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 Yun Fu

Yun Fu

Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization


Jun 22, 2021
Yizhou Wang, Yue Kang, Can Qin, Yi Xu, Huan Wang, Yulun Zhang, Yun Fu

Figure 1 for Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization
Figure 2 for Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization
Figure 3 for Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization
Figure 4 for Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization
* 40 pages, 27 figures 
  Access Paper or Ask Questions

Dynamical Isometry: The Missing Ingredient for Neural Network Pruning


May 12, 2021
Huan Wang, Can Qin, Yue Bai, Yun Fu

Figure 1 for Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
Figure 2 for Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
Figure 3 for Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
Figure 4 for Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
* 8 pages, 2 figures, 7 tables 
  Access Paper or Ask Questions

Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning


Apr 19, 2021
Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu

Figure 1 for Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning
Figure 2 for Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning
Figure 3 for Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning
Figure 4 for Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning
* 10 pages, 2 figures 
  Access Paper or Ask Questions

RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks


Apr 18, 2021
Kai Li, Curtis Wigington, Chris Tensmeyer, Vlad I. Morariu, Handong Zhao, Varun Manjunatha, Nikolaos Barmpalios, Yun Fu

Figure 1 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 2 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 3 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 4 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
* 10 pages, 5 figures 
  Access Paper or Ask Questions

Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution


Apr 15, 2021
Xiaoyu Xiang, Yapeng Tian, Yulun Zhang, Yun Fu, Jan P. Allebach, Chenliang Xu

Figure 1 for Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
Figure 2 for Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
Figure 3 for Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
Figure 4 for Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
* Journal version of "Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution"(CVPR-2020). 14 pages, 14 figures 
  Access Paper or Ask Questions

Skeleton Aware Multi-modal Sign Language Recognition


Mar 26, 2021
Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu

Figure 1 for Skeleton Aware Multi-modal Sign Language Recognition
Figure 2 for Skeleton Aware Multi-modal Sign Language Recognition
Figure 3 for Skeleton Aware Multi-modal Sign Language Recognition
Figure 4 for Skeleton Aware Multi-modal Sign Language Recognition
* This submission is a preprint version of our work SAM-SLR that ranked 1st at CVPR2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition 
  Access Paper or Ask Questions

Balancing Biases and Preserving Privacy on Balanced Faces in the Wild


Mar 16, 2021
Joseph P Robinson, Can Qin, Yann Henon, Samson Timoner, Yun Fu

Figure 1 for Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
Figure 2 for Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
Figure 3 for Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
Figure 4 for Balancing Biases and Preserving Privacy on Balanced Faces in the Wild

  Access Paper or Ask Questions

Skeleton Based Sign Language Recognition Using Whole-body Keypoints


Mar 16, 2021
Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu

Figure 1 for Skeleton Based Sign Language Recognition Using Whole-body Keypoints
Figure 2 for Skeleton Based Sign Language Recognition Using Whole-body Keypoints
Figure 3 for Skeleton Based Sign Language Recognition Using Whole-body Keypoints
Figure 4 for Skeleton Based Sign Language Recognition Using Whole-body Keypoints
* This submission is a preprint fact sheet version of our work at CVPR2021 Challenge on Looking at People Large Scale Signer Independent Isolated SLR 
  Access Paper or Ask Questions

Emerging Paradigms of Neural Network Pruning


Mar 11, 2021
Huan Wang, Can Qin, Yulun Zhang, Yun Fu

Figure 1 for Emerging Paradigms of Neural Network Pruning
Figure 2 for Emerging Paradigms of Neural Network Pruning

  Access Paper or Ask Questions

VINS: Visual Search for Mobile User Interface Design


Feb 10, 2021
Sara Bunian, Kai Li, Chaima Jemmali, Casper Harteveld, Yun Fu, Magy Seif El-Nasr

Figure 1 for VINS: Visual Search for Mobile User Interface Design
Figure 2 for VINS: Visual Search for Mobile User Interface Design
Figure 3 for VINS: Visual Search for Mobile User Interface Design
Figure 4 for VINS: Visual Search for Mobile User Interface Design

