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 Zhiwu Lu

Zhiwu Lu

Pre-Trained Models: Past, Present and Future


Jun 15, 2021
Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu

Figure 1 for Pre-Trained Models: Past, Present and Future
Figure 2 for Pre-Trained Models: Past, Present and Future
Figure 3 for Pre-Trained Models: Past, Present and Future
Figure 4 for Pre-Trained Models: Past, Present and Future

  Access Paper or Ask Questions

HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers


Jun 11, 2021
Mingyu Ding, Xiaochen Lian, Linjie Yang, Peng Wang, Xiaojie Jin, Zhiwu Lu, Ping Luo

Figure 1 for HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Figure 2 for HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Figure 3 for HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Figure 4 for HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
* Accepted by CVPR 2021 (Oral) 
  Access Paper or Ask Questions

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition


May 30, 2021
Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Zhiwu Lu, Jun He, Xiaoyong Du

Figure 1 for SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
Figure 2 for SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
Figure 3 for SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
Figure 4 for SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
* 14 pages, 7 figures 
  Access Paper or Ask Questions

Learning Versatile Neural Architectures by Propagating Network Codes


Mar 24, 2021
Mingyu Ding, Yuqi Huo, Haoyu Lu, Linjie Yang, Zhe Wang, Zhiwu Lu, Jingdong Wang, Ping Luo

Figure 1 for Learning Versatile Neural Architectures by Propagating Network Codes
Figure 2 for Learning Versatile Neural Architectures by Propagating Network Codes
Figure 3 for Learning Versatile Neural Architectures by Propagating Network Codes
Figure 4 for Learning Versatile Neural Architectures by Propagating Network Codes

  Access Paper or Ask Questions

WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training


Mar 19, 2021
Yuqi Huo, Manli Zhang, Guangzhen Liu, Haoyu Lu, Yizhao Gao, Guoxing Yang, Jingyuan Wen, Heng Zhang, Baogui Xu, Weihao Zheng, Zongzheng Xi, Yueqian Yang, Anwen Hu, Jinming Zhao, Ruichen Li, Yida Zhao, Liang Zhang, Yuqing Song, Xin Hong, Wanqing Cui, Danyang Hou, Yingyan Li, Junyi Li, Peiyu Liu, Zheng Gong, Chuhao Jin, Yuchong Sun, Shizhe Chen, Zhiwu Lu, Zhicheng Dou, Qin Jin, Yanyan Lan, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen

Figure 1 for WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Figure 2 for WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Figure 3 for WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Figure 4 for WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
* This paper is the outcome of the Chinese multi-modal pre-training project called 'WenLan' 
  Access Paper or Ask Questions

Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning


Jan 23, 2021
Yizhao Gao, Nanyi Fei, Guangzhen Liu, Zhiwu Lu, Tao Xiang, Songfang Huang

Figure 1 for Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
Figure 2 for Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
Figure 3 for Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
Figure 4 for Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning

  Access Paper or Ask Questions

Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding


Dec 02, 2020
Jiechao Guan, Zhiwu Lu, Tao Xiang, Timothy Hospedales

Figure 1 for Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
Figure 2 for Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
Figure 3 for Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
Figure 4 for Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
* 14 pages, 2 figures 
  Access Paper or Ask Questions

Counterfactual VQA: A Cause-Effect Look at Language Bias


Jun 15, 2020
Yulei Niu, Kaihua Tang, Hanwang Zhang, Zhiwu Lu, Xian-Sheng Hua, Ji-Rong Wen

Figure 1 for Counterfactual VQA: A Cause-Effect Look at Language Bias
Figure 2 for Counterfactual VQA: A Cause-Effect Look at Language Bias
Figure 3 for Counterfactual VQA: A Cause-Effect Look at Language Bias
Figure 4 for Counterfactual VQA: A Cause-Effect Look at Language Bias

  Access Paper or Ask Questions

Domain-Adaptive Few-Shot Learning


Mar 19, 2020
An Zhao, Mingyu Ding, Zhiwu Lu, Tao Xiang, Yulei Niu, Jiechao Guan, Ji-Rong Wen, Ping Luo

Figure 1 for Domain-Adaptive Few-Shot Learning
Figure 2 for Domain-Adaptive Few-Shot Learning
Figure 3 for Domain-Adaptive Few-Shot Learning
Figure 4 for Domain-Adaptive Few-Shot Learning

  Access Paper or Ask Questions

Meta-Learning across Meta-Tasks for Few-Shot Learning


Mar 09, 2020
Nanyi Fei, Zhiwu Lu, Yizhao Gao, Jia Tian, Tao Xiang, Ji-Rong Wen

Figure 1 for Meta-Learning across Meta-Tasks for Few-Shot Learning
Figure 2 for Meta-Learning across Meta-Tasks for Few-Shot Learning
Figure 3 for Meta-Learning across Meta-Tasks for Few-Shot Learning
Figure 4 for Meta-Learning across Meta-Tasks for Few-Shot Learning
* Our code is at https://github.com/neilfei/MLMT-FSL 
  Access Paper or Ask Questions

AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning


Mar 09, 2020
Jianhong Zhang, Manli Zhang, Zhiwu Lu, Tao Xiang, Jirong Wen

Figure 1 for AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
Figure 2 for AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
Figure 3 for AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
Figure 4 for AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
* The code is at github - https://github.com/RiceZJH/AdarGCN 
  Access Paper or Ask Questions

Few-Shot Learning as Domain Adaptation: Algorithm and Analysis


Feb 12, 2020
Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen

Figure 1 for Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
Figure 2 for Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
Figure 3 for Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
Figure 4 for Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
* Github URL https://github.com/JiechaoGuan/FSL-DAPNA 
  Access Paper or Ask Questions

Learning Depth-Guided Convolutions for Monocular 3D Object Detection


Dec 13, 2019
Mingyu Ding, Yuqi Huo, Hongwei Yi, Zhe Wang, Jianping Shi, Zhiwu Lu, Ping Luo

Figure 1 for Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Figure 2 for Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Figure 3 for Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Figure 4 for Learning Depth-Guided Convolutions for Monocular 3D Object Detection
* 12 pages, 8 figures, modify email and add code 
  Access Paper or Ask Questions

Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow


Nov 28, 2019
Mingyu Ding, Zhe Wang, Bolei Zhou, Jianping Shi, Zhiwu Lu, Ping Luo

Figure 1 for Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Figure 2 for Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Figure 3 for Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Figure 4 for Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
* Published in AAAI 2020 
  Access Paper or Ask Questions

Mobile Video Action Recognition


Aug 27, 2019
Yuqi Huo, Xiaoli Xu, Yao Lu, Yulei Niu, Zhiwu Lu, Ji-Rong Wen

Figure 1 for Mobile Video Action Recognition
Figure 2 for Mobile Video Action Recognition
Figure 3 for Mobile Video Action Recognition
Figure 4 for Mobile Video Action Recognition

  Access Paper or Ask Questions

Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions


Jul 08, 2019
Yulei Niu, Hanwang Zhang, Zhiwu Lu, Shih-Fu Chang

Figure 1 for Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
Figure 2 for Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
Figure 3 for Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
Figure 4 for Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
* Accepted as regular paper in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Substantial text overlap with arXiv:1712.01892 
  Access Paper or Ask Questions

Face-Focused Cross-Stream Network for Deception Detection in Videos


Dec 11, 2018
Mingyu Ding, An Zhao, Zhiwu Lu, Tao Xiang, Ji-Rong Wen

Figure 1 for Face-Focused Cross-Stream Network for Deception Detection in Videos
Figure 2 for Face-Focused Cross-Stream Network for Deception Detection in Videos
Figure 3 for Face-Focused Cross-Stream Network for Deception Detection in Videos
Figure 4 for Face-Focused Cross-Stream Network for Deception Detection in Videos

  Access Paper or Ask Questions

Zero-Shot Learning with Sparse Attribute Propagation


Dec 11, 2018
Nanyi Fei, Jiajun Liu, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen

Figure 1 for Zero-Shot Learning with Sparse Attribute Propagation
Figure 2 for Zero-Shot Learning with Sparse Attribute Propagation
Figure 3 for Zero-Shot Learning with Sparse Attribute Propagation
Figure 4 for Zero-Shot Learning with Sparse Attribute Propagation

  Access Paper or Ask Questions

Recursive Visual Attention in Visual Dialog


Dec 06, 2018
Yulei Niu, Hanwang Zhang, Manli Zhang, Jianhong Zhang, Zhiwu Lu, Ji-Rong Wen

Figure 1 for Recursive Visual Attention in Visual Dialog
Figure 2 for Recursive Visual Attention in Visual Dialog
Figure 3 for Recursive Visual Attention in Visual Dialog
Figure 4 for Recursive Visual Attention in Visual Dialog

  Access Paper or Ask Questions

Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning


Oct 19, 2018
Zhiwu Lu, Jiechao Guan, Aoxue Li, Tao Xiang, An Zhao, Ji-Rong Wen

Figure 1 for Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
Figure 2 for Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
Figure 3 for Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
Figure 4 for Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
* Submitted to IEEE TPAMI 
  Access Paper or Ask Questions

Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation


Oct 19, 2018
Yulei Niu, Zhiwu Lu, Ji-Rong Wen, Tao Xiang, Shih-Fu Chang

Figure 1 for Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
Figure 2 for Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
Figure 3 for Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
Figure 4 for Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
* Submited to IEEE TIP 
  Access Paper or Ask Questions

Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning


Oct 19, 2018
Aoxue Li, Zhiwu Lu, Jiechao Guan, Tao Xiang, Liwei Wang, Ji-Rong Wen

Figure 1 for Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Figure 2 for Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Figure 3 for Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Figure 4 for Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
* Submitted to IJCV 
  Access Paper or Ask Questions