scispace - formally typeset
Y

Yongyi Lu

Researcher at Johns Hopkins University

Publications -  31
Citations -  1079

Yongyi Lu is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 12, co-authored 27 publications receiving 757 citations. Previous affiliations of Yongyi Lu include Sun Yat-sen University & Hong Kong University of Science and Technology.

Papers
More filters
Book ChapterDOI

Attribute-Guided Face Generation Using Conditional CycleGAN

TL;DR: This work condition the CycleGAN and proposes conditional CycleGAN, which is designed to handle unpaired training data because the training low/high-res and high-res attribute images may not necessarily align with each other, and to allow easy control of the appearance of the generated face via the input attributes.
Posted Content

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TL;DR: TransUNet as mentioned in this paper combines Transformers and U-Net to enhance finer details by recovering localized spatial information for medical image segmentation, which achieves superior performances to various competing methods on different medical applications including multi-organ segmentation and cardiac segmentation.
Book ChapterDOI

Image Generation from Sketch Constraint Using Contextual GAN

TL;DR: This paper addresses image generation guided by hand sketch using a novel joint image completion approach, where the sketch provides the image context for completing, or generating the output image, using a generated adversarial network.
Proceedings ArticleDOI

Online Video Object Detection Using Association LSTM

TL;DR: Compared to the traditional video object detection methods, the association LSTM approach outperforms them on standard video datasets and works in an online manner, which is important for most video tasks.
Posted Content

Conditional CycleGAN for Attribute Guided Face Image Generation

TL;DR: This work extends the cycleGAN to Conditional cycleGAN such that the mapping from X to Y is subjected to attribute condition Z, and uses face feature vector extracted from face verification network as Z to demonstrate the efficacy of this approach on identity preserving face image super-resolution.