  Access Paper or Ask Questions

One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision


Feb 03, 2021
Zaid Khan, Yun Fu

Figure 1 for One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
Figure 2 for One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
Figure 3 for One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
Figure 4 for One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
* Published as a conference paper at the 4th ACM Conference on Fairness, Accountability, and Transparency (FAccT 2021) 
  Access Paper or Ask Questions

Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts


Jan 11, 2021
Kunpeng Li, Zizhao Zhang, Guanhang Wu, Xuehan Xiong, Chen-Yu Lee, Zhichao Lu, Yun Fu, Tomas Pfister

Figure 1 for Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
Figure 2 for Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
Figure 3 for Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
Figure 4 for Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts

  Access Paper or Ask Questions

Neural Pruning via Growing Regularization


Dec 16, 2020
Huan Wang, Can Qin, Yulun Zhang, Yun Fu

Figure 1 for Neural Pruning via Growing Regularization
Figure 2 for Neural Pruning via Growing Regularization
Figure 3 for Neural Pruning via Growing Regularization
Figure 4 for Neural Pruning via Growing Regularization

  Access Paper or Ask Questions

Multimodal In-bed Pose and Shape Estimation under the Blankets


Dec 12, 2020
Yu Yin, Joseph P. Robinson, Yun Fu

Figure 1 for Multimodal In-bed Pose and Shape Estimation under the Blankets
Figure 2 for Multimodal In-bed Pose and Shape Estimation under the Blankets
Figure 3 for Multimodal In-bed Pose and Shape Estimation under the Blankets
Figure 4 for Multimodal In-bed Pose and Shape Estimation under the Blankets

  Access Paper or Ask Questions

SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis


Dec 07, 2020
Yu Yin, Joseph P. Robinson, Songyao Jiang, Yue Bai, Can Qin, Yun Fu

Figure 1 for SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
Figure 2 for SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
Figure 3 for SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
Figure 4 for SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis

  Access Paper or Ask Questions

Multi-head Knowledge Distillation for Model Compression


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

Figure 1 for Multi-head Knowledge Distillation for Model Compression
Figure 2 for Multi-head Knowledge Distillation for Model Compression
Figure 3 for Multi-head Knowledge Distillation for Model Compression
Figure 4 for Multi-head Knowledge Distillation for Model Compression
* Copyright: 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 
  Access Paper or Ask Questions

Knowledge Distillation Thrives on Data Augmentation


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

Figure 1 for Knowledge Distillation Thrives on Data Augmentation
Figure 2 for Knowledge Distillation Thrives on Data Augmentation
Figure 3 for Knowledge Distillation Thrives on Data Augmentation
Figure 4 for Knowledge Distillation Thrives on Data Augmentation
* Code will be updated soon 
  Access Paper or Ask Questions

Collaborative Attention Mechanism for Multi-View Action Recognition


Sep 14, 2020
Yue Bai, Zhiqiang Tao, Lichen Wang, Sheng Li, Yu Yin, Yun Fu

Figure 1 for Collaborative Attention Mechanism for Multi-View Action Recognition
Figure 2 for Collaborative Attention Mechanism for Multi-View Action Recognition
Figure 3 for Collaborative Attention Mechanism for Multi-View Action Recognition
Figure 4 for Collaborative Attention Mechanism for Multi-View Action Recognition

  Access Paper or Ask Questions

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection


Aug 17, 2020
Shuhan Chen, Yun Fu

Figure 1 for Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
Figure 2 for Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
Figure 3 for Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
Figure 4 for Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
* ECCV 2020 
  Access Paper or Ask Questions

Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship


Jul 28, 2020
Joseph P. Robinson, Zaid Khan, Yu Yin, Ming Shao, Yun Fu

Figure 1 for Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship
Figure 2 for Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship
Figure 3 for Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship
Figure 4 for Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship

  Access Paper or Ask Questions

Visual Kinship Recognition: A Decade in the Making


Jun 29, 2020
Joseph P Robinson, Ming Shao, Yun Fu

Figure 1 for Visual Kinship Recognition: A Decade in the Making
Figure 2 for Visual Kinship Recognition: A Decade in the Making
Figure 3 for Visual Kinship Recognition: A Decade in the Making
Figure 4 for Visual Kinship Recognition: A Decade in the Making

