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 Liang Lin

Liang Lin

Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation


Jul 23, 2021
Bingqian Lin, Yi Zhu, Yanxin Long, Xiaodan Liang, Qixiang Ye, Liang Lin

Figure 1 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 2 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 3 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Figure 4 for Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
* IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 
 * Accepted by TPAMI 2021 
  Access Paper or Ask Questions

Hybrid and dynamic policy gradient optimization for bipedal robot locomotion


Jul 05, 2021
Changxin Huang, Jiang Su, Zhihong Zhang, Dong Zhao, Liang Lin

Figure 1 for Hybrid and dynamic policy gradient optimization for bipedal robot locomotion
Figure 2 for Hybrid and dynamic policy gradient optimization for bipedal robot locomotion
Figure 3 for Hybrid and dynamic policy gradient optimization for bipedal robot locomotion
Figure 4 for Hybrid and dynamic policy gradient optimization for bipedal robot locomotion

  Access Paper or Ask Questions

Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation


Jul 05, 2021
Lingbo Liu, Yuying Zhu, Guanbin Li, Ziyi Wu, Lei Bai, Mingzhi Mao, Liang Lin

Figure 1 for Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
Figure 2 for Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
Figure 3 for Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
Figure 4 for Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
* UnderReview 
  Access Paper or Ask Questions

Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks


Jul 03, 2021
Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin

Figure 1 for Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
Figure 2 for Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
Figure 3 for Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
Figure 4 for Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
* ACL 2021 
  Access Paper or Ask Questions

Prototypical Graph Contrastive Learning


Jun 17, 2021
Shuai Lin, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang

Figure 1 for Prototypical Graph Contrastive Learning
Figure 2 for Prototypical Graph Contrastive Learning
Figure 3 for Prototypical Graph Contrastive Learning
Figure 4 for Prototypical Graph Contrastive Learning

  Access Paper or Ask Questions

GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning


Jun 08, 2021
Jiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang, Lingbo Liu, Eric P. Xing, Liang Lin

Figure 1 for GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Figure 2 for GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Figure 3 for GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Figure 4 for GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
* Accepted to Findings of ACL 2021 
  Access Paper or Ask Questions

Towards Quantifiable Dialogue Coherence Evaluation


Jun 01, 2021
Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, Xiaodan Liang

Figure 1 for Towards Quantifiable Dialogue Coherence Evaluation
Figure 2 for Towards Quantifiable Dialogue Coherence Evaluation
Figure 3 for Towards Quantifiable Dialogue Coherence Evaluation
Figure 4 for Towards Quantifiable Dialogue Coherence Evaluation
* Long paper; ACL2021 
  Access Paper or Ask Questions

Solving Inefficiency of Self-supervised Representation Learning


Apr 18, 2021
Guangrun Wang, Keze Wang, Guangcong Wang, Phillip H. S. Torr, Liang Lin

Figure 1 for Solving Inefficiency of Self-supervised Representation Learning
Figure 2 for Solving Inefficiency of Self-supervised Representation Learning
Figure 3 for Solving Inefficiency of Self-supervised Representation Learning
Figure 4 for Solving Inefficiency of Self-supervised Representation Learning
* 11 pages, 3 figures 
  Access Paper or Ask Questions

Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition


Mar 31, 2021
Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang

Figure 1 for Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
Figure 2 for Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
Figure 3 for Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
Figure 4 for Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
* To appear in IEEE Transactions ON Neural Networks and Learning Systems. We prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture 
  Access Paper or Ask Questions

Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation


Mar 09, 2021
Chaohao Xie, Dongwei Ren, Lei Wang, Qinghua Hu, Liang Lin, Wangmeng Zuo

Figure 1 for Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
Figure 2 for Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
Figure 3 for Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
Figure 4 for Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
* 14 pages, 7 figures 
  Access Paper or Ask Questions

GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer


Feb 01, 2021
Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, Liang Lin

Figure 1 for GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
Figure 2 for GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
Figure 3 for GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
Figure 4 for GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
* The first two authors share equal-authorship; Code:https://github.com/SenZHANG-GitHub/graph-text-style-transfer ; benchmark: https://github.com/ykshi/text-style-transfer-benchmark 
  Access Paper or Ask Questions

