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 Jiwen Lu

Jiwen Lu

Data-Efficient Instance Segmentation with a Single GPU


Oct 08, 2021
Pengyu Chen, Wanhua Li, Jiwen Lu

Figure 1 for Data-Efficient Instance Segmentation with a Single GPU
Figure 2 for Data-Efficient Instance Segmentation with a Single GPU
Figure 3 for Data-Efficient Instance Segmentation with a Single GPU
Figure 4 for Data-Efficient Instance Segmentation with a Single GPU
* Technical report 
  Access Paper or Ask Questions

Structure-Preserving Image Super-Resolution


Sep 26, 2021
Cheng Ma, Yongming Rao, Jiwen Lu, Jie Zhou

Figure 1 for Structure-Preserving Image Super-Resolution
Figure 2 for Structure-Preserving Image Super-Resolution
Figure 3 for Structure-Preserving Image Super-Resolution
Figure 4 for Structure-Preserving Image Super-Resolution
* Accepted by T-PAMI. Journal version of arXiv:2003.13081 (CVPR 2020) 
  Access Paper or Ask Questions

Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical


Sep 06, 2021
Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi, Jianjiang Feng, Jie Zhou

Figure 1 for Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
Figure 2 for Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
Figure 3 for Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
Figure 4 for Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
* IEEE Transactions on Image Processing, vol. 30, pp. 4947-4961, 2021 
 * Accepted by IEEE Transactions on Image Processing (TIP) 
  Access Paper or Ask Questions

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo


Sep 03, 2021
Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie Zhou

Figure 1 for NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Figure 2 for NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Figure 3 for NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Figure 4 for NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
* To appear in ICCV 2021 (Oral). Project page: https://weiyithu.github.io/NerfingMVS/ 
  Access Paper or Ask Questions

Diverse Sample Generation: Pushing the Limit of Data-free Quantization


Sep 03, 2021
Haotong Qin, Yifu Ding, Xiangguo Zhang, Aoyu Li, Jiakai Wang, Xianglong Liu, Jiwen Lu

Figure 1 for Diverse Sample Generation: Pushing the Limit of Data-free Quantization
Figure 2 for Diverse Sample Generation: Pushing the Limit of Data-free Quantization
Figure 3 for Diverse Sample Generation: Pushing the Limit of Data-free Quantization
Figure 4 for Diverse Sample Generation: Pushing the Limit of Data-free Quantization

  Access Paper or Ask Questions

Deep Relational Metric Learning


Aug 23, 2021
Wenzhao Zheng, Borui Zhang, Jiwen Lu, Jie Zhou

Figure 1 for Deep Relational Metric Learning
Figure 2 for Deep Relational Metric Learning
Figure 3 for Deep Relational Metric Learning
Figure 4 for Deep Relational Metric Learning
* Accepted to ICCV 2021. Source code available at https://github.com/zbr17/DRML 
  Access Paper or Ask Questions

PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers


Aug 19, 2021
Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu, Jiwen Lu, Jie Zhou

Figure 1 for PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
Figure 2 for PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
Figure 3 for PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
Figure 4 for PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
* Accepted to ICCV 2021 (Oral Presentation) 
  Access Paper or Ask Questions

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification


Aug 19, 2021
Yongming Rao, Guangyi Chen, Jiwen Lu, Jie Zhou

Figure 1 for Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Figure 2 for Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Figure 3 for Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Figure 4 for Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Group-aware Contrastive Regression for Action Quality Assessment


Aug 17, 2021
Xumin Yu, Yongming Rao, Wenliang Zhao, Jiwen Lu, Jie Zhou

Figure 1 for Group-aware Contrastive Regression for Action Quality Assessment
Figure 2 for Group-aware Contrastive Regression for Action Quality Assessment
Figure 3 for Group-aware Contrastive Regression for Action Quality Assessment
Figure 4 for Group-aware Contrastive Regression for Action Quality Assessment
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection


