Hwann-Tzong Chen

is this you? claim profile

0 followers
Google ∙ National Tsing Hua University

HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

We present HoHoNet, a versatile and efficient framework for holistic und...
11/23/2020 ∙ by Cheng Sun, et al. ∙ 2 ∙ share

read it
Learning Camera-Aware Noise Models

Modeling imaging sensor noise is a fundamental problem for image process...
08/21/2020 ∙ by Ke-Chi Chang, et al. ∙ 3 ∙ share

read it
Learning Gaussian Instance Segmentation in Point Clouds

This paper presents a novel method for instance segmentation of 3D point...
07/20/2020 ∙ by Shih-Hung Liu, et al. ∙ 0 ∙ share

read it
Silhouette-Net: 3D Hand Pose Estimation from Silhouettes

3D hand pose estimation has received a lot of attention for its wide ran...
12/28/2019 ∙ by Kuo-Wei Lee, et al. ∙ 36 ∙ share

read it
One-Shot Object Detection with Co-Attention and Co-Excitation

This paper aims to tackle the challenging problem of one-shot object det...
11/28/2019 ∙ by Ting-I Hsieh, et al. ∙ 15 ∙ share

read it
Flat2Layout: Flat Representation for Estimating Layout of General Room Types

This paper proposes a new approach, Flat2Layout, for estimating general ...
05/29/2019 ∙ by Chi-Wei Hsiao, et al. ∙ 1 ∙ share

read it
Instance-Level Meta Normalization

This paper presents a normalization mechanism called Instance-Level Meta...
04/06/2019 ∙ by Songhao Jia, et al. ∙ 0 ∙ share

read it
C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning

This paper describes a channel-selection approach for simplifying deep n...
04/06/2019 ∙ by Chih-Yao Chiu, et al. ∙ 0 ∙ share

read it
Point-to-Point Video Generation

While image manipulation achieves tremendous breakthroughs (e.g., genera...
04/05/2019 ∙ by Tsun-Hsuan Wang, et al. ∙ 0 ∙ share

read it
COCO-GAN: Generation by Parts via Conditional Coordinating

Humans can only interact with part of the surrounding environment due to...
03/30/2019 ∙ by Chieh Hubert Lin, et al. ∙ 0 ∙ share

read it
Bridging the Gap Between Computational Photography and Visual Recognition

What is the current state-of-the-art for image restoration and enhanceme...
01/28/2019 ∙ by Rosaura G. VidalMata, et al. ∙ 0 ∙ share

read it
HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation

We present a new approach to the problem of estimating 3D room layout fr...
01/12/2019 ∙ by Cheng Sun, et al. ∙ 9 ∙ share

read it
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects

This paper presents a "learning to learn" approach to figure-ground imag...
12/20/2018 ∙ by Ding-Jie Chen, et al. ∙ 14 ∙ share

read it
SwipeCut: Interactive Segmentation with Diversified Seed Proposals

Interactive image segmentation algorithms rely on the user to provide an...
12/18/2018 ∙ by Ding-Jie Chen, et al. ∙ 12 ∙ share

read it
Non-local RoI for Cross-Object Perception

We present a generic and flexible module that encodes region proposals b...
11/25/2018 ∙ by Shou-Yao Roy Tseng, et al. ∙ 0 ∙ share

read it
Escaping from Collapsing Modes in a Constrained Space

Generative adversarial networks (GANs) often suffer from unpredictable m...
08/22/2018 ∙ by Chia-Che Chang, et al. ∙ 0 ∙ share

read it
Non-local RoIs for Instance Segmentation

We introduce the concept of Non-Local RoI (NL-RoI) Block as a generic an...
07/14/2018 ∙ by Shou-Yao Roy Tseng, et al. ∙ 0 ∙ share

read it
Self Adversarial Training for Human Pose Estimation

This paper presents a deep learning based approach to the problem of hum...
07/08/2017 ∙ by Chia-Jung Chou, et al. ∙ 0 ∙ share

read it
Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study

Automatic photo cropping is an important tool for improving visual quali...
01/05/2017 ∙ by Yi-Ling Chen, et al. ∙ 0 ∙ share

read it

Hwann-Tzong Chen

Featured Co-authors

Zhangyang Wang

Wei Wei

Jiaying Liu

Min Sun

Wenhan Yang

Ye Yuan

Da-Cheng Juan

Walter J. Scheirer

Tyng-Luh Liu

Bing-Yu Chen

Ren Wang

HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

Learning Camera-Aware Noise Models

Learning Gaussian Instance Segmentation in Point Clouds

Silhouette-Net: 3D Hand Pose Estimation from Silhouettes

One-Shot Object Detection with Co-Attention and Co-Excitation

Flat2Layout: Flat Representation for Estimating Layout of General Room Types

Instance-Level Meta Normalization

C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning

Point-to-Point Video Generation

COCO-GAN: Generation by Parts via Conditional Coordinating

Bridging the Gap Between Computational Photography and Visual Recognition

HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation

Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects

SwipeCut: Interactive Segmentation with Diversified Seed Proposals

Non-local RoI for Cross-Object Perception

Escaping from Collapsing Modes in a Constrained Space

Non-local RoIs for Instance Segmentation

Self Adversarial Training for Human Pose Estimation

Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study