Wei-Chen (Walon) Chiu's Website (original) (raw)

Publications

teaser figure

Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution

[WACV 2025 (BibTeX)]

@inproceedings{lu2025wacv,
title = {Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution},
author = {Shao-Hao Lu and Ren Wang and Ching-Chun Huang and Wei-Chen Chiu},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
year = {2025}
}

teaser figure

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition

Chen Yeh*,You-Ming Chang*,Wei-Chen Chiu,Ning Yu

(* indicates equal contribution.)

[NeurIPS 2024 Datasets and Benchmarks Track (BibTeX)] [ArXiv 2024] [Project Page]

@inproceedings{yeh2024neurips,
title = {T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition},
author = {Chen Yeh and You-Ming Chang and Wei-Chen Chiu and Ning Yu},
booktitle = {Annual Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track},
year = {2024}
}

teaser figure

A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting

Tsung-Han Chou,Brian Wang,Wei-Chen Chiu,Jun-Cheng Chen

[ACCV 2024 (BibTeX)] [Project Page]

@inproceedings{chou2024accv,
title = {A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting},
author = {Tsung-Han Chou and Brian Wang and Wei-Chen Chiu and Jun-Cheng Chen},
booktitle = {Asian Conference on Computer Vision (ACCV)},
year = {2024}
}

teaser figure

Best of Both Sides: Integration of Absolute and Relative Depth Sensing Modalities Based on iToF and RGB Cameras

I-Sheng Fang,Wei-Chen Chiu,Yong-Sheng Chen

[ICPR 2024 (BibTeX)] [Supplementary Materials] [Source Code]

@inproceedings{fang2024icpr,
title = {Best of Both Sides: Integration of Absolute and Relative Depth Sensing Modalities Based on iToF and RGB Cameras},
author = {I-Sheng Fang and Wei-Chen Chiu and Yong-Sheng Chen},
booktitle = {International Conference on Pattern Recognition (ICPR)},
year = {2024}
}

teaser figure

Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow

Sheng-Chi Huang andWei-Chen Chiu

[IROS 2024 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{huang2024iros,
title = {Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow},
author = {Sheng-Chi Huang and Wei-Chen Chiu},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2024}
}

teaser figure

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

Zhi-Yi Chin*, Chieh-Ming Jiang*,Ching-Chun Huang,Pin-Yu Chen,Wei-Chen Chiu

(* indicates equal contribution.)

[ICML 2024 (BibTeX)] [ArXiv 2023] [Project Page]

@inproceedings{chin2024icml,
title = {Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts},
author = {Zhi-Yi Chin and Chieh-Ming Jiang and Ching-Chun Huang and Pin-Yu Chen and Wei-Chen Chiu},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2024}
}

teaser figure

MCPNet:An Interpretable Classifier via Multi-Level Concept Prototypes

Bor-Shiun Wang,Chien-Yi Wang,Wei-Chen Chiu

[CVPR 2024 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{wang2024cvpr,
title = {MCPNet:An Interpretable Classifier via Multi-Level Concept Prototypes},
author = {Bor-Shiun Wang and Chien-Yi Wang and Wei-Chen Chiu},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2024}
}

teaser figure

teaser figure

Best of Both Worlds: Learning Arbitrary-scale Blind Super-Resolution via Dual Degradation Representations and Cycle-Consistency

Shao-Yu Weng,Hsuan Yuan,Yu-Syuan Xu,Ching-Chun Huang,Wei-Chen Chiu

[WACV 2024 (BibTeX)] [Project Page] [Supplementary Materials] [Presentation Video]

@inproceedings{weng2024wacv,
title = {Best of Both Worlds: Learning Arbitrary-scale Blind Super-Resolution via Dual Degradation Representations and Cycle-Consistency},
author = {Shao-Yu Weng and Hsuan Yuan and Yu-Syuan Xu and Ching-Chun Huang and Wei-Chen Chiu},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
year = {2024}
}

teaser figure

Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where

Zhi-Yi Chin*,Chieh-Ming Jiang*,Ching-Chun Huang,Pin-Yu Chen,Wei-Chen Chiu

(* indicates equal contribution.)

