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 Jun Yu

Jun Yu

Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis


Oct 07, 2021
Xiaopeng Li, Jiang Wu, Zhanbo Xu, Kun Liu, Jun Yu, Xiaohong Guan

Figure 1 for Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis
Figure 2 for Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis
Figure 3 for Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis
Figure 4 for Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis

  Access Paper or Ask Questions

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration


Aug 16, 2021
Yuhao Cui, Zhou Yu, Chunqi Wang, Zhongzhou Zhao, Ji Zhang, Meng Wang, Jun Yu

Figure 1 for ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
Figure 2 for ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
Figure 3 for ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
Figure 4 for ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
* Accepted at ACM Multimedia 2021. Code available at https://github.com/MILVLG/rosita 
  Access Paper or Ask Questions

BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition


Jul 14, 2021
Hao Chang, Guochen Xie, Jun Yu, Qiang Ling

Figure 1 for BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition
Figure 2 for BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition
Figure 3 for BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition
Figure 4 for BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition
* arXiv admin note: text overlap with arXiv:2102.09559 by other authors 
  Access Paper or Ask Questions

A Weakly-Supervised Depth Estimation Network Using Attention Mechanism


Jul 10, 2021
Fang Gao, Jiabao Wang, Jun Yu, Yaoxiong Wang, Feng Shuang

Figure 1 for A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
Figure 2 for A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
Figure 3 for A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
Figure 4 for A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
* 8 pages, 8 figures, IJCAI-WSRL 
  Access Paper or Ask Questions

The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation


Jun 27, 2021
Jun Bao, Buyu Liu, Jun Yu

Figure 1 for The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation
Figure 2 for The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation
Figure 3 for The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation
Figure 4 for The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation

  Access Paper or Ask Questions

Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training


Jun 10, 2021
Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Jun Yu, Xiaoyu Wang, Tongliang Liu

Figure 1 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 2 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 3 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 4 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training

  Access Paper or Ask Questions

Instance Correction for Learning with Open-set Noisy Labels


Jun 01, 2021
Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

Figure 1 for Instance Correction for Learning with Open-set Noisy Labels
Figure 2 for Instance Correction for Learning with Open-set Noisy Labels
Figure 3 for Instance Correction for Learning with Open-set Noisy Labels
Figure 4 for Instance Correction for Learning with Open-set Noisy Labels

  Access Paper or Ask Questions

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels


Jun 01, 2021
Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

Figure 1 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 2 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 3 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 4 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

  Access Paper or Ask Questions

Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching


May 18, 2021
Bofeng Wu, Guocheng Niu, Jun Yu, Xinyan Xiao, Jian Zhang, Hua Wu

Figure 1 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 2 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 3 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 4 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching

  Access Paper or Ask Questions

Removing Adversarial Noise in Class Activation Feature Space


Apr 19, 2021
Dawei Zhou, Nannan Wang, Chunlei Peng, Xinbo Gao, Xiaoyu Wang, Jun Yu, Tongliang Liu

Figure 1 for Removing Adversarial Noise in Class Activation Feature Space
Figure 2 for Removing Adversarial Noise in Class Activation Feature Space
Figure 3 for Removing Adversarial Noise in Class Activation Feature Space
Figure 4 for Removing Adversarial Noise in Class Activation Feature Space

  Access Paper or Ask Questions

QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective


Mar 03, 2021
Jun Yu, Rui Wang, Jun Wu

Figure 1 for QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective
Figure 2 for QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective
Figure 3 for QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective
Figure 4 for QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective

  Access Paper or Ask Questions

Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing


Dec 25, 2020
Jun Yu, Hao Zhou, Yibing Zhan, Dacheng Tao

Figure 1 for Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing
Figure 2 for Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing
Figure 3 for Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing
Figure 4 for Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing

  Access Paper or Ask Questions

Sufficient dimension reduction for classification using principal optimal transport direction


Oct 21, 2020
Cheng Meng, Jun Yu, Jingyi Zhang, Ping Ma, Wenxuan Zhong

Figure 1 for Sufficient dimension reduction for classification using principal optimal transport direction
Figure 2 for Sufficient dimension reduction for classification using principal optimal transport direction
Figure 3 for Sufficient dimension reduction for classification using principal optimal transport direction
Figure 4 for Sufficient dimension reduction for classification using principal optimal transport direction
* 18 pages, 4 figures, to be published in 34th Conference on Neural Information Processing Systems (NeurIPS 2020), add the supplementary material 
  Access Paper or Ask Questions

Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples


Aug 21, 2020
Jinfeng Li, Weifeng Liu, Yicong Zhou, Jun Yu, Dapeng Tao

Figure 1 for Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples
Figure 2 for Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples
Figure 3 for Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples
Figure 4 for Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples

  Access Paper or Ask Questions

Deep Fusion Siamese Network for Automatic Kinship Verification


Jun 07, 2020
Jun Yu, Mengyan Li, Xinlong Hao, Guochen Xie

Figure 1 for Deep Fusion Siamese Network for Automatic Kinship Verification
Figure 2 for Deep Fusion Siamese Network for Automatic Kinship Verification
Figure 3 for Deep Fusion Siamese Network for Automatic Kinship Verification
Figure 4 for Deep Fusion Siamese Network for Automatic Kinship Verification
* 2020 15th IEEE Conference on Automatic Face and Gesture Recognition; 4th Recognizing Families In the Wild (RFIW) 
 * 8 pages, 8 figures 
  Access Paper or Ask Questions

