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

SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning


Nov 25, 2021
Kevin Lin, Linjie Li, Chung-Ching Lin, Faisal Ahmed, Zhe Gan, Zicheng Liu, Yumao Lu, Lijuan Wang

Figure 1 for SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
Figure 2 for SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
Figure 3 for SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
Figure 4 for SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning

  Access Paper or Ask Questions

An Empirical Study of Training End-to-End Vision-and-Language Transformers


Nov 25, 2021
Zi-Yi Dou, Yichong Xu, Zhe Gan, Jianfeng Wang, Shuohang Wang, Lijuan Wang, Chenguang Zhu, Pengchuan Zhang, Lu Yuan, Nanyun Peng, Zicheng Liu, Michael Zeng

Figure 1 for An Empirical Study of Training End-to-End Vision-and-Language Transformers
Figure 2 for An Empirical Study of Training End-to-End Vision-and-Language Transformers
Figure 3 for An Empirical Study of Training End-to-End Vision-and-Language Transformers
Figure 4 for An Empirical Study of Training End-to-End Vision-and-Language Transformers

  Access Paper or Ask Questions

VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling


Nov 24, 2021
Tsu-Jui Fu, Linjie Li, Zhe Gan, Kevin Lin, William Yang Wang, Lijuan Wang, Zicheng Liu

Figure 1 for VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
Figure 2 for VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
Figure 3 for VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
Figure 4 for VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
* Code is available at https://github.com/tsujuifu/pytorch_violet 
  Access Paper or Ask Questions

Scaling Up Vision-Language Pre-training for Image Captioning


Nov 24, 2021
Xiaowei Hu, Zhe Gan, Jianfeng Wang, Zhengyuan Yang, Zicheng Liu, Yumao Lu, Lijuan Wang

Figure 1 for Scaling Up Vision-Language Pre-training for Image Captioning
Figure 2 for Scaling Up Vision-Language Pre-training for Image Captioning
Figure 3 for Scaling Up Vision-Language Pre-training for Image Captioning
Figure 4 for Scaling Up Vision-Language Pre-training for Image Captioning

  Access Paper or Ask Questions

Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling


Nov 23, 2021
Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Faisal Ahmed, Zicheng Liu, Yumao Lu, Lijuan Wang

Figure 1 for Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling
Figure 2 for Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling
Figure 3 for Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling
Figure 4 for Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling

  Access Paper or Ask Questions

Florence: A New Foundation Model for Computer Vision


Nov 22, 2021
Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, Pengchuan Zhang

Figure 1 for Florence: A New Foundation Model for Computer Vision
Figure 2 for Florence: A New Foundation Model for Computer Vision
Figure 3 for Florence: A New Foundation Model for Computer Vision
Figure 4 for Florence: A New Foundation Model for Computer Vision

  Access Paper or Ask Questions

UFO: A UniFied TransfOrmer for Vision-Language Representation Learning


Nov 19, 2021
Jianfeng Wang, Xiaowei Hu, Zhe Gan, Zhengyuan Yang, Xiyang Dai, Zicheng Liu, Yumao Lu, Lijuan Wang

Figure 1 for UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Figure 2 for UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Figure 3 for UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Figure 4 for UFO: A UniFied TransfOrmer for Vision-Language Representation Learning

  Access Paper or Ask Questions

Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering


Nov 13, 2021
Zicheng Liu, Mayank Roy, Dilip K. Prasad, Krishna Agarwal

Figure 1 for Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering
Figure 2 for Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering
Figure 3 for Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering
Figure 4 for Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering

  Access Paper or Ask Questions

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop


Oct 14, 2021
Peng Jin, Xitong Zhang, Yinpeng Chen, Sharon Xiaolei Huang, Zicheng Liu, Youzuo Lin

Figure 1 for Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
Figure 2 for Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
Figure 3 for Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
Figure 4 for Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

  Access Paper or Ask Questions

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA


Sep 10, 2021
Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, Lijuan Wang

Figure 1 for An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
Figure 2 for An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
Figure 3 for An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
Figure 4 for An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