[WACV 2024 (BibTeX)] [Project Page] [Supplementary Materials] [Presentation Video]

@inproceedings{ching2024wacv,
title = {Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where},
author = {Zhi-Yi Chin and Chieh-Ming Jiang and Ching-Chun Huang and Pin-Yu Chen and Wei-Chen Chiu},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
year = {2024}
}

teaser figure

TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception

Yi-Hsin Chen,Ying-Chieh Weng,Chia-Hao Kao,Cheng Chien,Wei-Chen Chiu,Wen-Hsiao Peng

[ICCV 2023 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{chen2023iccv,
title = {TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception},
author = {Yi-Hsin Chen and Ying-Chieh Weng and Chia-Hao Kao and Cheng Chien and Wei-Chen Chiu and Wen-Hsiao Peng},
booktitle = {IEEE International Conference on Computer Vision (ICCV)},
year = {2023}
}

teaser figure

MENTOR: Multilingual tExt detectioN TOward leaRning by analogy

Hsin-Ju Lin,Tsu-Chun Chung,Ching-Chun Hsiao,Pin-Yu Chen,Wei-Chen Chiu,Ching-Chun Huang

[IROS 2023 (BibTeX)] [Supplementary Video]

@inproceedings{lin2023iros,
title = {MENTOR: Multilingual tExt detectioN TOward leaRning by analogy},
author = {Hsin-Ju Lin and Tsu-Chun Chung and Ching-Chun Hsiao and Pin-Yu Chen and Wei-Chen Chiu and Ching-Chun Huang},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2023}
}

teaser figure

Transformer-based Variable-rate Image Compression with Region-of-interest Control

Chia-Hao Kao*,Ying-Chieh Weng*,Yi-Hsin Chen,Wei-Chen Chiu,Wen-Hsiao Peng

(* indicates equal contribution.)

[ICIP 2023 (BibTeX)] [Project Page]

@inproceedings{kao2023icip,
title = {Transformer-based Variable-rate Image Compression with Region-of-interest Control},
author = {Chia-Hao Kao and Ying-Chieh Weng and Yi-Hsin Chen and Wei-Chen Chiu and Wen-Hsiao Peng},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
year = {2023}
}

teaser figure

Mitigating Forgetting in Continual Learning Via Contrasting Semantically Distinct Augmentations

Sheng-Feng Yu and Wei-Chen Chiu

[SMC 2023 (BibTeX)]

@inproceedings{yu2023smc,
title = {Mitigating Forgetting in Continual Learning Via Contrasting Semantically Distinct Augmentations},
author = {Sheng-Feng Yu and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
year = {2023}
}

teaser figure

Continually-Adapted Margin and Multi-Anchor Distillation for Class-Incremental Learning

Yi-Hsin Chen*,Dian-Shan Chen*,Ying-Chieh Weng,Wen-Hsiao Peng,Wei-Chen Chiu

(* indicates equal contribution.)

[SMC 2023 (BibTeX)]

@inproceedings{chen2023smc,
title = {Continually-Adapted Margin and Multi-Anchor Distillation for Class-Incremental Learning},
author = {Yi-Hsin Chen and Dian-Shan Chen and Ying-Chieh Weng and Wen-Hsiao Peng and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
year = {2023}
}

teaser figure

Data Efficient Incremental Learning Via Attentive Knowledge Replay

Yi-Lun Lee,Dian-Shan Chen,Chen-Yu Lee,Yi-Hsuan Tsai,Wei-Chen Chiu

[SMC 2023 (BibTeX)]

@inproceedings{lee2023smc,
title = {Data Efficient Incremental Learning Via Attentive Knowledge Replay},
author = {Yi-Lun Lee and Dian-Shan Chen and Chen-Yu Lee and Yi-Hsuan Tsai and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
year = {2023}
}

teaser figure

Multimodal Prompting with Missing Modalities for Visual Recognition

Yi-Lun Lee,Yi-Hsuan Tsai,Wei-Chen Chiu,Chen-Yu Lee

[CVPR 2023 (BibTeX)] [ArXiv 2023] [Project Page] [Supplementary Materials]

@inproceedings{lee2023cvpr,
title = {Multimodal Prompting with Missing Modalities for Visual Recognition},
author = {Yi-Lun Lee and Yi-Hsuan Tsai and Wei-Chen Chiu and Chen-Yu Lee},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2023}
}

teaser figure

Decontamination Transformer for Blind Image Inpainting

Chun-Yi Li,Yen-Yu Lin,Wei-Chen Chiu

[ICASSP 2023 (BibTeX)] [Project Page]

@inproceedings{li2023icassp,
title = {Decontamination Transformer for Blind Image Inpainting},
author = {Chun-Yi Li and Yen-Yu Lin and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2023}
}

teaser figure

Are You Killing Time? Predicting Smartphone Users’ Time-killing Moments via Fusion of Smartphone Sensor Data and Screenshots

Yu-Chun Chen*,Yu-Jen Lee*,Kuei-Chun Kao,Jie Tsai,En-Chi Liang,Wei-Chen Chiu,Faye Shih,Yung-Ju Chang

(* indicates equal contribution.)