Aug 17, 2021
Yongming Rao, Benlin Liu, Yi Wei, Jiwen Lu, Cho-Jui Hsieh, Jie Zhou

Figure 1 for RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
Figure 2 for RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
Figure 3 for RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
Figure 4 for RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Masked Face Recognition Challenge: The WebFace260M Track Report


Aug 16, 2021
Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, Junjie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jia Guo, Jiwen Lu, Dalong Du, Jie Zhou

Figure 1 for Masked Face Recognition Challenge: The WebFace260M Track Report
Figure 2 for Masked Face Recognition Challenge: The WebFace260M Track Report
Figure 3 for Masked Face Recognition Challenge: The WebFace260M Track Report
Figure 4 for Masked Face Recognition Challenge: The WebFace260M Track Report
* The WebFace260M Track of ICCV-21 MFR Challenge is still open in https://www.face-benchmark.org/challenge.html 
  Access Paper or Ask Questions

Towards Interpretable Deep Metric Learning with Structural Matching


Aug 12, 2021
Wenliang Zhao, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie Zhou

Figure 1 for Towards Interpretable Deep Metric Learning with Structural Matching
Figure 2 for Towards Interpretable Deep Metric Learning with Structural Matching
Figure 3 for Towards Interpretable Deep Metric Learning with Structural Matching
Figure 4 for Towards Interpretable Deep Metric Learning with Structural Matching
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Person Re-identification via Attention Pyramid


Aug 11, 2021
Guangyi Chen, Tianpei Gu, Jiwen Lu, Jin-An Bao, Jie Zhou

Figure 1 for Person Re-identification via Attention Pyramid
Figure 2 for Person Re-identification via Attention Pyramid
Figure 3 for Person Re-identification via Attention Pyramid
Figure 4 for Person Re-identification via Attention Pyramid
* Accepted by IEEE Transcations on Image Processing. Code available at https://github.com/CHENGY12/APNet 
  Access Paper or Ask Questions

Instance Similarity Learning for Unsupervised Feature Representation


Aug 05, 2021
Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie Zhou

Figure 1 for Instance Similarity Learning for Unsupervised Feature Representation
Figure 2 for Instance Similarity Learning for Unsupervised Feature Representation
Figure 3 for Instance Similarity Learning for Unsupervised Feature Representation
Figure 4 for Instance Similarity Learning for Unsupervised Feature Representation
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Generalizable Mixed-Precision Quantization via Attribution Rank Preservation


Aug 05, 2021
Ziwei Wang, Han Xiao, Jiwen Lu, Jie Zhou

Figure 1 for Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
Figure 2 for Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
Figure 3 for Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
Figure 4 for Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Personalized Trajectory Prediction via Distribution Discrimination


Jul 29, 2021
Guangyi Chen, Junlong Li, Nuoxing Zhou, Liangliang Ren, Jiwen Lu

Figure 1 for Personalized Trajectory Prediction via Distribution Discrimination
Figure 2 for Personalized Trajectory Prediction via Distribution Discrimination
Figure 3 for Personalized Trajectory Prediction via Distribution Discrimination
Figure 4 for Personalized Trajectory Prediction via Distribution Discrimination
* Accepted to ICCV 2021. Code: https://github.com/CHENGY12/DisDis 
  Access Paper or Ask Questions

Human Trajectory Prediction via Counterfactual Analysis


Jul 29, 2021
Guangyi Chen, Junlong Li, Jiwen Lu, Jie Zhou

Figure 1 for Human Trajectory Prediction via Counterfactual Analysis
Figure 2 for Human Trajectory Prediction via Counterfactual Analysis
Figure 3 for Human Trajectory Prediction via Counterfactual Analysis
Figure 4 for Human Trajectory Prediction via Counterfactual Analysis
* Accepted to ICCV 2021. Code: https://github.com/CHENGY12/CausalHTP 
  Access Paper or Ask Questions

