Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ming-Hsuan Yang

Ming-Hsuan Yang

Federated Multi-Target Domain Adaptation


Aug 17, 2021
Chun-Han Yao, Boqing Gong, Yin Cui, Hang Qi, Yukun Zhu, Ming-Hsuan Yang

Figure 1 for Federated Multi-Target Domain Adaptation
Figure 2 for Federated Multi-Target Domain Adaptation
Figure 3 for Federated Multi-Target Domain Adaptation
Figure 4 for Federated Multi-Target Domain Adaptation

  Access Paper or Ask Questions

Discovering 3D Parts from Image Collections


Jul 28, 2021
Chun-Han Yao, Wei-Chih Hung, Varun Jampani, Ming-Hsuan Yang

Figure 1 for Discovering 3D Parts from Image Collections
Figure 2 for Discovering 3D Parts from Image Collections
Figure 3 for Discovering 3D Parts from Image Collections
Figure 4 for Discovering 3D Parts from Image Collections
* Accepted by ICCV 2021. Project page: https://chhankyao.github.io/lpd/ 
  Access Paper or Ask Questions

End-to-end Multi-modal Video Temporal Grounding


Jul 12, 2021
Yi-Wen Chen, Yi-Hsuan Tsai, Ming-Hsuan Yang

Figure 1 for End-to-end Multi-modal Video Temporal Grounding
Figure 2 for End-to-end Multi-modal Video Temporal Grounding
Figure 3 for End-to-end Multi-modal Video Temporal Grounding
Figure 4 for End-to-end Multi-modal Video Temporal Grounding

  Access Paper or Ask Questions

Learning 3D Dense Correspondence via Canonical Point Autoencoder


Jul 10, 2021
An-Chieh Cheng, Xueting Li, Min Sun, Ming-Hsuan Yang, Sifei Liu

Figure 1 for Learning 3D Dense Correspondence via Canonical Point Autoencoder
Figure 2 for Learning 3D Dense Correspondence via Canonical Point Autoencoder
Figure 3 for Learning 3D Dense Correspondence via Canonical Point Autoencoder
Figure 4 for Learning 3D Dense Correspondence via Canonical Point Autoencoder

  Access Paper or Ask Questions

Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking


Jun 21, 2021
Xin Li, Wenjie Pei, Zikun Zhou, Zhenyu He, Huchuan Lu, Ming-Hsuan Yang

Figure 1 for Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking
Figure 2 for Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking
Figure 3 for Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking
Figure 4 for Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking
* 10 pages, 5 figures 
  Access Paper or Ask Questions

Intriguing Properties of Vision Transformers


Jun 08, 2021
Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang

Figure 1 for Intriguing Properties of Vision Transformers
Figure 2 for Intriguing Properties of Vision Transformers
Figure 3 for Intriguing Properties of Vision Transformers
Figure 4 for Intriguing Properties of Vision Transformers
* Code: https://git.io/Js15X 
  Access Paper or Ask Questions

Incremental False Negative Detection for Contrastive Learning


Jun 07, 2021
Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien, Ming-Hsuan Yang

Figure 1 for Incremental False Negative Detection for Contrastive Learning
Figure 2 for Incremental False Negative Detection for Contrastive Learning
Figure 3 for Incremental False Negative Detection for Contrastive Learning
Figure 4 for Incremental False Negative Detection for Contrastive Learning
* Submitted to NeurIPS 2021. Code: https://github.com/tsaishien-chen/IFND 
  Access Paper or Ask Questions

Large-scale Unsupervised Semantic Segmentation


Jun 06, 2021
Shang-Hua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr

Figure 1 for Large-scale Unsupervised Semantic Segmentation
Figure 2 for Large-scale Unsupervised Semantic Segmentation
Figure 3 for Large-scale Unsupervised Semantic Segmentation
Figure 4 for Large-scale Unsupervised Semantic Segmentation

  Access Paper or Ask Questions

Learning to Stylize Novel Views


May 27, 2021
Hsin-Ping Huang, Hung-Yu Tseng, Saurabh Saini, Maneesh Singh, Ming-Hsuan Yang

Figure 1 for Learning to Stylize Novel Views
Figure 2 for Learning to Stylize Novel Views
Figure 3 for Learning to Stylize Novel Views
Figure 4 for Learning to Stylize Novel Views
* Project page: https://hhsinping.github.io/3d_scene_stylization/ 
  Access Paper or Ask Questions

COMISR: Compression-Informed Video Super-Resolution


May 04, 2021
Yinxiao Li, Pengchong Jin, Feng Yang, Ce Liu, Ming-Hsuan Yang, Peyman Milanfar

Figure 1 for COMISR: Compression-Informed Video Super-Resolution
Figure 2 for COMISR: Compression-Informed Video Super-Resolution
Figure 3 for COMISR: Compression-Informed Video Super-Resolution
Figure 4 for COMISR: Compression-Informed Video Super-Resolution
* 14 pages, 13 figures 
  Access Paper or Ask Questions

