dai, Peng; Li, Ruihui; Qi, Xiaojuan; Fu, Chi-Wing
Source: Self-asserted source
Qi Xiaojuan

DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation

IEEE Transactions on Pattern Analysis and Machine Intelligence
2023 | Journal article
Contributors: Zhengzhe Liu; Peng Dai; Ruihui Li; Xiaojuan Qi; Chi-Wing Fu
Source: check_circle
Crossref

EMDiffuse: a diffusion-based deep learning method augmenting ultrastructural imaging and volume electron microscopy

bioRxiv
2023 | Journal article
Contributors: Lu, Chixiang; Chen, Kai; Qiu, Heng; Chen, Xiaojun; Chen, Gu; Qi, Xiaojuan; Jiang, Haibo
Source: Self-asserted source
Qi Xiaojuan

High-dimensional anticounterfeiting nanodiamonds authenticated with deep metric learning

2023 | Journal article
Contributors: Wang, Lingzhi; Yu, Xin; Zhang, Tongtong; Hou, Yong; Lei, Dangyuan; Qi, Xiaojuan; Chu, Zhiqin
Source: Self-asserted source
Qi Xiaojuan

Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur

Conference on Computer Vision and Pattern Recognition (CVPR)
2023 | Conference paper
Contributors: Dai, Peng; Zhang, Yinda; Yu, Xin; Lyu, Xiaoyang; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

In-situ model downloading to realize versatile edge AI in 6G mobile networks

IEEE Wireless Communications
2023 | Journal article
Contributors: Huang, Kaibin; Wu, Hai; Liu, Zhiyan; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Is synthetic data from generative models ready for image recognition?

International Conference on Learning Representations (ICLR)
2023 | Conference paper
Contributors: He, Ruifei; Sun, Shuyang; Yu, Xin; Xue, Chuhui; Zhang, Wenqing; Torr, Philip; Bai, Song; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation

International Conference on Learning Representations (ICLR)
2023 | Conference paper
Contributors: Liu, Zhengzhe; Dai, Peng; Li, Ruihui; Qi, Xiaojuan; Fu, Chi-Wing
Source: Self-asserted source
Qi Xiaojuan

LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Chen, Yukang; Liu, Jianhui; Zhang, Xiangyu; Qi, Xiaojuan; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan

Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation

International Conference on Computer Vision (ICCV)
2023 | Conference paper
Contributors: Lyu, Xiaoyang; Dai, Peng; Li, Zizhang; Yan, Dongyu; Lin, Yi; Peng, Yifan; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Learning Context-aware Classifier for Semantic Segmentation

Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI)
2023 | Conference paper
Contributors: Tian, Zhuotao; Cui, Jiequan; Jiang, Li; Qi, Xiaojuan; Lai, Xin; Chen, Yixin; Liu, Shu; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan

Lowis3d: Language-driven open-world instance-level 3d scene understanding

arXiv preprint arXiv:2308.00353
2023 | Journal article
Contributors: Ding, Runyu; Yang, Jihan; Xue, Chuhui; Zhang, Wenqing; Bai, Song; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Liu, Jiahui; Chang, Chirui; Liu, Jianhui; Wu, Xiaoyang; Ma, Lan; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection

Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI)
2023 | Conference paper
Contributors: Chen, Yingxian; Liu, Zhengzhe; Zhang, Baoheng; Fok, Wilton; Qi, Xiaojuan; Wu, Yik-Chung
Source: Self-asserted source
Qi Xiaojuan

One Thing One Click++: Self-Training for Weakly Supervised 3D Scene Understanding

arXiv preprint arXiv:2303.14727
2023 | Journal article
Contributors: Liu, Zhengzhe; Qi, Xiaojuan; Fu, Chi-Wing
Source: Self-asserted source
Qi Xiaojuan

Parametric Classification for Generalized Category Discovery: A Baseline Study

International Conference on Computer Vision (ICCV)
2023 | Conference paper
Contributors: Wen, Xin; Zhao, Bingchen; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Ding, Runyu; Yang, Jihan; Xue, Chuhui; Zhang, Wenqing; Bai, Song; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Prior-free Category-level Pose Estimation with Implicit Space Transformation

