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 Chenxi Liu

Chenxi Liu

Scene Transformer: A unified multi-task model for behavior prediction and planning


Jun 15, 2021
Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan, Zhengdong Zhang, Hao-Tien Lewis Chiang, Jeffrey Ling, Rebecca Roelofs, Alex Bewley, Chenxi Liu, Ashish Venugopal, David Weiss, Ben Sapp, Zhifeng Chen, Jonathon Shlens

Figure 1 for Scene Transformer: A unified multi-task model for behavior prediction and planning
Figure 2 for Scene Transformer: A unified multi-task model for behavior prediction and planning
Figure 3 for Scene Transformer: A unified multi-task model for behavior prediction and planning
Figure 4 for Scene Transformer: A unified multi-task model for behavior prediction and planning

  Access Paper or Ask Questions

Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement


Jun 11, 2021
Zefan Li, Chenxi Liu, Alan Yuille, Bingbing Ni, Wenjun Zhang, Wen Gao

Figure 1 for Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
Figure 2 for Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
Figure 3 for Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
Figure 4 for Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
* Accepted by the IEEE conference on computer vision and pattern recognition. 2021 
  Access Paper or Ask Questions

Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset


Apr 20, 2021
Scott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu, Hang Zhao, Sabeek Pradhan, Yuning Chai, Ben Sapp, Charles Qi, Yin Zhou, Zoey Yang, Aurelien Chouard, Pei Sun, Jiquan Ngiam, Vijay Vasudevan, Alexander McCauley, Jonathon Shlens, Dragomir Anguelov

Figure 1 for Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
Figure 2 for Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
Figure 3 for Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
Figure 4 for Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
* 15 pages, 10 figures 
  Access Paper or Ask Questions

Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network


Feb 26, 2021
Peng Yang, Kun Guo, Xing Xi, Tony Q. S. Quek, Xianbin Cao, Chenxi Liu

Figure 1 for Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network
Figure 2 for Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network
Figure 3 for Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network
Figure 4 for Fresh, Fair and Energy-Efficient Content Provision in a Private and Cache-Enabled UAV Network

  Access Paper or Ask Questions

Are Labels Necessary for Neural Architecture Search?


Mar 26, 2020
Chenxi Liu, Piotr Dollár, Kaiming He, Ross Girshick, Alan Yuille, Saining Xie

Figure 1 for Are Labels Necessary for Neural Architecture Search?
Figure 2 for Are Labels Necessary for Neural Architecture Search?
Figure 3 for Are Labels Necessary for Neural Architecture Search?
Figure 4 for Are Labels Necessary for Neural Architecture Search?

  Access Paper or Ask Questions

Identifying Model Weakness with Adversarial Examiner


Nov 25, 2019
Michelle Shu, Chenxi Liu, Weichao Qiu, Alan Yuille

Figure 1 for Identifying Model Weakness with Adversarial Examiner
Figure 2 for Identifying Model Weakness with Adversarial Examiner
Figure 3 for Identifying Model Weakness with Adversarial Examiner
Figure 4 for Identifying Model Weakness with Adversarial Examiner
* To appear in AAAI-20 
  Access Paper or Ask Questions

Rethinking Normalization and Elimination Singularity in Neural Networks


Nov 21, 2019
Siyuan Qiao, Huiyu Wang, Chenxi Liu, Wei Shen, Alan Yuille

Figure 1 for Rethinking Normalization and Elimination Singularity in Neural Networks
Figure 2 for Rethinking Normalization and Elimination Singularity in Neural Networks
Figure 3 for Rethinking Normalization and Elimination Singularity in Neural Networks
Figure 4 for Rethinking Normalization and Elimination Singularity in Neural Networks

  Access Paper or Ask Questions

V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation


Jun 06, 2019
Zhuotun Zhu, Chenxi Liu, Dong Yang, Alan Yuille, Daguang Xu

Figure 1 for V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
Figure 2 for V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
Figure 3 for V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
Figure 4 for V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
* 8 pages, 1 figure for the paper; 3 more figures in the 1-page supplementary 
  Access Paper or Ask Questions

Weight Standardization


Mar 25, 2019
Siyuan Qiao, Huiyu Wang, Chenxi Liu, Wei Shen, Alan Yuille

Figure 1 for Weight Standardization
Figure 2 for Weight Standardization
Figure 3 for Weight Standardization
Figure 4 for Weight Standardization

  Access Paper or Ask Questions

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation


Jan 10, 2019
Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan Yuille, Li Fei-Fei

Figure 1 for Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Figure 2 for Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Figure 3 for Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Figure 4 for Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

  Access Paper or Ask Questions

CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions


Jan 03, 2019
Runtao Liu, Chenxi Liu, Yutong Bai, Alan Yuille

Figure 1 for CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Figure 2 for CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Figure 3 for CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Figure 4 for CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
* All data and code concerning CLEVR-Ref+ and IEP-Ref have been released at https://cs.jhu.edu/~cxliu/2019/clevr-ref+ 
  Access Paper or Ask Questions