Decoupled Dynamic Filter Networks


Apr 29, 2021
Jingkai Zhou, Varun Jampani, Zhixiong Pi, Qiong Liu, Ming-Hsuan Yang

Figure 1 for Decoupled Dynamic Filter Networks
Figure 2 for Decoupled Dynamic Filter Networks
Figure 3 for Decoupled Dynamic Filter Networks
Figure 4 for Decoupled Dynamic Filter Networks
* CVPR 2021 
  Access Paper or Ask Questions

2.5D Visual Relationship Detection


Apr 26, 2021
Yu-Chuan Su, Soravit Changpinyo, Xiangning Chen, Sathish Thoppay, Cho-Jui Hsieh, Lior Shapira, Radu Soricut, Hartwig Adam, Matthew Brown, Ming-Hsuan Yang, Boqing Gong

Figure 1 for 2.5D Visual Relationship Detection
Figure 2 for 2.5D Visual Relationship Detection
Figure 3 for 2.5D Visual Relationship Detection
Figure 4 for 2.5D Visual Relationship Detection

  Access Paper or Ask Questions

Understanding Synonymous Referring Expressions via Contrastive Features


Apr 20, 2021
Yi-Wen Chen, Yi-Hsuan Tsai, Ming-Hsuan Yang

Figure 1 for Understanding Synonymous Referring Expressions via Contrastive Features
Figure 2 for Understanding Synonymous Referring Expressions via Contrastive Features
Figure 3 for Understanding Synonymous Referring Expressions via Contrastive Features
Figure 4 for Understanding Synonymous Referring Expressions via Contrastive Features
* Codes and models will be available at https://github.com/wenz116/RefContrast 
  Access Paper or Ask Questions

Weakly Supervised Object Localization and Detection: A Survey


Apr 16, 2021
Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang

Figure 1 for Weakly Supervised Object Localization and Detection: A Survey
Figure 2 for Weakly Supervised Object Localization and Detection: A Survey
Figure 3 for Weakly Supervised Object Localization and Detection: A Survey
Figure 4 for Weakly Supervised Object Localization and Detection: A Survey
* IEEE Transactions on Pattern Analysis and Machine Intelligence, Accepted 
  Access Paper or Ask Questions

Know What and Know Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation


Apr 09, 2021
Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang, Anton van den Hengel, Qi Wu

Figure 1 for Know What and Know Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Figure 2 for Know What and Know Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Figure 3 for Know What and Know Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Figure 4 for Know What and Know Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

  Access Paper or Ask Questions

InfinityGAN: Towards Infinite-Resolution Image Synthesis


Apr 08, 2021
Chieh Hubert Lin, Hsin-Ying Lee, Yen-Chi Cheng, Sergey Tulyakov, Ming-Hsuan Yang

Figure 1 for InfinityGAN: Towards Infinite-Resolution Image Synthesis
Figure 2 for InfinityGAN: Towards Infinite-Resolution Image Synthesis
Figure 3 for InfinityGAN: Towards Infinite-Resolution Image Synthesis
Figure 4 for InfinityGAN: Towards Infinite-Resolution Image Synthesis
* Project page: https://hubert0527.github.io/infinityGAN/ 
  Access Paper or Ask Questions

Regularizing Generative Adversarial Networks under Limited Data


Apr 07, 2021
Hung-Yu Tseng, Lu Jiang, Ce Liu, Ming-Hsuan Yang, Weilong Yang

Figure 1 for Regularizing Generative Adversarial Networks under Limited Data
Figure 2 for Regularizing Generative Adversarial Networks under Limited Data
Figure 3 for Regularizing Generative Adversarial Networks under Limited Data
Figure 4 for Regularizing Generative Adversarial Networks under Limited Data
* CVPR 2021. Project Page: https://hytseng0509.github.io/lecam-gan Code: https://github.com/google/lecam-gan 
  Access Paper or Ask Questions

In&Out : Diverse Image Outpainting via GAN Inversion


Apr 01, 2021
Yen-Chi Cheng, Chieh Hubert Lin, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Ming-Hsuan Yang

Figure 1 for In&Out : Diverse Image Outpainting via GAN Inversion
Figure 2 for In&Out : Diverse Image Outpainting via GAN Inversion
Figure 3 for In&Out : Diverse Image Outpainting via GAN Inversion
Figure 4 for In&Out : Diverse Image Outpainting via GAN Inversion
* Project Page: https://yccyenchicheng.github.io/InOut/ 
  Access Paper or Ask Questions

Unsupervised Sound Localization via Iterative Contrastive Learning


Apr 01, 2021
Yan-Bo Lin, Hung-Yu Tseng, Hsin-Ying Lee, Yen-Yu Lin, Ming-Hsuan Yang