[CHI 2023 (BibTeX)]

@inproceedings{lesley2023chi,
title = {Are You Killing Time? Predicting Smartphone Users’ Time-killing Moments via Fusion of Smartphone Sensor Data and Screenshots},
author = {Yu-Chun Chen and Yu-Jen Lee and Kuei-Chun Kao and Jie Tsai and En-Chi Liang and Wei-Chen Chiu and Faye Shih and Yung-Ju Chang},
booktitle = {ACM SIGCHI Conference on Human Factors in Computing Systems (CHI)},
year = {2023}
}

teaser figure

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis

Yu-Hsuan Li*,Tzu-Yin Chao*,Ching-Chun Huang,Pin-Yu Chen,Wei-Chen Chiu

(* indicates equal contribution.)

[NeurIPS 2022 (BibTeX)] [ArXiv 2021] [Project Page]

@inproceedings{li2022nips,
title = {Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis},
author = {Yu-Hsuan Li and Tzu-Yin Chao and Ching-Chun Huang and Pin-Yu Chen and Wei-Chen Chiu},
booktitle = {Annual Conference on Neural Information Processing Systems (NeurIPS)},
year = {2022}
}

teaser figure

teaser figure

Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model

Shin-I Cheng*,Yu-Jie Chen*,Wei-Chen Chiu,Hung-Yu Tseng,Hsin-Ying Lee

(* indicates equal contribution.)

[WACV 2023 (BibTeX)] [ArXiv 2022] [Project Page] [Supplementary Materials]

@inproceedings{cheng2023wacv,
title = {Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model},
author = {Shin-I Cheng and Yu-Jie Chen and Wei-Chen Chiu and Hung-Yu Tseng and Hsin-Ying Lee},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
year = {2023}
}

teaser figure

teaser figure

teaser figure

teaser figure

Improving Single-View Mesh Reconstruction for Unseen Categories via Primitive-Based Representation and Mesh Augmentation

Yu-Liang Kuo,Wei-Jan Ko,Chen-Yi Chiu,Wei-Chen Chiu

[IROS 2022 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{kuo2022iros,
title = {Improving Single-View Mesh Reconstruction for Unseen Categories via Primitive-Based Representation and Mesh Augmentation},
author = {Yu-Liang Kuo and Wei-Jan Ko and Chen-Yi Chiu and Wei-Chen Chiu},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2022}
}

teaser figure

Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement

Meng-Shiun Tsai*,Pei-Ze Chiang*,Yi-Hsuan Tsai,Wei-Chen Chiu

(* indicates equal contribution.)

[IROS 2022 (BibTeX)] [ArXiv 2022] [Project Page] [Supplementary Materials]

@inproceedings{tsai2022iros,
title = {Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement},
author = {Meng-Shiun Tsai and Pei-Ze Chiang and Yi-Hsuan Tsai and Wei-Chen Chiu},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2022}
}

teaser figure

Find the Way Back: Invertible Kernel Estimator for Blind Image Super-Resolution

Ting-Wei Chang,Wei-Chen Chiu,Ching-Chun Huang

[ICASSP 2022 (BibTeX)] [Project Page]

@inproceedings{chang2022icassp,
title = {Find the Way Back: Invertible Kernel Estimator for Blind Image Super-Resolution},
author = {Ting-Wei Chang and Wei-Chen Chiu and Ching-Chun Huang},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2022}
}

teaser figure

MAML is a Noisy Contrastive Learner in Classification

Chia-Hsiang Kao,Wei-Chen Chiu,Pin-Yu Chen

[ICLR 2022 (BibTeX)] [ArXiv 2021] [Project Page]

@inproceedings{kao2022iclr,
title = {MAML is a Noisy Contrastive Learner in Classification},
author = {Chia-Hsiang Kao and Wei-Chen Chiu and Pin-Yu Chen},
booktitle = {International Conference on Learning Representations (ICLR)},
year = {2022}
}

teaser figure

teaser figure

teaser figure

Learning Facial Representations from the Cycle-consistency of Face

Jia-Ren Chang,Yong-Sheng Chen,Wei-Chen Chiu

[ICCV 2021 (BibTeX)] [ArXiv 2021] [Project Page] [Supplementary Materials]

@inproceedings{chang2021iccv,
title = {Learning Facial Representations from the Cycle-consistency of Face},
author = {Jia-Ren Chang and Yong-Sheng Chen and Wei-Chen Chiu},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2021}
}

teaser figure

teaser figure

Killing-Time Detection from Smartphone Screenshots

Yu-Chun Chen*,Keui-Chun Kao*,Yu-Jen Lee,Faye Shih,Wei-Chen Chiu,Yung-Ju Chang

(* indicates equal contribution.)

