Ming-Hsuan Yang

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

Aug 19, 2020
Cheng-Chun Hsu, Yi-Hsuan Tsai, Yen-Yu Lin, Ming-Hsuan Yang

* Accepted in ECCV'20. Project page: https://chengchunhsu.github.io/EveryPixelMatters/

Access Model/Code and Paper

SoDA: Multi-Object Tracking with Soft Data Association

Aug 19, 2020
Wei-Chih Hung, Henrik Kretzschmar, Tsung-Yi Lin, Yuning Chai, Ruichi Yu, Ming-Hsuan Yang, Dragomir Anguelov

Access Model/Code and Paper

Learning to Caricature via Semantic Shape Transform

Aug 13, 2020
Wenqing Chu, Wei-Chih Hung, Yi-Hsuan Tsai, Yu-Ting Chang, Yijun Li, Deng Cai, Ming-Hsuan Yang

* Submitted to IJCV, code and model are available at https://github.com/wenqingchu/Semantic-CariGANs/

Access Model/Code and Paper

Learning to See Through Obstructions with Layered Decomposition

Aug 11, 2020
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

* Project page: https://alex04072000.github.io/SOLD/ Code: https://github.com/alex04072000/SOLD Extension of the CVPR 2020 paper: arXiv:2004.01180

Access Model/Code and Paper

Spatiotemporal Contrastive Video Representation Learning

Aug 09, 2020
Rui Qian, Tianjian Meng, Boqing Gong, Ming-Hsuan Yang, Huisheng Wang, Serge Belongie, Yin Cui

Access Model/Code and Paper

Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

Aug 03, 2020
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang

* Accepted at BMVC 2020

Access Model/Code and Paper

Weakly-Supervised Semantic Segmentation via Sub-category Exploration

Aug 03, 2020
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang

* Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020

Access Model/Code and Paper

Learnable Cost Volume Using the Cayley Representation

Jul 21, 2020
Taihong Xiao, Jinwei Yuan, Deqing Sun, Qifei Wang, Xin-Yu Zhang, Kehan Xu, Ming-Hsuan Yang

* ECCV 2020

Access Model/Code and Paper

Controllable Image Synthesis via SegVAE

Jul 17, 2020
Yen-Chi Cheng, Hsin-Ying Lee, Min Sun, Ming-Hsuan Yang

* ECCV 2020. Project page: https://yccyenchicheng.github.io/SegVAE/ Code: https://github.com/yccyenchicheng/SegVAE

Access Model/Code and Paper

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

Jul 16, 2020
Hung-Yu Tseng, Hsin-Ying Lee, Lu Jiang, Ming-Hsuan Yang, Weilong Yang

* ECCV 2020

Access Model/Code and Paper

Modeling Artistic Workflows for Image Generation and Editing

Jul 14, 2020
Hung-Yu Tseng, Matthew Fisher, Jingwan Lu, Yijun Li, Vladimir Kim, Ming-Hsuan Yang

* ECCV 2020. Code: https://github.com/hytseng0509/ArtEditing

Access Model/Code and Paper

Semi-Supervised Learning with Meta-Gradient

Jul 08, 2020
Xin-Yu Zhang, Hao-Lin Jia, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang

* 17 pages

Access Model/Code and Paper

Ventral-Dorsal Neural Networks: Object Detection via Selective Attention

May 15, 2020
Mohammad K. Ebrahimpour, Jiayun Li, Yen-Yun Yu, Jackson L. Reese, Azadeh Moghtaderi, Ming-Hsuan Yang, David C. Noelle

* in Proceedings of WACV. arXiv admin note: substantial text overlap with arXiv:2005.07787

Access Model/Code and Paper

WW-Nets: Dual Neural Networks for Object Detection

May 15, 2020
Mohammad K. Ebrahimpour, J. Ben Falandays, Samuel Spevack, Ming-Hsuan Yang, David C. Noelle

* 8 pages, 3 figures

Access Model/Code and Paper

Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

Apr 28, 2020
Hang Dong, Jinshan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, Ming-Hsuan Yang

* Accepted by CVPR 2020. The code are available at https://github.com/BookerDeWitt/MSBDN-DFF

Access Model/Code and Paper

Regularizing Meta-Learning via Gradient Dropout

Apr 13, 2020
Hung-Yu Tseng, Yi-Wen Chen, Yi-Hsuan Tsai, Sifei Liu, Yen-Yu Lin, Ming-Hsuan Yang

* Code: https://github.com/hytseng0509/DropGrad

Access Model/Code and Paper

Learning to See Through Obstructions

Apr 02, 2020
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

* CVPR 2020. Project page: https://www.cmlab.csie.ntu.edu.tw/~yulunliu/ObstructionRemoval Code: https://github.com/alex04072000/ObstructionRemoval

Access Model/Code and Paper

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Apr 02, 2020
Yu-Lun Liu, Wei-Sheng Lai, Yu-Sheng Chen, Yi-Lung Kao, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

* CVPR 2020. Project page: https://www.cmlab.csie.ntu.edu.tw/~yulunliu/SingleHDR Code: https://github.com/alex04072000/SingleHDR

Access Model/Code and Paper

Deep Semantic Matching with Foreground Detection and Cycle-Consistency

Mar 31, 2020
Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu, Jia-Bin Huang, Ming-Hsuan Yang, Yen-Yu Lin

* ACCV 2018. PAMI 2020 extension: arXiv:1906.05857

Access Model/Code and Paper

TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge

Mar 30, 2020
Junyi Feng, Songyuan Li, Xi Li, Fei Wu, Qi Tian, Ming-Hsuan Yang, Haibin Ling

Access Model/Code and Paper

Collaborative Distillation for Ultra-Resolution Universal Style Transfer

Mar 24, 2020
Huan Wang, Yijun Li, Yuehai Wang, Haoji Hu, Ming-Hsuan Yang

* Accepted by CVPR 2020, higher-resolution images than the camera-ready version

Access Model/Code and Paper

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Mar 24, 2020
Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang, Liqiang Wang, Boqing Gong

* Accepted for publication at CVPR2020

Access Model/Code and Paper

CycleISP: Real Image Restoration via Improved Data Synthesis

Mar 17, 2020
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

* CVPR 2020 (Oral)

Access Model/Code and Paper

Learning Enriched Features for Real Image Restoration and Enhancement

Mar 15, 2020
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Access Model/Code and Paper

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

Mar 13, 2020
Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz

* Codes and other resources will be released at: https://sites.google.com/view/unsup-mesh/home

Access Model/Code and Paper

Gated Fusion Network for Degraded Image Super Resolution

Mar 04, 2020
Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang

* Accepted by IJCV. The code will be publicly available at https://github.com/BookerDeWitt/GFN-IJCV

Access Model/Code and Paper

Model-Agnostic Structured Sparsification with Learnable Channel Shuffle

Feb 19, 2020
Xin-Yu Zhang, Kai Zhao, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang

Access Model/Code and Paper