Figure 1 for Unsupervised Sound Localization via Iterative Contrastive Learning
Figure 2 for Unsupervised Sound Localization via Iterative Contrastive Learning
Figure 3 for Unsupervised Sound Localization via Iterative Contrastive Learning
Figure 4 for Unsupervised Sound Localization via Iterative Contrastive Learning

  Access Paper or Ask Questions

ReMix: Towards Image-to-Image Translation with Limited Data


Mar 31, 2021
Jie Cao, Luanxuan Hou, Ming-Hsuan Yang, Ran He, Zhenan Sun

Figure 1 for ReMix: Towards Image-to-Image Translation with Limited Data
Figure 2 for ReMix: Towards Image-to-Image Translation with Limited Data
Figure 3 for ReMix: Towards Image-to-Image Translation with Limited Data
Figure 4 for ReMix: Towards Image-to-Image Translation with Limited Data
* CVPR 2021 
  Access Paper or Ask Questions

Self-Attentive 3D Human Pose and Shape Estimation from Videos


Mar 26, 2021
Yun-Chun Chen, Marco Piccirilli, Robinson Piramuthu, Ming-Hsuan Yang

Figure 1 for Self-Attentive 3D Human Pose and Shape Estimation from Videos
Figure 2 for Self-Attentive 3D Human Pose and Shape Estimation from Videos
Figure 3 for Self-Attentive 3D Human Pose and Shape Estimation from Videos
Figure 4 for Self-Attentive 3D Human Pose and Shape Estimation from Videos
* This paper is under consideration at Computer Vision and Image Understanding 
  Access Paper or Ask Questions

Neural Re-rendering for Full-frame Video Stabilization


Feb 12, 2021
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

Figure 1 for Neural Re-rendering for Full-frame Video Stabilization
Figure 2 for Neural Re-rendering for Full-frame Video Stabilization
Figure 3 for Neural Re-rendering for Full-frame Video Stabilization
Figure 4 for Neural Re-rendering for Full-frame Video Stabilization
* Project page: https://alex04072000.github.io/NeRViS/ 
  Access Paper or Ask Questions

Multi-Stage Progressive Image Restoration


Feb 04, 2021
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Figure 1 for Multi-Stage Progressive Image Restoration
Figure 2 for Multi-Stage Progressive Image Restoration
Figure 3 for Multi-Stage Progressive Image Restoration
Figure 4 for Multi-Stage Progressive Image Restoration

  Access Paper or Ask Questions

Exploiting Raw Images for Real-Scene Super-Resolution


Feb 02, 2021
Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang

Figure 1 for Exploiting Raw Images for Real-Scene Super-Resolution
Figure 2 for Exploiting Raw Images for Real-Scene Super-Resolution
Figure 3 for Exploiting Raw Images for Real-Scene Super-Resolution
Figure 4 for Exploiting Raw Images for Real-Scene Super-Resolution
* IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 
 * A larger version with higher-resolution figures is available at: https://sites.google.com/view/xiangyuxu. arXiv admin note: text overlap with arXiv:1905.12156 
  Access Paper or Ask Questions

Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising


Jan 26, 2021
Xiangyu Xu, Muchen Li, Wenxiu Sun, Ming-Hsuan Yang

Figure 1 for Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
Figure 2 for Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
Figure 3 for Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
Figure 4 for Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
* IEEE Transactions on Image Processing 29 (2020): 7153-7165 
 * Project page: https://sites.google.com/view/xiangyuxu/denoise_stpan. arXiv admin note: substantial text overlap with arXiv:1904.06903 
  Access Paper or Ask Questions

GAN Inversion: A Survey


Jan 14, 2021
Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, Ming-Hsuan Yang

Figure 1 for GAN Inversion: A Survey
Figure 2 for GAN Inversion: A Survey
Figure 3 for GAN Inversion: A Survey
Figure 4 for GAN Inversion: A Survey
* papers on generative modeling: https://github.com/zhoubolei/awesome-generative-modeling awesome gan-inversion papers: https://github.com/weihaox/awesome-image-translation/blob/master/awesome-gan-inversion.md 
  Access Paper or Ask Questions

Low Light Image Enhancement via Global and Local Context Modeling


Jan 04, 2021
Aditya Arora, Muhammad Haris, Syed Waqas Zamir, Munawar Hayat, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang

Figure 1 for Low Light Image Enhancement via Global and Local Context Modeling
Figure 2 for Low Light Image Enhancement via Global and Local Context Modeling
Figure 3 for Low Light Image Enhancement via Global and Local Context Modeling
Figure 4 for Low Light Image Enhancement via Global and Local Context Modeling

  Access Paper or Ask Questions

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations


Dec 11, 2020
Sanath Narayan, Hisham Cholakkal, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Figure 1 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 2 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 3 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 4 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

  Access Paper or Ask Questions