[UbiComp/ISWC 2021 Posters and Demos (BibTeX)] [Poster]

@inproceedings{chen2021ubicomp_poster,
title = {UKilling-Time Detection from Smartphone Screenshots},
author = {Yu-Chun Chen and Keui-Chun Kao and Yu-Jen Lee and Faye Shih and Wei-Chen Chiu and Yung-Ju Chang},
booktitle = {Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (UbiComp-ISWC)},
year = {2021}
}

teaser figure

Boosting Semi-Supervised Anomaly Detection via Contrasting Synthetic Images

Sheng-Feng Yu,Wei-Chen Chiu

[MVA 2021 (BibTeX)] [Supplementary Materials] [Presentation Video]
(Best Paper Award)

@inproceedings{yu2021mva,
title = {Boosting Semi-Supervised Anomaly Detection via Contrasting Synthetic Images},
author = {Sheng-Feng Yu and Wei-Chen Chiu},
booktitle = {International Conference on Machine Vision Applications (MVA)},
year = {2021}
}

teaser figure

Inverse Halftone Colorization: Making Halftone Prints Color Photos

Yu-Ting Yen,Chia-Chi Cheng,Wei-Chen Chiu

[ICIP 2021 (BibTeX)] [Supplementary Materials] [Presentation Video]

@inproceedings{yen2021icip,
title = {Inverse Halftone Colorization: Making Halftone Prints Color Photos},
author = {Yu-Ting Yen and Chia-Chi Cheng and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
year = {2021}
}

teaser figure

Demystifying T1-MRI to FDG18-PET Image Translation via Representational Similarity

Chia-Hsiang Kao,Yong-Sheng Chen,Li-Fen Chen,Wei-Chen Chiu

[MICCAI 2021 (BibTeX)] [Supplementary Materials]

@inproceedings{kao2021miccai,
title = {Demystifying T1-MRI to FDG18-PET Image Translation via Representational Similarity},
author = {Chia-Hsiang Kao and Yong-Sheng Chen and Li-Fen Chen and Wei-Chen Chiu},
booktitle = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
year = {2021}
}

teaser figure

An Unsupervised Video Game Playstyle Metric via State Discretization

Chiu-Chou Lin,Wei-Chen Chiu,I-Chen Wu

[UAI 2021 (BibTeX)] [ArXiv 2021]

@inproceedings{lin2021uai,
title = {An Unsupervised Video Game Playstyle Metric via State Discretization},
author = {Chiu-Chou Lin and Wei-Chen Chiu and I-Chen Wu},
booktitle = {37th Conference on Uncertainty in Artificial Intelligence (UAI)},
year = {2021}
}

teaser figure

teaser figure

LED2-Net: Monocular 360° Layout Estimation via Differentiable Depth Rendering

Fu-En Wang*,Yu-Hsuan Yeh*,Min Sun,Wei-Chen Chiu,Yi-Hsuan Tsai

(* indicates equal contribution.)

[CVPR 2021 (BibTeX)] [ArXiv 2021] [Project Page]

@inproceedings{wang2021cvpr,
title = {LED$^{2}$-Net: Monocular 360$^{\circ}$ Layout Estimation via Differentiable Depth Rendering},
author = {Fu-En Wang and Yu-Hsuan Yeh and Min Sun and Wei-Chen Chiu and Yi-Hsuan Tsai},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}

teaser figure

teaser figure

Domain Adaptation for Learning Generator from Paired Few-Shot Data

Chun-Chih Teng,Pin-Yu Chen,Wei-Chen Chiu

[ICASSP 2021 (BibTeX)] [ArXiv 2021]

@inproceedings{teng21icassp,
title = {Domain Adaptation for Learning Generator from Paired Few-Shot Data},
author = {Chun-Chih Teng and Pin-Yu Chen and Wei-Chen Chiu},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2021}
}

teaser figure

teaser figure

Single Image Reflection Removal with Edge Guidance, Reflection Classifier, and Recurrent Decomposition

Ya-Chu Chang*,Chia-Ni Lu*,Chia-Chi Cheng,Wei-Chen Chiu

(* indicates equal contribution.)

[WACV 2021 (BibTeX)] [Supplementary Materials] [Project Page] [Presentation Video]

@inproceedings{chang21wacv,
title = {Single Image Reflection Removal with Edge Guidance, Reflection Classifier, and Recurrent Decomposition},
author = {Ya-Chu Chang and Chia-Ni Lu and Chia-Chi Cheng and Wei-Chen Chiu},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
year = {2021}
}

teaser figure

Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation

Li-Wei Chen,Wei-Chen Chiu,Chin-Tien Wu

[ArXiv 2020 (BibTeX)]

@article{chen2020spectral,
title = {Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation},
author = {Li-Wei Chen and Wei-Chen Chiu and Chin-Tien Wu},
journal = {ArXiv:2012.14123},
year = {2020}
}

teaser figure

Timbre-enhanced Multi-modal Music Style Transfer with Domain Balance Loss

Fan Tsai-Jyun,Chien-Yu Lu,Wei-Chen Chiu,Li Su,Che-Rung Lee

[TAAI 2020 (International Track) (BibTeX)]
(Best Paper Award - Masterpiece)

