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 Zicheng Liu

Zicheng Liu

Compressing Visual-linguistic Model via Knowledge Distillation


Apr 05, 2021
Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu, Lijuan Wang, Yezhou Yang, Zicheng Liu

Figure 1 for Compressing Visual-linguistic Model via Knowledge Distillation
Figure 2 for Compressing Visual-linguistic Model via Knowledge Distillation
Figure 3 for Compressing Visual-linguistic Model via Knowledge Distillation
Figure 4 for Compressing Visual-linguistic Model via Knowledge Distillation

  Access Paper or Ask Questions

TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking


Apr 03, 2021
Peng Chu, Jiang Wang, Quanzeng You, Haibin Ling, Zicheng Liu

Figure 1 for TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 2 for TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 3 for TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 4 for TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking

  Access Paper or Ask Questions

Mesh Graphormer


Apr 01, 2021
Kevin Lin, Lijuan Wang, Zicheng Liu

Figure 1 for Mesh Graphormer
Figure 2 for Mesh Graphormer
Figure 3 for Mesh Graphormer
Figure 4 for Mesh Graphormer

  Access Paper or Ask Questions

Spatial-Temporal Graph Transformer for Multiple Object Tracking


Apr 01, 2021
Peng Chu, Jiang Wang, Quanzeng You, Haibin Ling, Zicheng Liu

Figure 1 for Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 2 for Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 3 for Spatial-Temporal Graph Transformer for Multiple Object Tracking
Figure 4 for Spatial-Temporal Graph Transformer for Multiple Object Tracking

  Access Paper or Ask Questions

Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification


Mar 25, 2021
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Quanzeng You, Zicheng Liu, Kecheng Zheng, Zhibo Chen

Figure 1 for Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Figure 2 for Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Figure 3 for Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Figure 4 for Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification

  Access Paper or Ask Questions

AutoMix: Unveiling the Power of Mixup


Mar 24, 2021
Zicheng Liu, Siyuan Li, Di Wu, Zhiyuan Chen, Lirong Wu, Jianzhu Guo, Stan Z. Li

Figure 1 for AutoMix: Unveiling the Power of Mixup
Figure 2 for AutoMix: Unveiling the Power of Mixup
Figure 3 for AutoMix: Unveiling the Power of Mixup
Figure 4 for AutoMix: Unveiling the Power of Mixup
* The first version of AutoMix. 13 pages, 11 figures 
  Access Paper or Ask Questions

Revisiting Dynamic Convolution via Matrix Decomposition


Mar 15, 2021
Yunsheng Li, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Ye Yu, Lu Yuan, Zicheng Liu, Mei Chen, Nuno Vasconcelos

Figure 1 for Revisiting Dynamic Convolution via Matrix Decomposition
Figure 2 for Revisiting Dynamic Convolution via Matrix Decomposition
Figure 3 for Revisiting Dynamic Convolution via Matrix Decomposition
Figure 4 for Revisiting Dynamic Convolution via Matrix Decomposition
* Accepted by ICLR 2021 
  Access Paper or Ask Questions

Weak NAS Predictors Are All You Need


Feb 21, 2021
Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan

Figure 1 for Weak NAS Predictors Are All You Need
Figure 2 for Weak NAS Predictors Are All You Need
Figure 3 for Weak NAS Predictors Are All You Need
Figure 4 for Weak NAS Predictors Are All You Need

  Access Paper or Ask Questions

SEED: Self-supervised Distillation For Visual Representation


Jan 12, 2021
Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu

Figure 1 for SEED: Self-supervised Distillation For Visual Representation
Figure 2 for SEED: Self-supervised Distillation For Visual Representation
Figure 3 for SEED: Self-supervised Distillation For Visual Representation
Figure 4 for SEED: Self-supervised Distillation For Visual Representation
* Accepted as a conference paper at ICLR 2021 
  Access Paper or Ask Questions

3D Human motion anticipation and classification


Dec 31, 2020
Emad Barsoum, John Kender, Zicheng Liu

Figure 1 for 3D Human motion anticipation and classification
Figure 2 for 3D Human motion anticipation and classification
Figure 3 for 3D Human motion anticipation and classification
Figure 4 for 3D Human motion anticipation and classification
* arXiv admin note: substantial text overlap with arXiv:1711.09561 
  Access Paper or Ask Questions

