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 Bo Li

Bo Li

Scaling End-to-End Models for Large-Scale Multilingual ASR


Apr 30, 2021
Bo Li, Ruoming Pang, Tara N. Sainath, Anmol Gulati, Yu Zhang, James Qin, Parisa Haghani, W. Ronny Huang, Min Ma

Figure 1 for Scaling End-to-End Models for Large-Scale Multilingual ASR
Figure 2 for Scaling End-to-End Models for Large-Scale Multilingual ASR
Figure 3 for Scaling End-to-End Models for Large-Scale Multilingual ASR
* Submitted to INTERSPEECH 2021 
  Access Paper or Ask Questions

Multi-view Inference for Relation Extraction with Uncertain Knowledge


Apr 28, 2021
Bo Li, Wei Ye, Canming Huang, Shikun Zhang

Figure 1 for Multi-view Inference for Relation Extraction with Uncertain Knowledge
Figure 2 for Multi-view Inference for Relation Extraction with Uncertain Knowledge
Figure 3 for Multi-view Inference for Relation Extraction with Uncertain Knowledge
Figure 4 for Multi-view Inference for Relation Extraction with Uncertain Knowledge
* Published at AAAI 2021, full paper 
  Access Paper or Ask Questions

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness


Apr 01, 2021
Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Benjamin Rubinstein, Ce Zhang, Bo Li

Figure 1 for TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Figure 2 for TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Figure 3 for TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Figure 4 for TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

  Access Paper or Ask Questions

Spatiotemporal Transformer for Video-based Person Re-identification


Mar 30, 2021
Tianyu Zhang, Longhui Wei, Lingxi Xie, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian

Figure 1 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 2 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 3 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 4 for Spatiotemporal Transformer for Video-based Person Re-identification
* 10 pages, 7 figures 
  Access Paper or Ask Questions

Residual Energy-Based Models for End-to-End Speech Recognition


Mar 25, 2021
Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland

Figure 1 for Residual Energy-Based Models for End-to-End Speech Recognition
Figure 2 for Residual Energy-Based Models for End-to-End Speech Recognition
Figure 3 for Residual Energy-Based Models for End-to-End Speech Recognition
Figure 4 for Residual Energy-Based Models for End-to-End Speech Recognition
* Submitted to Interspeech 2021 
  Access Paper or Ask Questions

Self-Supervised Pretraining Improves Self-Supervised Pretraining


Mar 25, 2021
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell

Figure 1 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 2 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 3 for Self-Supervised Pretraining Improves Self-Supervised Pretraining
Figure 4 for Self-Supervised Pretraining Improves Self-Supervised Pretraining

  Access Paper or Ask Questions

Multi-Robot Task Allocation -- Complexity and Approximation


Mar 23, 2021
Haris Aziz, Hau Chan, Ágnes Cseh, Bo Li, Fahimeh Ramezani, Chenhao Wang

Figure 1 for Multi-Robot Task Allocation -- Complexity and Approximation
* AAMAS 2021 
  Access Paper or Ask Questions

DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation


Mar 20, 2021
Boxin Wang, Fan Wu, Yunhui Long, Luka Rimanic, Ce Zhang, Bo Li

Figure 1 for DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Figure 2 for DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Figure 3 for DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Figure 4 for DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
* 29 pages, 3 figures, 6 tables 
  Access Paper or Ask Questions

Real-Time Visual Object Tracking via Few-Shot Learning


Mar 18, 2021
Jinghao Zhou, Bo Li, Peng Wang, Peixia Li, Weihao Gan, Wei Wu, Junjie Yan, Wanli Ouyang

Figure 1 for Real-Time Visual Object Tracking via Few-Shot Learning
Figure 2 for Real-Time Visual Object Tracking via Few-Shot Learning
Figure 3 for Real-Time Visual Object Tracking via Few-Shot Learning
Figure 4 for Real-Time Visual Object Tracking via Few-Shot Learning