@inproceedings{fan20taai,
title = {Timbre-enhanced Multi-modal Music Style Transfer with Domain Balance Loss},
author = {Fan Tsai-Jyun and Chien-Yu Lu and Wei-Chen Chiu and Li Su and Che-Rung Lee},
booktitle = {International Conference on Technologies and Applications of Artificial Intelligence (TAAI)},
year = {2020}
}

teaser figure

teaser figure

Boosting Image and Video Compression via Learning Latent Residual Patterns

Yen-Chung Chen*,Keng-Jui Chang*,Yi-Hsuan Tsai,Wei-Chen Chiu

(* indicates equal contribution.)

[BMVC 2020 (BibTeX)] [Supplementary Materials] [Project Page] [Presentation Video] [with its shorter version presented in CLIC 2019 (BibTeX)]

@inproceedings{chen20bmvc,
title = {Boosting Image and Video Compression via Learning Latent Residual Patterns},
author = {Yen-Chung Chen and Keng-Jui Chang and Yi-Hsuan Tsai and Wei-Chen Chiu},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2020}
}

@inproceedings{chen19clic,
title = {Boosting Image and Video Compression via Learning Latent Residual Patterns},
author = {Yen-Chung Chen and Keng-Jui Chang and Yi-Hsuan Tsai and Wei-Chen Chiu},
booktitle = {Workshop and Challenge on Learned Image Compression (CLIC, in conjunction with CVPR)},
year = {2019}
}

teaser figure

Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization

Rogan Morrow,Wei-Chen Chiu

[ArXiv 2020 (BibTeX)]

@article{morrow2020unregularized,
title = {Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization},
author = {Rogan Morrow and Wei-Chen Chiu},
journal = {ArXiv:2007.03640},
year = {2020}
}

teaser figure

teaser figure

Learning Low-Shot Generative Networks for Cross-Domain Data

Hsuan-Kai Kao*,Cheng-Che Lee*,Wei-Chen Chiu

(* indicates equal contribution.)

[ICPR 2020 (BibTeX)] [Supplementary Materials] [Project Page]

@inproceedings{kao20icpr,
title = {Learning Low-Shot Generative Networks for Cross-Domain Data},
author = {Hsuan-Kai Kao and Cheng-Che Lee and Wei-Chen Chiu},
booktitle = {International Conference on Pattern Recognition (ICPR)},
year = {2020}
}

teaser figure

Real-time Monocular Depth Estimation with Extremely Light-Weight Neural Network

Mian-Jhong Chiu,Wei-Chen Chiu,Hua-Tsung Chen,Jen-Hui Chuang

[ICPR 2020 (BibTeX)]

@inproceedings{chiu20icpr,
title = {Real-time Monocular Depth Estimation with Extremely Light-Weight Neural Network},
author = {Mian-Jhong Chiu and Wei-Chen Chiu and Hua-Tsung Chen and Jen-Hui Chuang},
booktitle = {International Conference on Pattern Recognition (ICPR)},
year = {2020}
}

teaser figure

DEN: Disentangling and Exchanging Network for Depth Completion

You-Feng Wu,Vu-Hoang Tran,Ting-Wei Chang,Wei-Chen Chiu,Ching-Chun Huang

[ICPR 2020 (BibTeX)]

@inproceedings{wu20icpr,
title = {DEN: Disentangling and Exchanging Network for Depth Completion},
author = {You-Feng Wu and Vu-Hoang Tran and Ting-Wei Chang and Wei-Chen Chiu and Ching-Chun Huang},
booktitle = {International Conference on Pattern Recognition (ICPR)},
year = {2020}
}

teaser figure

Using Gamification to Create and Label Photos That Are Challenging for Computer Vision and People

Piotr Kotlinski,Xi-Jing Chang,Yang Chih-Yun,Wei-Chen Chiu,Yung-Ju Chang

[UbiComp/ISWC 2020 Posters and Demos (BibTeX)] [Supplementary Video]

@inproceedings{wu20icpr,
title = {Using Gamification to Create and Label Photos That Are Challenging for Computer Vision and People},
author = {Piotr Kotlinski and Xi-Jing Chang and Yang Chih-Yun and Wei-Chen Chiu and Yung-Ju Chang},
booktitle = {Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers (UbiComp-ISWC)},
year = {2020}
}

teaser figure

Variational Autoencoders with Normalizing Flow Decoders

Rogan Morrow,Wei-Chen Chiu

[ArXiv 2020 (BibTeX)]

@article{morrow2020normalizingflow,
title = {Variational Autoencoders with Normalizing Flow Decoders},
author = {Rogan Morrow and Wei-Chen Chiu},
journal = {ArXiv:2004.05617},
year = {2020}
}

teaser figure

LayoutMP3D: Layout Annotation of Matterport3D

Fu-En Wang*,Yu-Hsuan Yeh*,Min Sun,Wei-Chen Chiu,Yi-Hsuan Tsai

(* indicates equal contribution.)

