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 Qi Zhu

Qi Zhu

EJ

Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads


Apr 30, 2021
Chenyu Gao, Qi Zhu, Peng Wang, Qi Wu

Figure 1 for Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads
Figure 2 for Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads
Figure 3 for Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads
Figure 4 for Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads
* 14 pages 
  Access Paper or Ask Questions

Towards Fully Intelligent Transportation through Infrastructure-Vehicle Cooperative Autonomous Driving: Challenges and Opportunities


Mar 03, 2021
Shaoshan Liu, Bo Yu, Jie Tang, Qi Zhu

Figure 1 for Towards Fully Intelligent Transportation through Infrastructure-Vehicle Cooperative Autonomous Driving: Challenges and Opportunities
Figure 2 for Towards Fully Intelligent Transportation through Infrastructure-Vehicle Cooperative Autonomous Driving: Challenges and Opportunities
Figure 3 for Towards Fully Intelligent Transportation through Infrastructure-Vehicle Cooperative Autonomous Driving: Challenges and Opportunities

  Access Paper or Ask Questions

End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering


Feb 27, 2021
Ruochen Jiao, Hengyi Liang, Takami Sato, Junjie Shen, Qi Alfred Chen, Qi Zhu

Figure 1 for End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
Figure 2 for End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
Figure 3 for End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
Figure 4 for End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
* 8 pages for conference 
  Access Paper or Ask Questions

Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator


Feb 15, 2021
Shichao Xu, Lixu Wang, Yixuan Wang, Qi Zhu

Figure 1 for Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
Figure 2 for Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
Figure 3 for Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
Figure 4 for Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator

  Access Paper or Ask Questions

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps


Dec 09, 2020
Qi Zhu, Chenyu Gao, Peng Wang, Qi Wu

Figure 1 for Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
Figure 2 for Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
Figure 3 for Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
Figure 4 for Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

  Access Paper or Ask Questions

Overview of the Ninth Dialog System Technology Challenge: DSTC9


Nov 12, 2020
Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro, Abhinav Rastogi, Yun-Nung Chen, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Chao-Wei Huang, Dilek Hakkani-Tür, Jinchao Li, Qi Zhu, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Runze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Minlie Huang, Jianfeng Gao, Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi, David Traum, Maxine Eskenazi, Ahmad Beirami, Eunjoon, Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba

Figure 1 for Overview of the Ninth Dialog System Technology Challenge: DSTC9
Figure 2 for Overview of the Ninth Dialog System Technology Challenge: DSTC9
Figure 3 for Overview of the Ninth Dialog System Technology Challenge: DSTC9
Figure 4 for Overview of the Ninth Dialog System Technology Challenge: DSTC9

  Access Paper or Ask Questions

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization


Sep 11, 2020
Qi Zhu, Yidan Xu, Haonan Wang, Chao Zhang, Jiawei Han, Carl Yang

Figure 1 for Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Figure 2 for Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Figure 3 for Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Figure 4 for Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

  Access Paper or Ask Questions

Towards Class Imbalance in Federated Learning


Aug 14, 2020
Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu

Figure 1 for Towards Class Imbalance in Federated Learning
Figure 2 for Towards Class Imbalance in Federated Learning
Figure 3 for Towards Class Imbalance in Federated Learning
Figure 4 for Towards Class Imbalance in Federated Learning
* 17 pages, 5 figures 
  Access Paper or Ask Questions

Distributed Multi-agent Video Fast-forwarding


Aug 10, 2020
Shuyue Lan, Zhilu Wang, Amit K. Roy-Chowdhury, Ermin Wei, Qi Zhu

Figure 1 for Distributed Multi-agent Video Fast-forwarding
Figure 2 for Distributed Multi-agent Video Fast-forwarding
Figure 3 for Distributed Multi-agent Video Fast-forwarding
Figure 4 for Distributed Multi-agent Video Fast-forwarding
* To appear at ACM Multimedia 2020 
  Access Paper or Ask Questions