  Access Paper or Ask Questions

Neural Sparse Representation for Image Restoration


Jun 08, 2020
Yuchen Fan, Jiahui Yu, Yiqun Mei, Yulun Zhang, Yun Fu, Ding Liu, Thomas S. Huang

Figure 1 for Neural Sparse Representation for Image Restoration
Figure 2 for Neural Sparse Representation for Image Restoration
Figure 3 for Neural Sparse Representation for Image Restoration
Figure 4 for Neural Sparse Representation for Image Restoration

  Access Paper or Ask Questions

Pyramid Attention Networks for Image Restoration


Jun 03, 2020
Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Thomas S. Huang, Humphrey Shi

Figure 1 for Pyramid Attention Networks for Image Restoration
Figure 2 for Pyramid Attention Networks for Image Restoration
Figure 3 for Pyramid Attention Networks for Image Restoration
Figure 4 for Pyramid Attention Networks for Image Restoration

  Access Paper or Ask Questions

HyperSTAR: Task-Aware Hyperparameters for Deep Networks


May 21, 2020
Gaurav Mittal, Chang Liu, Nikolaos Karianakis, Victor Fragoso, Mei Chen, Yun Fu

Figure 1 for HyperSTAR: Task-Aware Hyperparameters for Deep Networks
Figure 2 for HyperSTAR: Task-Aware Hyperparameters for Deep Networks
Figure 3 for HyperSTAR: Task-Aware Hyperparameters for Deep Networks
Figure 4 for HyperSTAR: Task-Aware Hyperparameters for Deep Networks
* Published at CVPR 2020 (Oral) 
  Access Paper or Ask Questions

Learnable Subspace Clustering


Apr 09, 2020
Jun Li, Hongfu Liu, Zhiqiang Tao, Handong Zhao, Yun Fu

Figure 1 for Learnable Subspace Clustering
Figure 2 for Learnable Subspace Clustering
Figure 3 for Learnable Subspace Clustering
Figure 4 for Learnable Subspace Clustering
* IEEE Transactions on Neural Networks and Learning Systems (accepted with minor revision) 
  Access Paper or Ask Questions

Cross-Domain Document Object Detection: Benchmark Suite and Method


Mar 30, 2020
Kai Li, Curtis Wigington, Chris Tensmeyer, Handong Zhao, Nikolaos Barmpalios, Vlad I. Morariu, Varun Manjunatha, Tong Sun, Yun Fu

Figure 1 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 2 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 3 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 4 for Cross-Domain Document Object Detection: Benchmark Suite and Method
* To appear in CVPR 2020 
  Access Paper or Ask Questions

Adversarial Feature Hallucination Networks for Few-Shot Learning


Mar 30, 2020
Kai Li, Yulun Zhang, Kunpeng Li, Yun Fu

Figure 1 for Adversarial Feature Hallucination Networks for Few-Shot Learning
Figure 2 for Adversarial Feature Hallucination Networks for Few-Shot Learning
Figure 3 for Adversarial Feature Hallucination Networks for Few-Shot Learning
Figure 4 for Adversarial Feature Hallucination Networks for Few-Shot Learning
* To appear in CVPR 2020 
  Access Paper or Ask Questions

Generative Partial Multi-View Clustering


Mar 29, 2020
Qianqian Wang, Zhengming Ding, Zhiqiang Tao, Quanxue Gao, Yun Fu

Figure 1 for Generative Partial Multi-View Clustering
Figure 2 for Generative Partial Multi-View Clustering
Figure 3 for Generative Partial Multi-View Clustering
Figure 4 for Generative Partial Multi-View Clustering
* This paper is an extension to our previous work: "Wang Q, Ding Z, Tao Z, et al. Partial multi-view clustering via consistent GAN[C]//2018 IEEE International Conference on Data Mining (ICDM). IEEE, 2018: 1290-1295." 
  Access Paper or Ask Questions