[ArXiv 2020 (BibTeX)] [Project Page]

@article{wang2020LayoutMP3D,
title = {LayoutMP3D: Layout Annotation of Matterport3D},
author = {Fu-En Wang and Yu-Hsuan Yeh and Min Sun and Wei-Chen Chiu and Yi-Hsuan Tsai},
journal = {ArXiv:2003.13516},
year = {2020}
}

teaser figure

Time Flies: Animating a Still Image with Time-Lapse Video as Reference

Chia-Chi Cheng,Hung-Yu Chen,Wei-Chen Chiu

[CVPR 2020 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{cheng20cvpr,
title = {Time Flies: Animating a Still Image with Time-Lapse Video as Reference},
author = {Chia-Chi Cheng and Hung-Yu Chen and Wei-Chen Chiu},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2020}
}

teaser figure

BiFuse: Monocular 360 Depth Estimation via Bi-projection Fusion

Fu-En Wang*,Yu-Hsuan Yeh*,Min Sun,Wei-Chen Chiu,Yi-Hsuan Tsai

(* indicates equal contribution.)

[CVPR 2020 (BibTeX)] [Project Page] [Supplementary Materials]

@inproceedings{wang20cvpr,
title = {BiFuse: Monocular 360 Depth Estimation via Bi-projection Fusion},
author = {Fu-En Wang and Yu-Hsuan Yeh and Min Sun and Wei-Chen Chiu and Yi-Hsuan Tsai},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2020}
}

teaser figure

Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation

Yi-Lun Lee,Min-Yuan Tseng,Yu-Cheng Luo,Dung-Ru Yu,Wei-Chen Chiu

[ICRA 2020 (BibTeX)] [Presentation Video]

@inproceedings{lee20icra,
title = {Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation},
author = {Yi-Lun Lee and Min-Yuan Tseng and Yu-Cheng Luo and Dung-Ru Yu and Wei-Chen Chiu},
booktitle = {International Conference on Robotics and Automation (ICRA)},
year = {2020}
}

teaser figure

360SD-Net: 360°Stereo Depth Estimation with Learnable Cost Volume

Ning-Hsu Wang,Bolivar Solarte,Yi-Hsuan Tsai,Wei-Chen Chiu,Min Sun

[ICRA 2020 (BibTeX)] [ICCV 2019 Workshop (BibTeX)] [Project Page] [Presentation Video]

@inproceedings{wang19iccvw,
title = {360SD-Net: 360$^{\circ}$ Stereo Depth Estimation with Learnable Cost Volume},
author = {Ning-Hsu Wang and Bolivar Solarte and Yi-Hsuan Tsai and Wei-Chen Chiu and Min Sun},
booktitle = {Internationl Conference of Computer Vision (ICCV) Workshop on 360 Perception and Interaction},
year = {2019}
}

@inproceedings{wang20icra,
title = {360SD-Net: 360$^{\circ}$ Stereo Depth Estimation with Learnable Cost Volume },
author = {Ning-Hsu Wang and Bolivar Solarte andYi-Hsuan Tsai and Wei-Chen Chiu and Min Sun},
booktitle = {International Conference on Robotics and Automation (ICRA)},
year = {2020}
}

teaser figure

Static2Dynamic: Video Inference from a Deep Glimpse

Yu-Ying Yeh,Yen-Cheng Liu,Wei-Chen Chiu,Yu-Chiang Frank Wang

[IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI) (BibTeX)]

@article{yen20TETCI,
title = {Static2Dynamic: Video Inference from a Deep Glimpse},
author = {Yu-Ying Yeh and Yen-Cheng Liu and Wei-Chen Chiu and Yu-Chiang Frank Wang},
journal = {IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)},
volume = {4},
number = {4},
pages = {440-449},
year = {2020}
}

teaser figure

teaser figure

teaser figure

3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization

Tsun-Hsuan Wang,Hou-Ning Hu,Chieh Hubert Lin,Yi-Hsuan Tsai,Wei-Chen Chiu,Min Sun

[IROS 2019 (BibTeX)] [ArXiv 2019] [Project Page] [Presentation Video]

@inproceedings{wang19iros,
title = {3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization},
author = {Tsun-Hsuan Wang and Hou-Ning Hu and Chieh Hubert Lin and Yi-Hsuan Tsai and Wei-Chen Chiu and Min Sun},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2019}
}

teaser figure

Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence

Hsueh-Ying Lai,Yi-Hsuan Tsai,Wei-Chen Chiu

[CVPR 2019 (BibTeX)] [ArXiv 2019] [Project Page] [Supplementary Materials]

@inproceedings{lai19cvpr,
title = {Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence},
author = {Hsueh-Ying Lai and Yi-Hsuan Tsai and Wei-Chen Chiu},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}

teaser figure

All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation

Wei-Lun Chang*,Hui-Po Wang*,Wen-Hsiao Peng,Wei-Chen Chiu

(* indicates equal contribution.)

