Hung-Yu Tseng

Publications
Influence

Diverse Image-to-Image Translation via Disentangled Representations

Hsin-Ying Lee, Hung-Yu Tseng, Jia-Bin Huang, Maneesh Kumar Singh, Ming-Hsuan Yang
Computer Science
ECCV
2 August 2018

We present an approach based on disentangled representation for producing diverse outputs without paired training images. Expand

Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

Qi Mao, Hsin-Ying Lee, Hung-Yu Tseng, S. Ma, Ming-Hsuan Yang
Computer Science
IEEE/CVF Conference on Computer Vision and…
13 March 2019

We propose a simple yet effective regularization term that can be applied to cGANs for various tasks to alleviate the mode collapse problem. Expand

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, Ming-Hsuan Yang
Computer Science
ICLR
23 January 2020

We use feature-wise transformation layers for augmenting the image features using affine transforms to simulate various feature distributions under different domains in the training stage. Expand

Progressive Domain Adaptation for Object Detection

Han-Kai Hsu, Wei-Chih Hung, +4 authors Ming-Hsuan Yang
Computer Science
IEEE Winter Conference on Applications of…
24 October 2019

In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. Expand

[POSTER] A Benchmark Dataset for 6DoF Object Pose Tracking

Po-Chen Wu, Yueh-Ying Lee, Hung-Yu Tseng, Hsuan-I Ho, Ming-Hsuan Yang, S. Chien
Computer Science
IEEE International Symposium on Mixed and…
1 October 2017

We present a large object pose tracking benchmark dataset consisting of RGB-D video sequences of 2D and 3D targets with ground-truth information. Expand

LEaD: Utilizing Light Movement as Peripheral Visual Guidance for Scooter Navigation

Hung-Yu Tseng, Rong-Hao Liang, Li-Wei Chan, B. Chen
Computer Science
MobileHCI
24 August 2015

This work presents LEaD, a helmet-based visual guidance system utilizing light movement in scooter drivers' peripheral vision for turn-by-turn navigation. Expand

Few-Shot Viewpoint Estimation

Hung-Yu Tseng, Shalini De Mello, +4 authors J. Kautz
Computer Science
BMVC
1 May 2019

We introduce the problem of category-level few-shot viewpoint estimation, in which a few (10 or less) labeled training examples are used to train a viewpoint estimation network for each novel category. Expand

GaussBricks: magnetic building blocks for constructive tangible interactions on portable displays

Rong-Hao Liang, Li-Wei Chan, +4 authors B. Chen
Computer Science
CHI
26 April 2014

This work describes a novel building block system for tangible interaction design, GaussBricks, which enables real-time constructive tangible interactions on portable displays. Expand

Fabrication of surface metal nanoparticles and their induced surface plasmon coupling with subsurface InGaN/GaN quantum wells.

Che-Wei Huang, Hung-Yu Tseng, +8 authors C. Yang
Materials Science, Medicine
Nanotechnology
25 November 2011

Based on the fabrication of Ag nanoparticles (NPs) with controlled geometry and surface density on an InGaN/GaN quantum well (QW) epitaxial structure, which contains indium-rich nano-clusters for… Expand

Au nanorings for enhancing absorption and backscattering monitored with optical coherence tomography.

Hung-Yu Tseng, Cheng-Kuang Lee, +9 authors C. Chiang
Materials Science, Medicine
Nanotechnology
23 July 2010

Preparation of a high-concentration Au nanoring (NR) water solution and its applications to the enhancement of image contrast in optical coherence tomography (OCT) and the generation of the… Expand

Recommended Authors