End-to-End Human Pose and Mesh Reconstruction with Transformers


Dec 17, 2020
Kevin Lin, Lijuan Wang, Zicheng Liu

Figure 1 for End-to-End Human Pose and Mesh Reconstruction with Transformers
Figure 2 for End-to-End Human Pose and Mesh Reconstruction with Transformers
Figure 3 for End-to-End Human Pose and Mesh Reconstruction with Transformers
Figure 4 for End-to-End Human Pose and Mesh Reconstruction with Transformers

  Access Paper or Ask Questions

MiniVLM: A Smaller and Faster Vision-Language Model


Dec 13, 2020
Jianfeng Wang, Xiaowei Hu, Pengchuan Zhang, Xiujun Li, Lijuan Wang, Lei Zhang, Jianfeng Gao, Zicheng Liu

Figure 1 for MiniVLM: A Smaller and Faster Vision-Language Model
Figure 2 for MiniVLM: A Smaller and Faster Vision-Language Model
Figure 3 for MiniVLM: A Smaller and Faster Vision-Language Model
Figure 4 for MiniVLM: A Smaller and Faster Vision-Language Model

  Access Paper or Ask Questions

MicroNet: Towards Image Recognition with Extremely Low FLOPs


Nov 24, 2020
Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Lei Zhang, Nuno Vasconcelos

Figure 1 for MicroNet: Towards Image Recognition with Extremely Low FLOPs
Figure 2 for MicroNet: Towards Image Recognition with Extremely Low FLOPs
Figure 3 for MicroNet: Towards Image Recognition with Extremely Low FLOPs
Figure 4 for MicroNet: Towards Image Recognition with Extremely Low FLOPs

  Access Paper or Ask Questions

Asymmetric Siamese Networks for Semantic Change Detection


Oct 12, 2020
Kunping Yang, Gui-Song Xia, Zicheng Liu, Bo Du, Wen Yang, Marcello Pelillo

Figure 1 for Asymmetric Siamese Networks for Semantic Change Detection
Figure 2 for Asymmetric Siamese Networks for Semantic Change Detection
Figure 3 for Asymmetric Siamese Networks for Semantic Change Detection
Figure 4 for Asymmetric Siamese Networks for Semantic Change Detection

  Access Paper or Ask Questions

Deep Clustering and Representation Learning that Preserves Geometric Structures


Sep 29, 2020
Lirong Wu, Zicheng Liu, Zelin Zang, Jun Xia, Siyuan Li, Stan. Z Li

Figure 1 for Deep Clustering and Representation Learning that Preserves Geometric Structures
Figure 2 for Deep Clustering and Representation Learning that Preserves Geometric Structures
Figure 3 for Deep Clustering and Representation Learning that Preserves Geometric Structures
Figure 4 for Deep Clustering and Representation Learning that Preserves Geometric Structures
* 20 pages 
  Access Paper or Ask Questions

VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training


Sep 28, 2020
Xiaowei Hu, Xi Yin, Kevin Lin, Lijuan Wang, Lei Zhang, Jianfeng Gao, Zicheng Liu

Figure 1 for VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training
Figure 2 for VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training
Figure 3 for VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training
Figure 4 for VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training

  Access Paper or Ask Questions

Deep Clustering and Representation Learning with Geometric Structure Preservation


Sep 21, 2020
Lirong Wu, Zicheng Liu, Jun Xia, Siyuan Li, Stan. Z Li

Figure 1 for Deep Clustering and Representation Learning with Geometric Structure Preservation
Figure 2 for Deep Clustering and Representation Learning with Geometric Structure Preservation
Figure 3 for Deep Clustering and Representation Learning with Geometric Structure Preservation
Figure 4 for Deep Clustering and Representation Learning with Geometric Structure Preservation
* 20 pages 
  Access Paper or Ask Questions

Dynamic ReLU


Mar 22, 2020
Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, Zicheng Liu

Figure 1 for Dynamic ReLU
Figure 2 for Dynamic ReLU
Figure 3 for Dynamic ReLU
Figure 4 for Dynamic ReLU
* Technical report 
  Access Paper or Ask Questions

Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes


Feb 28, 2020
Kevin Lin, Lijuan Wang, Ying Jin, Zicheng Liu, Ming-Ting Sun

Figure 1 for Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes
Figure 2 for Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes
Figure 3 for Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes
Figure 4 for Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes

  Access Paper or Ask Questions

Dynamic Convolution: Attention over Convolution Kernels


Dec 07, 2019
Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, Zicheng Liu

Figure 1 for Dynamic Convolution: Attention over Convolution Kernels
Figure 2 for Dynamic Convolution: Attention over Convolution Kernels
Figure 3 for Dynamic Convolution: Attention over Convolution Kernels
Figure 4 for Dynamic Convolution: Attention over Convolution Kernels
* Technical report 
  Access Paper or Ask Questions

Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation


Jul 11, 2019
Kevin Lin, Lijuan Wang, Kun Luo, Yinpeng Chen, Zicheng Liu, Ming-Ting Sun

Figure 1 for Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation
Figure 2 for Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation
Figure 3 for Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation
Figure 4 for Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation

  Access Paper or Ask Questions

Double-Head RCNN: Rethinking Classification and Localization for Object Detection


May 31, 2019
Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, Yun Fu

Figure 1 for Double-Head RCNN: Rethinking Classification and Localization for Object Detection
Figure 2 for Double-Head RCNN: Rethinking Classification and Localization for Object Detection
Figure 3 for Double-Head RCNN: Rethinking Classification and Localization for Object Detection
Figure 4 for Double-Head RCNN: Rethinking Classification and Localization for Object Detection

  Access Paper or Ask Questions

Large Scale Incremental Learning


May 30, 2019
Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Yun Fu

Figure 1 for Large Scale Incremental Learning
Figure 2 for Large Scale Incremental Learning
Figure 3 for Large Scale Incremental Learning
Figure 4 for Large Scale Incremental Learning

  Access Paper or Ask Questions

Rethinking Classification and Localization in R-CNN


Apr 13, 2019
Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, Yun Fu

Figure 1 for Rethinking Classification and Localization in R-CNN
Figure 2 for Rethinking Classification and Localization in R-CNN
Figure 3 for Rethinking Classification and Localization in R-CNN
Figure 4 for Rethinking Classification and Localization in R-CNN

  Access Paper or Ask Questions

Incremental Classifier Learning with Generative Adversarial Networks


Feb 02, 2018
Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Zhengyou Zhang, Yun Fu

Figure 1 for Incremental Classifier Learning with Generative Adversarial Networks
Figure 2 for Incremental Classifier Learning with Generative Adversarial Networks
Figure 3 for Incremental Classifier Learning with Generative Adversarial Networks
Figure 4 for Incremental Classifier Learning with Generative Adversarial Networks
* 10 pages, 6 figures 
  Access Paper or Ask Questions

HP-GAN: Probabilistic 3D human motion prediction via GAN


Nov 27, 2017
Emad Barsoum, John Kender, Zicheng Liu

Figure 1 for HP-GAN: Probabilistic 3D human motion prediction via GAN
Figure 2 for HP-GAN: Probabilistic 3D human motion prediction via GAN
Figure 3 for HP-GAN: Probabilistic 3D human motion prediction via GAN
Figure 4 for HP-GAN: Probabilistic 3D human motion prediction via GAN

  Access Paper or Ask Questions

Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors


May 28, 2017
Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto

Figure 1 for Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors
Figure 2 for Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors
Figure 3 for Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors
Figure 4 for Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors
* 13 pages, 6 figures, 5 tables 
  Access Paper or Ask Questions

A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories


Apr 26, 2017
Weiyao Lin, Yang Zhou, Hongteng Xu, Junchi Yan, Mingliang Xu, Jianxin Wu, Zicheng Liu

Figure 1 for A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Figure 2 for A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Figure 3 for A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Figure 4 for A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
* IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2016.2608884, 2016. Code for our work is available at http://min.sjtu.edu.cn/lwydemo/Trajectory%20analysis.htm 
  Access Paper or Ask Questions