Home /  About Me /  People /  Research


Preprint
  1. Self-supervised Video Object Segmentation by Motion Grouping.
    Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie
    Project Page | Arxiv

    Summary: we propose a self-supervised learning approach for motion segmentation, i.e. foreground object vs. background, which achieves comparable performance as those trained with strong supervision on several popular benchmarks, e.g. DAVIS2016, MoCA (camouflage detection).

  2. All You Need Are a Few Pixels: Semantic Segmentation with PixelPick.
    Gyungin Shin, Weidi Xie, Samuel Albanie
    Project Page | Arxiv

    Summary: we investigate efficient annotation for semantic segmentation, and show that, with active learning, only sparse pixel annotation is required to achieve satisfactory results.

  3. Quantum Self-supervised Learning.
    Ben Jaderberg, Lewis W. Anderson, Weidi Xie, Samuel Albanie, Martin Kiffner, Dieter Jaksch
    Code | Arxiv

    Summary: to open up the concept of QNNs for self-supervised learning for computer vision task, lots of work remains to be done, to further show its scalability on real devices.

  4. NeRF--: Neural Radiance Fields Without Known Camera Parameters.
    Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, Victor Adrian Prisacariu
    Project Page | Arxiv

    Summary: we show the possibility of jointly optimizing camera parameters and neural radiance fields.
2021
  1. Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning.
    Pak Hei Yeung, Ana I.L. Namburete, Weidi Xie
    In: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021.
    Project Page | Arxiv

    Summary: Self-supervised training on raw 3D volumes, which enables to propagate a single-slice annotation to the whole 3D volume, for any structures across different modalities.

  2. Self-supervised Video Object Segmentation by Motion Grouping (Short Version).
    Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie
    In: Conference on Computer Vision and Pattern Recognition (CVPR), RVSU Workshop , 2021.   (Best Paper Award)
    Project Page | Arxiv

    Summary: we propose a self-supervised learning approach for motion segmentation, i.e. foreground object vs. background, which achieves comparable performance as those trained with strong supervision on several popular benchmarks, e.g. DAVIS2016, MoCA (camouflage detection).