Adversarial Attacks Beyond the Image Space


Sep 10, 2018
Xiaohui Zeng, Chenxi Liu, Yu-Siang Wang, Weichao Qiu, Lingxi Xie, Yu-Wing Tai, Chi Keung Tang, Alan L. Yuille

Figure 1 for Adversarial Attacks Beyond the Image Space
Figure 2 for Adversarial Attacks Beyond the Image Space
Figure 3 for Adversarial Attacks Beyond the Image Space
Figure 4 for Adversarial Attacks Beyond the Image Space
* 10 pages, 4 figures (new method and experiments added beyond v2) 
  Access Paper or Ask Questions

Progressive Neural Architecture Search


Jul 26, 2018
Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

Figure 1 for Progressive Neural Architecture Search
Figure 2 for Progressive Neural Architecture Search
Figure 3 for Progressive Neural Architecture Search
Figure 4 for Progressive Neural Architecture Search
* To appear in ECCV 2018 as oral. The code and checkpoint for PNASNet-5 trained on ImageNet (both Mobile and Large) can now be downloaded from https://github.com/tensorflow/models/tree/master/research/slim#Pretrained. Also see https://github.com/chenxi116/PNASNet.TF for refactored and simplified TensorFlow code; see https://github.com/chenxi116/PNASNet.pytorch for exact conversion to PyTorch 
  Access Paper or Ask Questions

Deep Nets: What have they ever done for Vision?


May 10, 2018
Alan L. Yuille, Chenxi Liu

Figure 1 for Deep Nets: What have they ever done for Vision?
Figure 2 for Deep Nets: What have they ever done for Vision?
Figure 3 for Deep Nets: What have they ever done for Vision?
Figure 4 for Deep Nets: What have they ever done for Vision?
* MIT CBMM Memo No. 088 
  Access Paper or Ask Questions

Scene Graph Parsing as Dependency Parsing


Mar 25, 2018
Yu-Siang Wang, Chenxi Liu, Xiaohui Zeng, Alan Yuille

Figure 1 for Scene Graph Parsing as Dependency Parsing
Figure 2 for Scene Graph Parsing as Dependency Parsing
Figure 3 for Scene Graph Parsing as Dependency Parsing
Figure 4 for Scene Graph Parsing as Dependency Parsing
* To appear in NAACL 2018 as oral. Code is available at https://github.com/Yusics/bist-parser/tree/sgparser 
  Access Paper or Ask Questions

Few-Shot Image Recognition by Predicting Parameters from Activations


Nov 25, 2017
Siyuan Qiao, Chenxi Liu, Wei Shen, Alan Yuille

Figure 1 for Few-Shot Image Recognition by Predicting Parameters from Activations
Figure 2 for Few-Shot Image Recognition by Predicting Parameters from Activations
Figure 3 for Few-Shot Image Recognition by Predicting Parameters from Activations
Figure 4 for Few-Shot Image Recognition by Predicting Parameters from Activations

  Access Paper or Ask Questions

SORT: Second-Order Response Transform for Visual Recognition


Sep 14, 2017
Yan Wang, Lingxi Xie, Chenxi Liu, Ya Zhang, Wenjun Zhang, Alan Yuille

Figure 1 for SORT: Second-Order Response Transform for Visual Recognition
Figure 2 for SORT: Second-Order Response Transform for Visual Recognition
Figure 3 for SORT: Second-Order Response Transform for Visual Recognition
Figure 4 for SORT: Second-Order Response Transform for Visual Recognition
* To appear in ICCV 2017 (10 pages, 4 figures) 
  Access Paper or Ask Questions

Recurrent Multimodal Interaction for Referring Image Segmentation


Aug 04, 2017
Chenxi Liu, Zhe Lin, Xiaohui Shen, Jimei Yang, Xin Lu, Alan Yuille

Figure 1 for Recurrent Multimodal Interaction for Referring Image Segmentation
Figure 2 for Recurrent Multimodal Interaction for Referring Image Segmentation
Figure 3 for Recurrent Multimodal Interaction for Referring Image Segmentation
Figure 4 for Recurrent Multimodal Interaction for Referring Image Segmentation
* To appear in ICCV 2017. See http://www.cs.jhu.edu/~cxliu/ for code and supplementary material 
  Access Paper or Ask Questions

ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond


Apr 22, 2017
Siyuan Qiao, Wei Shen, Weichao Qiu, Chenxi Liu, Alan Yuille

Figure 1 for ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
Figure 2 for ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
Figure 3 for ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
Figure 4 for ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond

  Access Paper or Ask Questions

Attention Correctness in Neural Image Captioning


Nov 23, 2016
Chenxi Liu, Junhua Mao, Fei Sha, Alan Yuille

Figure 1 for Attention Correctness in Neural Image Captioning
Figure 2 for Attention Correctness in Neural Image Captioning
Figure 3 for Attention Correctness in Neural Image Captioning
Figure 4 for Attention Correctness in Neural Image Captioning
* To appear in AAAI-17. See http://www.cs.jhu.edu/~cxliu/ for supplementary material 
  Access Paper or Ask Questions