  Access Paper or Ask Questions

Higher Performance Visual Tracking with Dual-Modal Localization


Mar 18, 2021
Jinghao Zhou, Bo Li, Lei Qiao, Peng Wang, Weihao Gan, Wei Wu, Junjie Yan, Wanli Ouyang

Figure 1 for Higher Performance Visual Tracking with Dual-Modal Localization
Figure 2 for Higher Performance Visual Tracking with Dual-Modal Localization
Figure 3 for Higher Performance Visual Tracking with Dual-Modal Localization
Figure 4 for Higher Performance Visual Tracking with Dual-Modal Localization

  Access Paper or Ask Questions

Learning Word-Level Confidence For Subword End-to-End ASR


Mar 11, 2021
David Qiu, Qiujia Li, Yanzhang He, Yu Zhang, Bo Li, Liangliang Cao, Rohit Prabhavalkar, Deepti Bhatia, Wei Li, Ke Hu, Tara N. Sainath, Ian McGraw

Figure 1 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 2 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 3 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 4 for Learning Word-Level Confidence For Subword End-to-End ASR
* To appear in ICASSP 2021 
  Access Paper or Ask Questions

Understanding Robustness in Teacher-Student Setting: A New Perspective


Mar 01, 2021
Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian

Figure 1 for Understanding Robustness in Teacher-Student Setting: A New Perspective
Figure 2 for Understanding Robustness in Teacher-Student Setting: A New Perspective
Figure 3 for Understanding Robustness in Teacher-Student Setting: A New Perspective
Figure 4 for Understanding Robustness in Teacher-Student Setting: A New Perspective
* Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, San Diego, California, USA. PMLR: Volume 130 
  Access Paper or Ask Questions

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks


Feb 25, 2021
Huichen Li, Linyi Li, Xiaojun Xu, Xiaolu Zhang, Shuang Yang, Bo Li

Figure 1 for Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
Figure 2 for Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
Figure 3 for Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
Figure 4 for Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
* Accepted by AISTATS 2021; 9 pages excluding references and appendices 
  Access Paper or Ask Questions

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space


Feb 06, 2021
Shihao Zhao, Xingjun Ma, Yisen Wang, James Bailey, Bo Li, Yu-Gang Jiang

Figure 1 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 2 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 3 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 4 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

  Access Paper or Ask Questions

Segmentation of Breast Microcalcifications: A Multi-Scale Approach


Feb 01, 2021
Chrysostomos Marasinou, Bo Li, Jeremy Paige, Akinyinka Omigbodun, Noor Nakhaei, Anne Hoyt, William Hsu

Figure 1 for Segmentation of Breast Microcalcifications: A Multi-Scale Approach
Figure 2 for Segmentation of Breast Microcalcifications: A Multi-Scale Approach
Figure 3 for Segmentation of Breast Microcalcifications: A Multi-Scale Approach
Figure 4 for Segmentation of Breast Microcalcifications: A Multi-Scale Approach
* Electronic Preprint version 1 
  Access Paper or Ask Questions

Rescuing Deep Hashing from Dead Bits Problem


Feb 01, 2021
Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang

Figure 1 for Rescuing Deep Hashing from Dead Bits Problem
Figure 2 for Rescuing Deep Hashing from Dead Bits Problem
Figure 3 for Rescuing Deep Hashing from Dead Bits Problem
Figure 4 for Rescuing Deep Hashing from Dead Bits Problem

  Access Paper or Ask Questions

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks


Jan 27, 2021
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

Figure 1 for Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Figure 2 for Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Figure 3 for Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Figure 4 for Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
* 19 pages, 14 figures, ICLR 2021 
  Access Paper or Ask Questions