One for Many: Transfer Learning for Building HVAC Control


Aug 09, 2020
Shichao Xu, Yixuan Wang, Yanzhi Wang, Zheng O'Neill, Qi Zhu

Figure 1 for One for Many: Transfer Learning for Building HVAC Control
Figure 2 for One for Many: Transfer Learning for Building HVAC Control
Figure 3 for One for Many: Transfer Learning for Building HVAC Control
Figure 4 for One for Many: Transfer Learning for Building HVAC Control
* Submitted to Buildsys 2020 
  Access Paper or Ask Questions

Unsupervised Differentiable Multi-aspect Network Embedding


Jun 12, 2020
Chanyoung Park, Carl Yang, Qi Zhu, Donghyun Kim, Hwanjo Yu, Jiawei Han

Figure 1 for Unsupervised Differentiable Multi-aspect Network Embedding
Figure 2 for Unsupervised Differentiable Multi-aspect Network Embedding
Figure 3 for Unsupervised Differentiable Multi-aspect Network Embedding
Figure 4 for Unsupervised Differentiable Multi-aspect Network Embedding
* KDD 2020 (Research Track). 9 Pages + Appendix (2 Pages). Source code can be found https://github.com/pcy1302/asp2vec 
  Access Paper or Ask Questions

Structured Multimodal Attentions for TextVQA


Jun 01, 2020
Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton van den Hengel, Qi Wu

Figure 1 for Structured Multimodal Attentions for TextVQA
Figure 2 for Structured Multimodal Attentions for TextVQA
Figure 3 for Structured Multimodal Attentions for TextVQA
Figure 4 for Structured Multimodal Attentions for TextVQA
* 19 pages, winner of TextVQA Challenge 2020 
  Access Paper or Ask Questions

Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation


May 15, 2020
Ryuichi Takanobu, Qi Zhu, Jinchao Li, Baolin Peng, Jianfeng Gao, Minlie Huang

Figure 1 for Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
Figure 2 for Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
Figure 3 for Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
Figure 4 for Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
* SIGDIAL 2020 long paper 
  Access Paper or Ask Questions

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset


Feb 28, 2020
Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang

Figure 1 for CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Figure 2 for CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Figure 3 for CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Figure 4 for CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
* Accepted by TACL 
  Access Paper or Ask Questions

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems


Feb 12, 2020
Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

Figure 1 for ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Figure 2 for ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Figure 3 for ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Figure 4 for ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

  Access Paper or Ask Questions

Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning


Jan 23, 2020
Xiangguo Liu, Guangchen Zhao, Neda Masoud, Qi Zhu

Figure 1 for Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning
Figure 2 for Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning
Figure 3 for Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning
Figure 4 for Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning

  Access Paper or Ask Questions

Eavesdrop the Composition Proportion of Training Labels in Federated Learning


Oct 27, 2019
Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu

Figure 1 for Eavesdrop the Composition Proportion of Training Labels in Federated Learning
Figure 2 for Eavesdrop the Composition Proportion of Training Labels in Federated Learning
Figure 3 for Eavesdrop the Composition Proportion of Training Labels in Federated Learning
Figure 4 for Eavesdrop the Composition Proportion of Training Labels in Federated Learning
* 15 pages, 10 figures, security conference 
  Access Paper or Ask Questions

MaskPlus: Improving Mask Generation for Instance Segmentation


Sep 05, 2019
Shichao Xu, Shuyue Lan, Qi Zhu

Figure 1 for MaskPlus: Improving Mask Generation for Instance Segmentation
Figure 2 for MaskPlus: Improving Mask Generation for Instance Segmentation
Figure 3 for MaskPlus: Improving Mask Generation for Instance Segmentation
Figure 4 for MaskPlus: Improving Mask Generation for Instance Segmentation