Similarity-Aware Fusion Network for 3D Semantic Segmentation


Jul 17, 2021
Linqing Zhao, Jiwen Lu, Jie Zhou

Figure 1 for Similarity-Aware Fusion Network for 3D Semantic Segmentation
Figure 2 for Similarity-Aware Fusion Network for 3D Semantic Segmentation
Figure 3 for Similarity-Aware Fusion Network for 3D Semantic Segmentation
Figure 4 for Similarity-Aware Fusion Network for 3D Semantic Segmentation
* Accepted by 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021) 
  Access Paper or Ask Questions

Global Filter Networks for Image Classification


Jul 01, 2021
Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, Jie Zhou

Figure 1 for Global Filter Networks for Image Classification
Figure 2 for Global Filter Networks for Image Classification
Figure 3 for Global Filter Networks for Image Classification
Figure 4 for Global Filter Networks for Image Classification
* Project page: https://gfnet.ivg-research.xyz/ 
  Access Paper or Ask Questions

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification


Jun 03, 2021
Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, Cho-Jui Hsieh

Figure 1 for DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Figure 2 for DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Figure 3 for DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Figure 4 for DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
* Project page: https://dynamicvit.ivg-research.xyz/ 
  Access Paper or Ask Questions

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection


May 17, 2021
Yi Wei, Shang Su, Jiwen Lu, Jie Zhou

Figure 1 for FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
Figure 2 for FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
Figure 3 for FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
Figure 4 for FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
* Accepted to ICRA 2021 
  Access Paper or Ask Questions

SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation


Apr 07, 2021
Jiabin Zhang, Zheng Zhu, Jiwen Lu, Junjie Huang, Guan Huang, Jie Zhou

Figure 1 for SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
Figure 2 for SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
Figure 3 for SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
Figure 4 for SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
* Accepted by AAAI2021 
  Access Paper or Ask Questions

Objects are Different: Flexible Monocular 3D Object Detection


Apr 06, 2021
Yunpeng Zhang, Jiwen Lu, Jie Zhou

Figure 1 for Objects are Different: Flexible Monocular 3D Object Detection
Figure 2 for Objects are Different: Flexible Monocular 3D Object Detection
Figure 3 for Objects are Different: Flexible Monocular 3D Object Detection
Figure 4 for Objects are Different: Flexible Monocular 3D Object Detection
* Accepted in CVPR 2021 
  Access Paper or Ask Questions

Meta-Mining Discriminative Samples for Kinship Verification


Mar 28, 2021
Wanhua Li, Shiwei Wang, Jiwen Lu, Jianjiang Feng, Jie Zhou

Figure 1 for Meta-Mining Discriminative Samples for Kinship Verification
Figure 2 for Meta-Mining Discriminative Samples for Kinship Verification
Figure 3 for Meta-Mining Discriminative Samples for Kinship Verification
Figure 4 for Meta-Mining Discriminative Samples for Kinship Verification
* Accepted by CVPR2021 
  Access Paper or Ask Questions

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes


Mar 27, 2021
Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou

Figure 1 for Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
Figure 2 for Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
Figure 3 for Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
Figure 4 for Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
* Accepted by the CVPR 2021. Project: https://sstzal.github.io/STAR-FC/ 
  Access Paper or Ask Questions

Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression


Mar 25, 2021
Wanhua Li, Xiaoke Huang, Jiwen Lu, Jianjiang Feng, Jie Zhou

Figure 1 for Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
Figure 2 for Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
Figure 3 for Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
Figure 4 for Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
* Accepted by CVPR2021. Code is available at https://github.com/Li-Wanhua/POEs 
  Access Paper or Ask Questions

WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition


Mar 06, 2021
Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, Junjie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jiwen Lu, Dalong Du, Jie Zhou

Figure 1 for WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Figure 2 for WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Figure 3 for WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Figure 4 for WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
* Accepted by CVPR2021. Benchmark website is https://www.face-benchmark.org 
  Access Paper or Ask Questions

Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search


Feb 02, 2021
Cheng Ma, Jiwen Lu, Jie Zhou

Figure 1 for Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
Figure 2 for Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
Figure 3 for Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
Figure 4 for Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
* IEEE Transactions on Multimedia, 2020 
  Access Paper or Ask Questions