W
Weidi Xie
Researcher at University of Oxford
Publications - 107
Citations - 6398
Weidi Xie is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 22, co-authored 65 publications receiving 3588 citations.
Papers
More filters
Proceedings ArticleDOI
Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
TL;DR: The proposed framework learns strong multi-modal representations that are beneficial to sound localisation and generalization to further applications, and systematically investigates the effects of data augmentations to understand what enables to learn useful representations.
Book ChapterDOI
Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-supervised Learning
TL;DR: In this article, a self-supervised slice registration method is proposed to segment any arbitrary structures of interest (SOI) in 3D volumes by only annotating a single slice.
Posted Content
VGGSound: A Large-scale Audio-Visual Dataset
TL;DR: The VGGSound dataset as mentioned in this paper is a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques, which can be used for training and evaluating audio recognition models.
Journal ArticleDOI
OvarNet: Towards Open-vocabulary Object Attribute Recognition
TL;DR: Zhang et al. as discussed by the authors proposed a two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes.
Journal ArticleDOI
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
TL;DR: In this paper , a generative-based model for medical visual understanding was proposed by aligning visual information from a pre-trained vision encoder with a large language model, which is crucial in efficiently interpreting medical images with vital clinic-relevant information.