[CVPR 2019 (BibTeX)] [ArXiv 2019] [Project Page] [Supplementary Materials] [Presentation Video]

@inproceedings{chang19cvpr,
title = {All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation Abstract},
author = {Wei-Lun Chang and Hui-Po Wang and Wen-Hsiao Peng and Wei-Chen Chiu},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}

teaser figure

Learning Pose-Aware 3D Reconstruction via 2D-3D Self-Consistency

Yi-Lun Liao*,Yao-Cheng Yang*,Yuan-Fang Lin,Pin-Jung Chen,Chia-Wen Kuo,Wei-Chen Chiu,Yu-Chiang Frank Wang

(* indicates equal contribution.)

[ICASSP 2019 (BibTeX)]

@inproceedings{liao19icassp,
title = {Learning Pose-Aware 3D Reconstruction via 2D-3D Self-Consistency},
author = {Yi-Lun Liao and Yao-Cheng Yang and Yuan-Fang Lin and Pin-Jung Chen and Chia-Wen Kuo and Wei-Chen Chiu and Yu-Chiang Frank Wang},
booktitle = {International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2019}
}

teaser figure

teaser figure

teaser figure

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

Yen-Cheng Liu*,Yu-Ying Yeh*,Tzu-Chien Fu,Sheng-De Wang,Wei-Chen Chiu,Yu-Chiang Frank Wang

(* indicates equal contribution.)

[CVPR 2018 "Spotlight" (BibTeX)] [ArXiv 2017 ] [Project Page] [Supplementary Materials]

@article{liu18cvpr,
title = {Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation},
author = {Yen-Cheng Liu and Yu-Ying Yeh and Tzu-Chien Fu and Sheng-De Wang and Wei-Chen Chiu and Yu-Chiang Frank Wang},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2018}
}

@inproceedings{liu17cvgip,
title = {Buy One and Get One Free: Cross-Domain Feature Disentanglement Learning with Single Domain Supervision},
author = {Yen-Cheng Liu and Tzu-Chien Fu and Wei-Chen Chiu and Sheng-De Wang and Yu-Chiang Frank Wang},
booktitle = {IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP)},
year = {2017}
}

teaser figure

Domain-Adaptive Generative Adversarial Networks For Sketch-To-Photo Inversion

Yen-Cheng Liu,Wei-Chen Chiu,Sheng-De Wang,Yu-Chiang Frank Wang

[MLSP 2017 (BibTeX)]

@inproceedings{liu17mlsp,
title = {Domain-Adaptive Generative Adversarial Networks For Sketch-To-Photo Inversion},
author = {Yen-Cheng Liu and Wei-Chen Chiu and Sheng-De Wang and Yu-Chiang Frank Wang},
booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
year = {2017}
}

teaser figure

Learning Guided Convolutional Neural Networks For Cross-Resolution Face Recognition

Tzu-Chien Fu,Wei-Chen Chiu,Yu-Chiang Frank Wang

[MLSP 2017 (BibTeX)]

@inproceedings{fu17mlsp,
title = {Learning Guided Convolutional Neural Networks For Cross-Resolution Face Recognition},
author = {Tzu-Chien Fu and Wei-Chen Chiu and Yu-Chiang Frank Wang},
booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
year = {2017}
}

teaser figure

STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling

Yang He,Wei-Chen Chiu,Margret Keuper,Mario Fritz

[CVPR 2017 (BibTeX)] [ArXiv 2016] [Project Page]

@inproceedings{yang17cvpr,
title = {STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling},
author = {Yang He and Wei-Chen Chiu and Margret Keuper and Mario Fritz},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2017}
}

teaser figure

Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles

Wei-Chen Chiu,Fabio Galasso,Mario Fritz

[ACCV 2016 (BibTeX)] [ArXiv 2016]

@inproceedings{chiu16accv,
title = {Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles},
author = {Wei-Chen Chiu and Fabio Galasso and Mario Fritz},
booktitle = {Asian Conference on Computer Vision (ACCV)},
year = {2016}
}

teaser figure

Bayesian Non-Parametrics for Multi-Modal Segmentation

Wei-Chen Chiu

[Doctoral Dissertation (BibTeX)]