Temporal Contrastive Graph for Self-supervised Video Representation Learning


Feb 01, 2021
Yang Liu, Keze Wang, Haoyuan Lan, Liang Lin

Figure 1 for Temporal Contrastive Graph for Self-supervised Video Representation Learning
Figure 2 for Temporal Contrastive Graph for Self-supervised Video Representation Learning
Figure 3 for Temporal Contrastive Graph for Self-supervised Video Representation Learning
Figure 4 for Temporal Contrastive Graph for Self-supervised Video Representation Learning
* 11 pages, 4 figures 
  Access Paper or Ask Questions

Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer


Jan 26, 2021
Liang Lin, Yiming Gao, Ke Gong, Meng Wang, Xiaodan Liang

Figure 1 for Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
Figure 2 for Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
Figure 3 for Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
Figure 4 for Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
* To appear in IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (T-PAMI) 2021. We propose a graph reasoning and transfer learning framework, which incorporates human knowledge and label taxonomy into the intermediate graph representation learning beyond local convolutions. arXiv admin note: substantial text overlap with arXiv:1904.04536 
  Access Paper or Ask Questions

Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition


Jan 09, 2021
Fuyu Wang, Xiaodan Liang, Lin Xu, Liang Lin

Figure 1 for Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition
Figure 2 for Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition
Figure 3 for Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition
Figure 4 for Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition
* To appear in IEEE Transactions on Cybernetics 2021. We attempt to resolve the challenging medical report composition task by i) enforcing the semantic consistency of medical terms to be incorporated into the final reports; and ii) encouraging the sentence generation for rare abnormal descriptions 
  Access Paper or Ask Questions

REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement


Jan 03, 2021
Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin

Figure 1 for REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
Figure 2 for REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
Figure 3 for REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
Figure 4 for REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition


Dec 29, 2020
Tao Pu, Tianshui Chen, Yuan Xie, Hefeng Wu, Liang Lin

Figure 1 for AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
Figure 2 for AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
Figure 3 for AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
Figure 4 for AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition

  Access Paper or Ask Questions

Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition


Dec 23, 2020
Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin

Figure 1 for Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
Figure 2 for Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
Figure 3 for Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
Figure 4 for Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
* accepted in AAAI2021 
  Access Paper or Ask Questions

Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation


Dec 22, 2020
Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang, Ruihui Zhao, Ziliang Chen, Liang Lin

Figure 1 for Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
Figure 2 for Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
Figure 3 for Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
Figure 4 for Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding


Dec 14, 2020
Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin

Figure 1 for Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
Figure 2 for Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
Figure 3 for Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
Figure 4 for Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
* To appear in TNNLS 2021. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning 
  Access Paper or Ask Questions

Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting


Dec 08, 2020
Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin

Figure 1 for Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Figure 2 for Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Figure 3 for Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Figure 4 for Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
* We introduce a large-scale RGBT benchmark for crowd counting 
  Access Paper or Ask Questions

Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp


Nov 30, 2020
Junfan Lin, Zhongzhan Huang, Keze Wang, Xiaodan Liang, Weiwei Chen, Liang Lin

Figure 1 for Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
Figure 2 for Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
Figure 3 for Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
Figure 4 for Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

  Access Paper or Ask Questions

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation


Oct 30, 2020
Yangxin Wu, Gengwei Zhang, Hang Xu, Xiaodan Liang, Liang Lin

Figure 1 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 2 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 3 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 4 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
* NeurIPS2020 
  Access Paper or Ask Questions

A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning


Oct 15, 2020
Hongjun Wang, Guanbin Li, Xiaobai Liu, Liang Lin

Figure 1 for A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Figure 2 for A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Figure 3 for A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Figure 4 for A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
* Accepted as a Regular Paper in IEEE Transactions on Pattern Analysis and Machine Intelligence 
  Access Paper or Ask Questions

Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems


Oct 14, 2020
Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin

Figure 1 for Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
Figure 2 for Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
Figure 3 for Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
Figure 4 for Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
* EMNLP2020 
  Access Paper or Ask Questions

GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems


Oct 08, 2020
Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang

Figure 1 for GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
Figure 2 for GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
Figure 3 for GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
Figure 4 for GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
* Long paper; EMNLP2020 
  Access Paper or Ask Questions