  3. Localizing Visual Sounds the Hard Way.
    Honglie Chen, Weidi Xie, Triantafyllos Afouras, Arsha Nagrani, Andrea Vedaldi, Andrew Zisserman
    In: Conference on Computer Vision and Pattern Recognition (CVPR), 2021
    Project Page | Arxiv
  4. Learning to Map 2D Ultrasound Images into 3D Space with Minimal Human Annotation.
    Pak-Hei Yeung, Moska Aliasi, Aris T. Papageorghiou, Monique Haak, Weidi Xie, Ana I.L. Namburete.
    In: Medical Image Analysis, February 2021. (Impact Factor: ~11)
    Paper
2020
  1. VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge.
    Arsha Nagrani, Joon Son Chung, Jaesung Huh, Andrew Brown, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, Andrew Zisserman.
    Tech Report
  2. Self-supervised Co-training for Video Representation Learning.
    Tengda Han, Weidi Xie, Andrew Zisserman
    In: Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) , 2020.
    Arxiv | Project Page | Code & Model
  3. Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation.
    Hala Lamdouar, Charig Yang, Weidi Xie, Andrew Zisserman
    In: Asian Conference on Computer Vision (ACCV), 2020.
    Arxiv | PDF | Project Page
  4. Layered Neural Rendering for Retiming People in Video.
    Erika Lu, Forrester Cole, Tali Dekel, Weidi Xie, Andrew Zisserman, David Salesin, William T. Freeman, Michael Rubinstein
    In: ACM Transactions on Graphics (TOG). Proc. SIGGRAPH Asia , 2020
    Arxiv | Project Page
  5. Inducing Predictive Uncertainty Estimation for Face Recognition.
    Weidi Xie, Jeffrey Byrne, Andrew Zisserman
    In: British Machine Vision Conference (BMVC) , 2020
    Arxiv | PDF
  6. Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval.
    Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman
    In: European Conference on Computer Vision (ECCV) , 2020
    Arxiv | Project Page | Code & Model
  7. Memory-augmented Dense Predictive Coding for Video Representation Learning.
    Tengda Han, Weidi Xie, Andrew Zisserman
    In: European Conference on Computer Vision (ECCV) , 2020   (Spotlight Presentation)
    Arxiv | Project Page | Code & Model
  8. MAST: A Memory-Augmented Self-Supervised Tracker.
    Zihang Lai, Erika Lu, Weidi Xie
    In: Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    Arxiv | Project Page | Code & Model
  9. VGG-Sound: A Large-Scale Audio-Visual Dataset.
    Honglie Chen, Weidi Xie, Andrea Vedaldi, Andrew Zisserman
    In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020
    Arxiv | PDF | Project Page | Code & Model
  10. Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment.
    Sagar Vaze, Weidi Xie, Ana Namburete.
    In: IEEE Journal of Biomedical and Health Informatics, 2020. (Impact Factor: ~4.2)
    Project Page | Code
  11. VoxCeleb: Large-scale Speaker Verification in the Wild.
    Arsha Nagrani*, Joon Son Chung*, Weidi Xie*, Andrew Zisserman. (* indicates equal contribution)
    In: Computer Speech & Language, 2020. (Impact Factor: ~1.8)
2019
  1. VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge.
    Joon Son Chung, Arsha Nagrani, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, Andrew Zisserman.
    Tech Report
  2. Video Representation Learning by Dense Predictive Coding.
    Tengda Han, Weidi Xie, Andrew Zisserman
    In: 1st International Workshop on Large-scale Holistic Video Understanding, ICCV, 2019.   (Oral Presentation)
    Arxiv | Project Page | Code
  3. Self-supervised Learning for Video Correspondence Flow.
    Zihang Lai, Weidi Xie
    In: British Machine Vision Conference (BMVC), 2019.   (Oral Presentation)
    Arxiv | Project Page
  4. AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations.
    Honglie Chen, Weidi Xie, Andrea Vedaldi, Andrew Zisserman.
    In: British Machine Vision Conference (BMVC), 2019.   (Spotlight Presentation)
    Arxiv | PDF
  5. Geometry-Aware Corner Network for Video Object Detection from Static Cameras.
    Dan Xu, Weidi Xie, Andrew Zisserman.
    In: British Machine Vision Conference (BMVC), 2019.   (Oral Presentation)
    Arxiv | PDF
  6. Utterance-level Aggregation for Speaker Recognition in the Wild.
    Weidi Xie, Arsha Nagrani, Joon Son Chung, Andrew Zisserman.
    In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.   (Oral Presentation)
    Arxiv | Project Page | Code & Model
2018
  1. Comparator Networks.
    Weidi Xie, Li Shen, Andrew Zisserman
    In: European Conference on Computer Vision (ECCV), 2018.
    Arxiv | PDF
  2. Multicolumn Networks on Face Recognition.
    Weidi Xie, Andrew Zisserman
    In: British Machine Vision Conference (BMVC), 2018.
    Arxiv | PDF | Code & Model | Bibtex
  3. Class-Agnostic Counting.
    Erika Lu, Weidi Xie, Andrew Zisserman
    In: Asian Conference on Computer Vision (ACCV), 2018.
    Arxiv | Project Page | Bibtex
  4. VGGFace2: A Dataset for Recognising Faces Across Pose and Age.
    Qiong Cao, Li Shen, Weidi Xie, Omkar M. Parkhi and Andrew Zisserman
    In: IEEE International Conference on Automatic Face and Gesture Recognition (F&G), 2018.   (Oral Presentation)
    Arxiv | PDF | Project Page | Bibtex
  5. Omega-Net: Fully Automatic, Multi-View Cardiac MR Detection, Orientation, and Segmentation with Deep Neural Networks.
    Weidi Xie*, Davis M. Vigneault*, Carolyn Y. Ho, David A. Bluemke and J. Alison Noble (*joint first author)
    In: Medical Image Analysis, Volume 48, Pages 95, August 2018. (Impact Factor: ~11)
    Arxiv | Paper
  6. VP-Nets: Efficient Automatic Localization of Key Brain Structures in 3D Fetal Neurosonography.
    Ruobing Huang, Weidi Xie and J. Alison Noble
    In: Medical Image Analysis, Volume 47, Pages 127, July 2018. (Impact Factor: ~11)
    Paper
  7. Fully-Automated Alignment of 3D Fetal Brain Ultrasound to a Canonical Reference Space Using Multi-task Learning.
    Weidi Xie*, Ana I.L. Namburete*, Mohammad Yaqub, Andrew Zisserman and J. Alison Noble (*joint first author)
    In: Medical Image Analysis, Volume 46, Pages 1, May 2018. (Impact Factor: ~11)
    Paper
2017
  1. Feature Tracking Cardiac Magnetic Resonance via Deep Learning and Spline Optimization.
    Davis M. Vigneaulta, Weidi Xie, David A. Bluemke and J. Alison Noble
    In: Functional Imaging and Modelling of the Heart (FIMH), 2017.   (Best Poster Award)
    Arxiv | Paper
  2. Robust Regression of Brain Maturation from 3D Fetal Neurosonography using CRNs.
    Ana I.L. Namburete, Weidi Xie and J. Alison Noble
    In: MICCAI Workshop on Fetal and InFant Image analysis (FIFI), 2017.   (Best Paper Award)
    Paper
2016
  1. Microscopy Cell Counting and Detection with Fully Convolutional Regression Networks.
    Weidi Xie, J. Alison Noble and Andrew Zisserman
    In: MICCAI 1st Deep Learning Workshop, 2015.
    In: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2016.   (Biannual Best Journal Article)
    Paper | Code | Award

Based on a template by Jon Barron