@phdthesis{chiu16phd,
title = {Bayesian Non-Parametrics for Multi-Modal Segmentation},
author = {Wei-Chen Chiu},
url = {http://scidok.sulb.uni-saarland.de/volltexte/2016/6637/pdf/walon\_thesis.pdf},
year = {2016}
}

teaser figure

See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG

Wei-Chen Chiu,Mario Fritz

[ICCV 2015 (BibTeX)] [ArXiv 2015] [Project Page]

@inproceedings{chiu15iccv,
title = {See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG},
author = {Wei-Chen Chiu and Mario Fritz},
booktitle = {IEEE International Conference on Computer Vision (ICCV)},
year = {2015}
}

teaser figure

Joint Segmentation and Activity Discovery using Semantic and Temporal Priors

Julia Seiter,Wei-Chen Chiu,Mario Fritz,Oliver Amft,Gerhard Troester

[PerCom 2015 (BibTeX)]

@inproceedings{seiter15percom,
title = {Joint Segmentation and Activity Discovery using Semantic and Temporal Priors},
author = {Julia Seiter and Wei-Chen Chiu and Mario Fritz and Oliver Amft and Gerhard Troester},
booktitle = {IEEE Internation Conference on Pervasive Computing and Communication (PerCom)},
year = {2015}
}

teaser figure

Object Disambiguation for Augmented Reality Applications

Wei-Chen Chiu,Gregory S. Johnson,Daniel Mcculley,Oliver Grau,Mario Fritz

[BMVC 2014 (BibTeX)] [Project Page]

@inproceedings{chiu14bmvc,
title = {Object Disambiguation for Augmented Reality Applications},
author = {Wei-Chen Chiu and Gregory S. Johnson and Daniel Mcculley and Oliver Grau and Mario Fritz},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2014}
}

teaser figure

Multi-Class Video Co-Segmentation with a Generative Multi-Video Model

Wei-Chen Chiu,Mario Fritz

[CVPR 2013 (BibTeX)] [Project Page]

@inproceedings{chiu13cvpr,
title = {Multi-Class Video Co-Segmentation with a Generative Multi-Video Model},
author = {Wei-Chen Chiu and Mario Fritz},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2013}
}

teaser figure

I spy with my little eye: Learning Optimal Filters for Cross-Modal Stereo under Projected Patterns

Wei-Chen Chiu,Ulf Blanke,Mario Fritz

[CDC4CV 2011 (BibTeX)] [Project Page]

@inproceedings{chiu11cdc4cv,
title = {I spy with my little eye: Learning Optimal Filters for Cross-Modal Stereo under Projected Patterns},
author = {Wei-Chen Chiu and Ulf Blanke and Mario Fritz},
booktitle = {IEEE Workshop on Consumer Depth Cameras for Computer Vision (CDC4CV)},
year = {2011}
}

teaser figure

Improving the Kinect by Cross-Modal Stereo

Wei-Chen Chiu,Ulf Blanke,Mario Fritz

[BMVC 2011 (BibTeX)] [Project Page]

@inproceedings{chiu11bmvc,
title = {Improving the Kinect by Cross-Modal Stereo},
author = {Wei-Chen Chiu and Ulf Blanke and Mario Fritz},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2011}
}

teaser figure

Probabilistic Modeling of Dynamic Traffic Flow between Non-overlapping FOVs

Wei-Chen Chiu,Ching-Chun Huang,Jen-Hui Chuang,Sheng-Jyh Wang

[ICPR 2010 (BibTeX)] [CVGIP 2009 (BibTeX)] [Master Thesis]

@inproceedings{huang10icpr,
title = {Probabilistic Modeling of Dynamic Traffic Flow across Non-overlapping Camera Views},
author = {Ching-Chun Huang and Wei-Chen Chiu and Sheng-Jyh Wang and Jen-Hui Chuang},
booktitle = {IEEE Conference on Pattern Recognition (ICPR)},
year = {2010}
}

@inproceedings{chiu09cvgip,
title = {Probabilistic Modeling of Dynamic Traffic Flow between Non-overlapping Camera Views},
author = {Wei-Chen Chiu and Ching-Chun Huang and Jen-Hui Chuang and Sheng-Jyh Wang},
booktitle = {IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP)},
year = {2009}
}

teaser figure

Robust Parking Space Detection Considering Inter-Space Correlation

Qi Wu,Ching-Chun Huang,Shih-Yu Wang,Wei-Chen Chiu,Tsuhan Chen

[ICME 2007 (BibTeX)]

@inproceedings{wu07icme,
title = {Robust Parking Space Detection Considering Inter-Space Correlation},
author = {Qi Wu and Ching-Chun Huang and Shih-Yu Wang and Wei-Chen Chiu and Tsuhan Chen},
booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
year = {2007}
}