Retrieval of Family Members Using Siamese Neural Network


May 30, 2020
Jun Yu, Guochen Xie, Mengyan Li, Xinlong Hao

Figure 1 for Retrieval of Family Members Using Siamese Neural Network
Figure 2 for Retrieval of Family Members Using Siamese Neural Network
Figure 3 for Retrieval of Family Members Using Siamese Neural Network
Figure 4 for Retrieval of Family Members Using Siamese Neural Network
* 5 pages, 3 figures 
  Access Paper or Ask Questions

Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data


May 21, 2020
Jun Yu, HaiYing Wang, Mingyao Ai, Huiming Zhang

Figure 1 for Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data
Figure 2 for Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data
Figure 3 for Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data
Figure 4 for Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data

  Access Paper or Ask Questions

Deep Multimodal Neural Architecture Search


Apr 25, 2020
Zhou Yu, Yuhao Cui, Jun Yu, Meng Wang, Dacheng Tao, Qi Tian

Figure 1 for Deep Multimodal Neural Architecture Search
Figure 2 for Deep Multimodal Neural Architecture Search
Figure 3 for Deep Multimodal Neural Architecture Search
Figure 4 for Deep Multimodal Neural Architecture Search
* 10 pages, 4 figures 
  Access Paper or Ask Questions

Repulsive Mixture Models of Exponential Family PCA for Clustering


Apr 07, 2020
Maoying Qiao, Tongliang Liu, Jun Yu, Wei Bian, Dacheng Tao

Figure 1 for Repulsive Mixture Models of Exponential Family PCA for Clustering
Figure 2 for Repulsive Mixture Models of Exponential Family PCA for Clustering
Figure 3 for Repulsive Mixture Models of Exponential Family PCA for Clustering
Figure 4 for Repulsive Mixture Models of Exponential Family PCA for Clustering

  Access Paper or Ask Questions

Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach


Apr 06, 2020
Maoying Qiao, Jun Yu, Wei Bian, Dacheng Tao

Figure 1 for Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach
Figure 2 for Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach
Figure 3 for Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach
Figure 4 for Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach

  Access Paper or Ask Questions

Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos


Mar 16, 2020
Yijun Song, Jingwen Wang, Lin Ma, Zhou Yu, Jun Yu

Figure 1 for Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos
Figure 2 for Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos
Figure 3 for Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos
Figure 4 for Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos

  Access Paper or Ask Questions

Multimodal Unified Attention Networks for Vision-and-Language Interactions


Aug 19, 2019
Zhou Yu, Yuhao Cui, Jun Yu, Dacheng Tao, Qi Tian

Figure 1 for Multimodal Unified Attention Networks for Vision-and-Language Interactions
Figure 2 for Multimodal Unified Attention Networks for Vision-and-Language Interactions
Figure 3 for Multimodal Unified Attention Networks for Vision-and-Language Interactions
Figure 4 for Multimodal Unified Attention Networks for Vision-and-Language Interactions
* 11 pages, 7 figures 
  Access Paper or Ask Questions

Deep Modular Co-Attention Networks for Visual Question Answering


Jun 25, 2019
Zhou Yu, Jun Yu, Yuhao Cui, Dacheng Tao, Qi Tian

Figure 1 for Deep Modular Co-Attention Networks for Visual Question Answering
Figure 2 for Deep Modular Co-Attention Networks for Visual Question Answering
Figure 3 for Deep Modular Co-Attention Networks for Visual Question Answering
Figure 4 for Deep Modular Co-Attention Networks for Visual Question Answering
* Accepted at CVPR 2019 
  Access Paper or Ask Questions

Effective degrees of freedom for surface finish defect detection and classification


Jun 20, 2019
Natalya Pya Arnqvist, Blaise Ngendangenzwa, Eric Lindahl, Leif Nilsson, Jun Yu

Figure 1 for Effective degrees of freedom for surface finish defect detection and classification
Figure 2 for Effective degrees of freedom for surface finish defect detection and classification
Figure 3 for Effective degrees of freedom for surface finish defect detection and classification
Figure 4 for Effective degrees of freedom for surface finish defect detection and classification
* 17 pages, 12 figures, 3 tables 
  Access Paper or Ask Questions

ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering


Jun 06, 2019
Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, Dacheng Tao

Figure 1 for ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
Figure 2 for ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
Figure 3 for ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
Figure 4 for ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
* Accepted at AAAI 2019 
  Access Paper or Ask Questions

Multimodal Transformer with Multi-View Visual Representation for Image Captioning


May 20, 2019
Jun Yu, Jing Li, Zhou Yu, Qingming Huang

Figure 1 for Multimodal Transformer with Multi-View Visual Representation for Image Captioning
Figure 2 for Multimodal Transformer with Multi-View Visual Representation for Image Captioning
Figure 3 for Multimodal Transformer with Multi-View Visual Representation for Image Captioning
Figure 4 for Multimodal Transformer with Multi-View Visual Representation for Image Captioning
* submitted to a journal 
  Access Paper or Ask Questions

Single Pixel Reconstruction for One-stage Instance Segmentation


May 17, 2019
Jun Yu, Jinghan Yao, Jian Zhang, Zhou Yu, Dacheng Tao

Figure 1 for Single Pixel Reconstruction for One-stage Instance Segmentation
Figure 2 for Single Pixel Reconstruction for One-stage Instance Segmentation
Figure 3 for Single Pixel Reconstruction for One-stage Instance Segmentation
Figure 4 for Single Pixel Reconstruction for One-stage Instance Segmentation

  Access Paper or Ask Questions