  Access Paper or Ask Questions

Mobile-Former: Bridging MobileNet and Transformer


Aug 12, 2021
Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Xiaoyi Dong, Lu Yuan, Zicheng Liu

Figure 1 for Mobile-Former: Bridging MobileNet and Transformer
Figure 2 for Mobile-Former: Bridging MobileNet and Transformer
Figure 3 for Mobile-Former: Bridging MobileNet and Transformer
Figure 4 for Mobile-Former: Bridging MobileNet and Transformer

  Access Paper or Ask Questions

MicroNet: Improving Image Recognition with Extremely Low FLOPs


Aug 12, 2021
Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Lei Zhang, Nuno Vasconcelos

Figure 1 for MicroNet: Improving Image Recognition with Extremely Low FLOPs
Figure 2 for MicroNet: Improving Image Recognition with Extremely Low FLOPs
Figure 3 for MicroNet: Improving Image Recognition with Extremely Low FLOPs
Figure 4 for MicroNet: Improving Image Recognition with Extremely Low FLOPs
* ICCV 2021, code is available at https://github.com/liyunsheng13/micronet}{https://github.com/liyunsheng13/micronet 
  Access Paper or Ask Questions

OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning


Aug 08, 2021
Sheng Liu, Kevin Lin, Lijuan Wang, Junsong Yuan, Zicheng Liu

Figure 1 for OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
Figure 2 for OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
Figure 3 for OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
Figure 4 for OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
* 10 pages 
  Access Paper or Ask Questions

Is Object Detection Necessary for Human-Object Interaction Recognition?


Jul 27, 2021
Ying Jin, Yinpeng Chen, Lijuan Wang, Jianfeng Wang, Pei Yu, Zicheng Liu, Jenq-Neng Hwang

Figure 1 for Is Object Detection Necessary for Human-Object Interaction Recognition?
Figure 2 for Is Object Detection Necessary for Human-Object Interaction Recognition?
Figure 3 for Is Object Detection Necessary for Human-Object Interaction Recognition?
Figure 4 for Is Object Detection Necessary for Human-Object Interaction Recognition?

  Access Paper or Ask Questions

A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams


Jul 16, 2021
Yifeng Zhao, Zicheng Liu, Pei Zhang, S. A. Galindo-Torres, Stan Z. Li

Figure 1 for A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
Figure 2 for A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
Figure 3 for A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
Figure 4 for A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
* Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file Subjects 
  Access Paper or Ask Questions

End-to-End Semi-Supervised Object Detection with Soft Teacher


Jun 17, 2021
Mengde Xu, Zheng Zhang, Han Hu, Jianfeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu

Figure 1 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 2 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 3 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 4 for End-to-End Semi-Supervised Object Detection with Soft Teacher

  Access Paper or Ask Questions

An interpretable prediction model for longitudinal dispersion coefficient in natural streams based on evolutionary symbolic regression network


Jun 17, 2021
Yifeng Zhao, Zicheng Liu, Pei Zhang, Stan Z. Li, S. A. Galindo-Torres

Figure 1 for An interpretable prediction model for longitudinal dispersion coefficient in natural streams based on evolutionary symbolic regression network
Figure 2 for An interpretable prediction model for longitudinal dispersion coefficient in natural streams based on evolutionary symbolic regression network
Figure 3 for An interpretable prediction model for longitudinal dispersion coefficient in natural streams based on evolutionary symbolic regression network
Figure 4 for An interpretable prediction model for longitudinal dispersion coefficient in natural streams based on evolutionary symbolic regression network
* Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file Subjects 
  Access Paper or Ask Questions

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation


Jun 08, 2021
Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai, Yu Cheng, Luowei Zhou, Xin Eric Wang, William Yang Wang, Tamara Lee Berg, Mohit Bansal, Jingjing Liu, Lijuan Wang, Zicheng Liu

Figure 1 for VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
Figure 2 for VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
Figure 3 for VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
Figure 4 for VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
* VALUE is available at https://value-leaderboard.github.io/ 
  Access Paper or Ask Questions

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