  Access Paper or Ask Questions

Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity


Sep 04, 2019
Yu Shi, Jiaming Shen, Yuchen Li, Naijing Zhang, Xinwei He, Zhengzhi Lou, Qi Zhu, Matthew Walker, Myunghwan Kim, Jiawei Han

Figure 1 for Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
Figure 2 for Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
Figure 3 for Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
Figure 4 for Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
* CIKM 2019 
  Access Paper or Ask Questions

Facet-Aware Evaluation for Extractive Text Summarization


Aug 27, 2019
Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han

Figure 1 for Facet-Aware Evaluation for Extractive Text Summarization
Figure 2 for Facet-Aware Evaluation for Extractive Text Summarization
Figure 3 for Facet-Aware Evaluation for Extractive Text Summarization
Figure 4 for Facet-Aware Evaluation for Extractive Text Summarization

  Access Paper or Ask Questions

ReachNN: Reachability Analysis of Neural-Network Controlled Systems


Jun 25, 2019
Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen, Qi Zhu

Figure 1 for ReachNN: Reachability Analysis of Neural-Network Controlled Systems
Figure 2 for ReachNN: Reachability Analysis of Neural-Network Controlled Systems
Figure 3 for ReachNN: Reachability Analysis of Neural-Network Controlled Systems
Figure 4 for ReachNN: Reachability Analysis of Neural-Network Controlled Systems

  Access Paper or Ask Questions

Task-Guided Pair Embedding in Heterogeneous Network


Jun 10, 2019
Chanyoung Park, Donghyun Kim, Qi Zhu, Jiawei Han, Hwanjo Yu

Figure 1 for Task-Guided Pair Embedding in Heterogeneous Network
Figure 2 for Task-Guided Pair Embedding in Heterogeneous Network
Figure 3 for Task-Guided Pair Embedding in Heterogeneous Network
Figure 4 for Task-Guided Pair Embedding in Heterogeneous Network

  Access Paper or Ask Questions

ConvLab: Multi-Domain End-to-End Dialog System Platform


Apr 18, 2019
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao

Figure 1 for ConvLab: Multi-Domain End-to-End Dialog System Platform
Figure 2 for ConvLab: Multi-Domain End-to-End Dialog System Platform
Figure 3 for ConvLab: Multi-Domain End-to-End Dialog System Platform
Figure 4 for ConvLab: Multi-Domain End-to-End Dialog System Platform

  Access Paper or Ask Questions

Integrating Local Context and Global Cohesiveness for Open Information Extraction


Nov 04, 2018
Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Ahmed El-Kishky, Jiawei Han

Figure 1 for Integrating Local Context and Global Cohesiveness for Open Information Extraction
Figure 2 for Integrating Local Context and Global Cohesiveness for Open Information Extraction
Figure 3 for Integrating Local Context and Global Cohesiveness for Open Information Extraction
Figure 4 for Integrating Local Context and Global Cohesiveness for Open Information Extraction
* 8 pages + 1 page reference. Accepted to WSDM 2019 
  Access Paper or Ask Questions

Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks


Jul 10, 2018
Yu Shi, Qi Zhu, Fang Guo, Chao Zhang, Jiawei Han

Figure 1 for Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
Figure 2 for Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
Figure 3 for Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
Figure 4 for Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
* 10 pages. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, United Kingdom, ACM, 2018 
  Access Paper or Ask Questions

FFNet: Video Fast-Forwarding via Reinforcement Learning


May 08, 2018
Shuyue Lan, Rameswar Panda, Qi Zhu, Amit K. Roy-Chowdhury

Figure 1 for FFNet: Video Fast-Forwarding via Reinforcement Learning
Figure 2 for FFNet: Video Fast-Forwarding via Reinforcement Learning
Figure 3 for FFNet: Video Fast-Forwarding via Reinforcement Learning
Figure 4 for FFNet: Video Fast-Forwarding via Reinforcement Learning
* CVPR 2018 
  Access Paper or Ask Questions