Bidirectional Graph Reasoning Network for Panoptic Segmentation

Apr 14, 2020
Yangxin Wu, Gengwei Zhang, Yiming Gao, Xiajun Deng, Ke Gong, Xiaodan Liang, Liang Lin

* CVPR2020 

  Access Model/Code and Paper
Linguistically Driven Graph Capsule Network for Visual Question Reasoning

Mar 23, 2020
Qingxing Cao, Xiaodan Liang, Keze Wang, Liang Lin

* Submitted to TPAMI 2020. We have achieved an end-to-end interpretable structural reasoning for general images without the requirement of layout annotations 

  Access Model/Code and Paper
Vision-Dialog Navigation by Exploring Cross-modal Memory

Mar 15, 2020
Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang

* CVPR2020 

  Access Model/Code and Paper
Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis

Mar 14, 2020
Junfan Lin, Ziliang Chen, Xiaodan Liang, Keze Wang, Liang Lin

* Submitted to TPAMI 2020. In the experiments, our trained agent achieves the new state-of-the-art under various experimental settings and possesses the advantage of sample-efficiency and robustness compared to other existing MAD methods 

  Access Model/Code and Paper
Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation

Mar 06, 2020
Jinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan Liang

* 8 pages, 2 figues, 6tables, AAAI2020, fix our model's abbreviation 

  Access Model/Code and Paper
ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection

Mar 03, 2020
Chenhan Jiang, Shaoju Wang, Hang Xu, Xiaodan Liang, Nong Xiao

* 7 pages, 5 figure, AAAI2020 

  Access Model/Code and Paper
Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Feb 18, 2020
Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang, Zhenguo Li

* Accepted by AAAI20 

  Access Model/Code and Paper
SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

Nov 30, 2019
Lewei Yao, Hang Xu, Wei Zhang, Xiaodan Liang, Zhenguo Li

* Accepted by AAAI 2020 

  Access Model/Code and Paper
Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Nov 29, 2019
Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang

* We achieve a state-of-the-art 78.4% top-1 accuracy on ImageNet in a mobile setting, which is about a 2.1% gain over EfficientNet-B0 

  Access Model/Code and Paper
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Nov 28, 2019
Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang


  Access Model/Code and Paper
Heterogeneous Graph Learning for Visual Commonsense Reasoning

Oct 25, 2019
Weijiang Yu, Jingwen Zhou, Weihao Yu, Xiaodan Liang, Nong Xiao

* 11 pages, 5 figures 

  Access Model/Code and Paper
Layout-Graph Reasoning for Fashion Landmark Detection

Oct 04, 2019
Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao, Liang Lin

* 9 pages, 5 figures, CVPR2019 

  Access Model/Code and Paper
Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning

Sep 28, 2019
Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang, Xiaodan Liang, Liang Lin

* Published in ICCV-2019. Project: https://yanxp.github.io/metarcnn.html 

  Access Model/Code and Paper
Explainable High-order Visual Question Reasoning: A New Benchmark and Knowledge-routed Network

Sep 23, 2019
Qingxing Cao, Bailin Li, Xiaodan Liang, Liang Lin


  Access Model/Code and Paper
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

Jul 08, 2019
Ziliang Chen, Zhanfu Yang, Xiaoxi Wang, Xiaodan Liang, Xiaopeng Yan, Guanbin Li, Liang Lin

* ICML-19 

  Access Model/Code and Paper
Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks

Jul 08, 2019
Ziliang Chen, Jingyu Zhuang, Xiaodan Liang, Liang Lin

* CVPR-19 (oral). Code is available at http://github.com/zjy526223908/BTDA 

  Access Model/Code and Paper
Fashion Editing with Multi-scale Attention Normalization

Jun 03, 2019
Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Zhenyu Xie, Bowen Wu, Ziqi Zhang, Xiaohui Shen, Jian Yin

* 22 pages, 18 figures 

  Access Model/Code and Paper
Target-Guided Open-Domain Conversation

May 29, 2019
Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric P. Xing, Zhiting Hu

* ACL 2019. Data and code available at https://github.com/squareRoot3/Target-Guided-Conversation. fixed typos 

  Access Model/Code and Paper
Graphonomy: Universal Human Parsing via Graph Transfer Learning

Apr 09, 2019
Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin

* Accepted to CVPR 2019. The Code is available at https://github.com/Gaoyiminggithub/Graphonomy 

  Access Model/Code and Paper
Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation

Mar 25, 2019
Christy Y. Li, Xiaodan Liang, Zhiting Hu, Eric P. Xing


  Access Model/Code and Paper
End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis

Mar 18, 2019
Lin Xu, Qixian Zhou, Ke Gong, Xiaodan Liang, Jianheng Tang, Liang Lin

* 8 pages, 5 figues, AAAI 

  Access Model/Code and Paper
Towards Multi-pose Guided Virtual Try-on Network

Feb 28, 2019
Haoye Dong, Xiaodan Liang, Bochao Wang, Hanjiang Lai, Jia Zhu, Jian Yin

* 11 pages, 10 figures 

  Access Model/Code and Paper
Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis

Oct 27, 2018
Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin

* 17 pages, 14 figures 

  Access Model/Code and Paper
Toward Controlled Generation of Text

Sep 13, 2018
Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, Eric P. Xing

* Code adapted for text style transfer is released at: https://github.com/asyml/texar/tree/master/examples/text_style_transfer 

  Access Model/Code and Paper