Yu-Chiang Frank Wang

Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis

Generating videos with content and motion variations is a challenging ta...
02/26/2021 ∙ by Fu-En Yang, et al. ∙ 0 ∙ share

read it
Deep Representation Decomposition for Feature Disentanglement

Representation disentanglement aims at learning interpretable features, ...
11/02/2020 ∙ by Shang-Fu Chen, et al. ∙ 8 ∙ share

read it
Semantics-Guided Representation Learning with Applications to Visual Synthesis

Learning interpretable and interpolatable latent representations has bee...
10/21/2020 ∙ by Jia-Wei Yan, et al. ∙ 0 ∙ share

read it
Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Aiming at recognizing images of the same person across distinct camera v...
10/19/2020 ∙ by Ci-Siang Lin, et al. ∙ 0 ∙ share

read it
Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification

Person re-identification (re-ID) requires one to match images of the sam...
10/02/2020 ∙ by Chih-Ting Liu, et al. ∙ 0 ∙ share

read it
Learning to Learn in a Semi-Supervised Fashion

To address semi-supervised learning from both labeled and unlabeled data...
08/25/2020 ∙ by Yun-Chun Chen, et al. ∙ 21 ∙ share

read it
Wavelet Channel Attention Module with a Fusion Network for Single Image Deraining

Single image deraining is a crucial problem because rain severely degene...
07/17/2020 ∙ by Hao-Hsiang Yang, et al. ∙ 0 ∙ share

read it
Transforming Multi-Concept Attention into Video Summarization

Video summarization is among challenging tasks in computer vision, which...
06/02/2020 ∙ by Yen-Ting Liu*, et al. ∙ 0 ∙ share

read it
Transfoming Multi-Concept Attention into Video Summarization

Video summarization is among challenging tasks in computer vision, which...
06/02/2020 ∙ by Yen-Ting Liu*, et al. ∙ 0 ∙ share

read it
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

Person re-identification (re-ID) aims at matching images of the same per...
02/19/2020 ∙ by Yu-Jhe Li, et al. ∙ 0 ∙ share

read it
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Person re-identification (re-ID) aims at recognizing the same person fro...
09/20/2019 ∙ by Yu-Jhe Li, et al. ∙ 0 ∙ share

read it
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Person re-identification (re-ID) aims at matching images of the same ide...
08/16/2019 ∙ by Yu-Jhe Li, et al. ∙ 0 ∙ share

read it
Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification

Video-based person re-identification (Re-ID) aims at matching video sequ...
08/05/2019 ∙ by Chih-Ting Liu, et al. ∙ 1 ∙ share

read it
Learning Resolution-Invariant Deep Representations for Person Re-Identification

Person re-identification (re-ID) solves the task of matching images acro...
07/25/2019 ∙ by Yun-Chun Chen, et al. ∙ 4 ∙ share

read it
A Closer Look at Few-shot Classification

Few-shot classification aims to learn a classifier to recognize unseen c...
04/08/2019 ∙ by Wei-Yu Chen, et al. ∙ 8 ∙ share

read it
Dual-modality seq2seq network for audio-visual event localization

Audio-visual event localization requires one to identify theevent which ...
02/20/2019 ∙ by Yan-Bo Lin, et al. ∙ 0 ∙ share

read it
3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency

Aiming at inferring 3D shapes from 2D images, 3D shape reconstruction ha...
11/29/2018 ∙ by Yi-Lun Liao, et al. ∙ 2 ∙ share

read it
A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

We present a novel and unified deep learning framework which is capable ...
09/05/2018 ∙ by Alexander Liu, et al. ∙ 4 ∙ share

read it
Deep Reinforcement Learning for Playing 2.5D Fighting Games

Deep reinforcement learning has shown its success in game playing. Howev...
05/05/2018 ∙ by Yu-Jhe Li, et al. ∙ 0 ∙ share

read it
Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification

Person re-identification (Re-ID) aims at recognizing the same person fro...
04/25/2018 ∙ by Yu-Jhe Li, et al. ∙ 0 ∙ share

read it
For Your Eyes Only: Learning to Summarize First-Person Videos

With the increasing amount of video data, it is desirable to highlight o...
11/24/2017 ∙ by Hsuan-I Ho, et al. ∙ 0 ∙ share

read it
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs

In this paper, we propose a novel deep learning architecture for multi-l...
11/17/2017 ∙ by Chung-Wei Lee, et al. ∙ 0 ∙ share

read it
Order-Free RNN with Visual Attention for Multi-Label Classification

In this paper, we propose the joint learning attention and recurrent neu...
07/18/2017 ∙ by Shang-Fu Chen, et al. ∙ 0 ∙ share

read it
Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

While representation learning aims to derive interpretable features for ...
05/03/2017 ∙ by Yen-Cheng Liu, et al. ∙ 0 ∙ share

read it
No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Despite the recent success of deep-learning based semantic segmentation,...
04/27/2017 ∙ by Yi-Hsin Chen, et al. ∙ 0 ∙ share

read it

Yu-Chiang Frank Wang

Featured Co-authors

Jia-Bin Huang

Min Sun

Zsolt Kira

Chao-Han Huck Yang

Yen-Yu Lin

Wei-Chen Chiu

Shao-Yi Chien

Yu-Jhe Li

Yu-Ting Chen

Yun-Chun Chen

Yen-Cheng Liu

Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis

Deep Representation Decomposition for Feature Disentanglement

Semantics-Guided Representation Learning with Applications to Visual Synthesis

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification

Learning to Learn in a Semi-Supervised Fashion

Wavelet Channel Attention Module with a Fusion Network for Single Image Deraining

Transforming Multi-Concept Attention into Video Summarization

Transfoming Multi-Concept Attention into Video Summarization

Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification

Learning Resolution-Invariant Deep Representations for Person Re-Identification

A Closer Look at Few-shot Classification

Dual-modality seq2seq network for audio-visual event localization

3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Deep Reinforcement Learning for Playing 2.5D Fighting Games

Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification

For Your Eyes Only: Learning to Summarize First-Person Videos

Multi-Label Zero-Shot Learning with Structured Knowledge Graphs

Order-Free RNN with Visual Attention for Multi-Label Classification

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

No More Discrimination: Cross City Adaptation of Road Scene Segmenters