Robusta: Robust AutoML for Feature Selection via Reinforcement Learning


Jan 15, 2021
Xiaoyang Wang, Bo Li, Yibo Zhang, Bhavya Kailkhura, Klara Nahrstedt

Figure 1 for Robusta: Robust AutoML for Feature Selection via Reinforcement Learning
Figure 2 for Robusta: Robust AutoML for Feature Selection via Reinforcement Learning
Figure 3 for Robusta: Robust AutoML for Feature Selection via Reinforcement Learning
Figure 4 for Robusta: Robust AutoML for Feature Selection via Reinforcement Learning

  Access Paper or Ask Questions

ORDNet: Capturing Omni-Range Dependencies for Scene Parsing


Jan 11, 2021
Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han, Bo Li, Jiashi Feng, Shuicheng Yan

Figure 1 for ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
Figure 2 for ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
Figure 3 for ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
Figure 4 for ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
* IEEE Transactions on Image Processing, 2020, 29: 8251-8263 
 * Published at TIP 
  Access Paper or Ask Questions

A novel shape matching descriptor for real-time hand gesture recognition


Jan 11, 2021
Michalis Lazarou, Bo Li, Tania Stathaki

Figure 1 for A novel shape matching descriptor for real-time hand gesture recognition
Figure 2 for A novel shape matching descriptor for real-time hand gesture recognition
Figure 3 for A novel shape matching descriptor for real-time hand gesture recognition
Figure 4 for A novel shape matching descriptor for real-time hand gesture recognition

  Access Paper or Ask Questions

Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses


Dec 30, 2020
Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein

Figure 1 for Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 2 for Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 3 for Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 4 for Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

  Access Paper or Ask Questions

Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration


Dec 28, 2020
Bo Li, Wiro J. Niessen, Stefan Klein, Marius de Groot, M. Arfan Ikram, Meike W. Vernooij, Esther E. Bron

Figure 1 for Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
Figure 2 for Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
Figure 3 for Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
Figure 4 for Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
* Under review 
  Access Paper or Ask Questions

Data Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses


Dec 18, 2020
Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein

Figure 1 for Data Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 2 for Data Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 3 for Data Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Figure 4 for Data Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

  Access Paper or Ask Questions

On the Limitations of Denoising Strategies as Adversarial Defenses


Dec 17, 2020
Zhonghan Niu, Zhaoxi Chen, Linyi Li, Yubin Yang, Bo Li, Jinfeng Yi

Figure 1 for On the Limitations of Denoising Strategies as Adversarial Defenses
Figure 2 for On the Limitations of Denoising Strategies as Adversarial Defenses
Figure 3 for On the Limitations of Denoising Strategies as Adversarial Defenses
Figure 4 for On the Limitations of Denoising Strategies as Adversarial Defenses

  Access Paper or Ask Questions

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification


Dec 09, 2020
Tianyu Zhang, Lingxi Xie, Longhui Wei, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian

Figure 1 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 2 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 3 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 4 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
* 10 pages, 5 figure 
  Access Paper or Ask Questions

Evaluating adversarial robustness in simulated cerebellum


Dec 05, 2020
Liu Yuezhang, Bo Li, Qifeng Chen

Figure 1 for Evaluating adversarial robustness in simulated cerebellum
Figure 2 for Evaluating adversarial robustness in simulated cerebellum
* 6 pages, 2 figures, NeurIPS 2020 Pre-registration Workshop 
  Access Paper or Ask Questions

Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks -- Applications in Point Spread Function Estimation


Nov 20, 2020
Peng Jia, Xuebo Wu, Zhengyang Li, Bo Li, Weihua Wang, Qiang Liu, Adam Popowicz

Figure 1 for Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks -- Applications in Point Spread Function Estimation
Figure 2 for Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks -- Applications in Point Spread Function Estimation
Figure 3 for Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks -- Applications in Point Spread Function Estimation
Figure 4 for Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks -- Applications in Point Spread Function Estimation
* Submitted to MNRAS 
  Access Paper or Ask Questions