International Conference on Computer Vision (ICCV)
2023 | Conference paper
Contributors: Liu, Jianhui; Chen, Yukang; Ye, Xiaoqing; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Regionplc: Regional point-language contrastive learning for open-world 3d scene understanding

arXiv preprint arXiv:2304.00962
2023 | Journal article
Contributors: Yang, Jihan; Ding, Runyu; Wang, Zhe; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

International Conference on Computer Vision (ICCV)
2023 | Conference paper
Contributors: Wu, Xiuzhe; Hu, Pengfei; Wu, Yang; Lyu, Xiaoyang; Cao, Yan-Pei; Shan, Ying; Yang, Wenming; Sun, Zhongqian; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features

arXiv preprint arXiv:2309.16987
2023 | Journal article
Contributors: Wang, Song; Wang, Zhu; Li, Can; Qi, Xiaojuan; So, Hayden Kwok-Hay
Source: Self-asserted source
Qi Xiaojuan

Texture Generation on 3D Meshes with Point-UV Diffusion

International Conference on Computer Vision (ICCV)
2023 | Conference paper
Contributors: Yu, Xin; Dai, Peng; Li, Wenbo; Ma, Lan; Liu, Zhengzhe; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

The liver tumor segmentation benchmark (lits)

Medical Image Analysis
2023 | Journal article
Contributors: Bilic, Patrick; Christ, Patrick; Li, Hongwei Bran; Vorontsov, Eugene; Ben-Cohen, Avi; Kaissis, Georgios; Szeskin, Adi; Jacobs, Colin; Mamani, Gabriel Efrain Humpire; Chartrand, Gabriel et al.
Source: Self-asserted source
Qi Xiaojuan

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

Conference on Computer Vision and Pattern Recognition (CVPR)
2023 | Conference paper
Contributors: Zhong, Zhisheng; Cui, Jiequan; Yang, Yibo; Wu, Xiaoyang; Qi, Xiaojuan; Zhang, Xiangyu; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan

Vertical Layering of Quantized Neural Networks for Heterogeneous Inference

IEEE Transactions on Pattern Analysis and Machine Intelligence
2023 | Journal article
Contributors: Wu, Hai; He, Ruifei; Tan, Haoru; Qi, Xiaojuan; Huang, Kaibin
Source: Self-asserted source
Qi Xiaojuan

Vertical Layering of Quantized Neural Networks for Heterogeneous Inference

IEEE Transactions on Pattern Analysis and Machine Intelligence
2023 | Journal article
Contributors: Hai Wu; Ruifei He; Haoru Tan; Xiaojuan Qi; Kaibin Huang
Source: check_circle
Crossref

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

Conference on Computer Vision and Pattern Recognition (CVPR)
2023 | Conference paper
Contributors: Chen, Yukang; Liu, Jianhui; Zhang, Xiangyu; Qi, Xiaojuan; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan

Model training based on synthetic data

2023-10 | Other
Contributors: Bai, Song; Ruifei, HE; Shuyang, SUN; Yu, Xin; Xue, Chuhui; Zhang, Wenqing; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Open vocabulary 3d scene processing

2023-09 | Other
Contributors: Bai, Song; Ding, Runyu; Yang, Jihan; Xue, Chuhui; Zhang, Wenqing; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

European Conference on Computer Vision (ECCV)
2022 | Conference paper
Contributors: Ding, Runyu; Yang, Jihan; Jiang, Li; Qi, Xiaojuan
Source: Self-asserted source
Qi Xiaojuan

Fast classification and action recognition with event-based imaging

IEEE Access
2022 | Journal article
Contributors: Liu, Chang; Qi, Xiaojuan; Lam, Edmund Y; Wong, Ngai
Source: Self-asserted source
Qi Xiaojuan

Fast Classification and Action Recognition With Event-Based Imaging

IEEE Access
2022 | Journal article
Contributors: Chang Liu; Xiaojuan Qi; Edmund Y. Lam; Ngai Wong
Source: check_circle
Crossref

Fully convolutional networks for panoptic segmentation with point-based supervision

IEEE Transactions on Pattern Recognition and Machine Intelligence (TPAMI)
2022 | Journal article
Contributors: Li, Yanwei; Zhao, Hengshuang; Qi, Xiaojuan; Chen, Yukang; Qi, Lu; Wang, Liwei; Li, Zeming; Sun, Jian; Jia, Jiaya
Source: Self-asserted source
Qi Xiaojuan
Items per page:
Page 1 of 3