Pengkai Zhu - IEEE Xplore Author Profile

Scheduled Maintenance on Monday 1/13/2025

Single article sales and account management will be unavailable from 5:00 AM - 7:00 PM ET (09:00 - 23:00 UTC). We apologize for the inconvenience.

IEEE.org
IEEE Xplore
IEEE SA
IEEE Spectrum
More Sites

- Donate
- Personal Sign In

Institutional Sign In

Institutional Sign In

ADVANCED SEARCH

Author details

Pengkai Zhu

Publications

5

Citations

167

Publications by Year

20192024

Co-Authors:

Srikar AppalarajuEdouard BelvalYuan GaoShabnam GhadarVijay Mahadevan

Show All Co-Authors (12)

Pengkai Zhu

Affiliation

AWS AI Labs

Publication Topics

Semantic Vectors,
Unseen Classes,
Zero-shot,
Bounding Box,
Object Detection,
Semantic Properties,
Visual Features,
Confidence Score,
Ground-truth Bounding Box,
High-dimensional Feature,
Image Encoder,
Learning Rate

Biography

Pengkai Zhu received the PhD degree from Boston University, where he was supervised by Prof. Venkatesh Saligrama. He is an applied scientist with AWS AI. His research interests include computer vision and machine learning, specially low-shot recognition and visual document understanding.(Based on document published on 10 October 2022).

Publications

5

Citations

167

Publications by Year

20192024

Co-Authors:

Srikar Appalaraju
Edouard Belval
Yuan Gao
Shabnam Ghadar
Vijay Mahadevan

Show All Co-Authors (12)

Author's Published Works

Search History

Showing 1-14 of 14 results

Conferences (13)

Early Access Articles (1)

Sort

Filter Results

Show

Open Access Only

Range
Single Year
Xuefeng Xiao(14)
Jie Wu(6)
Rui Wang(5)
Xin Pan(5)
Xin Xia(4)
ByteDance Inc.(4)
ByteDance Inc(4)
School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China(2)
ByteDance Inc, China(1)
School of Electronic and Information Engineering, South China(1)
2023 IEEE/CVF International Conference on Computer Vision (ICCV)(3)
2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)(2)
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(2)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2)
2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)(1)
IEEE(14)
Media(3)
Paris, France(3)
Kyoto, Japan(2)
Nashville, TN, USA(2)
Vancouver, BC, Canada(2)
Montreal, QC, Canada(1)
Convolutional Layers(4)
Neural Architecture Search(4)
Search Space(4)
Training Set(4)
Convolutional Neural Network(3)

Select All on Page

Sort By

Results

VmambaIR: Visual State Space Model for Image Restoration

Yuan Shi;Bin Xia;Xiaoyu Jin;Xing Wang;Tianyu Zhao;Xin Xia;Xuefeng Xiao;Wenming Yang

IEEE Transactions on Circuits and Systems for Video Technology

Year: 2025 | Early Access Article |

Cited by: Papers (4)

Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and diffusion models (DMs), have been employed to address this problem with significant impact. However, CNNs have limitations in capturing long-range depend...Show More

VmambaIR: Visual State Space Model for Image Restoration

Yuan Shi;Bin Xia;Xiaoyu Jin;Xing Wang;Tianyu Zhao;Xin Xia;Xuefeng Xiao;Wenming Yang

IEEE Transactions on Circuits and Systems for Video Technology

Year: 2025 | Early Access Article |

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

Haichao Zhang;Kuangrong Hao;Jiashi Li;Xin Xia;Xuefeng Xiao

2024 2nd International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT)

Year: 2024 | Conference Paper |

HTML

Recently, neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on image classification tasks. However, the architecture searched through the classification task is sub-optimal because of the gap between the task of classification and object detection. While work focuses on backbone network ar...Show More

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

Haichao Zhang;Kuangrong Hao;Jiashi Li;Xin Xia;Xuefeng Xiao

2024 2nd International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT)

Year: 2024 | Conference Paper |

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Lijiang Li;Huixia Li;Xiawu Zheng;Jie Wu;Xuefeng Xiao;Rui Wang;Min Zheng;Xin Pan;Fei Chao;Rongrong Ji

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

Cited by: Papers (4)

HTML

Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undisputed principle of diffusion models. We consider that such a uniform assumption is not the optimal solution in practice; i.e., we can find different optim...Show More

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Lijiang Li;Huixia Li;Xiawu Zheng;Jie Wu;Xuefeng Xiao;Rui Wang;Min Zheng;Xin Pan;Fei Chao;Rongrong Ji

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

Yuxi Ren;Jie Wu;Peng Zhang;Manlin Zhang;Xuefeng Xiao;Qian He;Rui Wang;Min Zheng;Xin Pan

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

Cited by: Papers (3)

HTML

Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data. Current efficient GAN learning techniques often fall into two orthogonal aspects: i) model slimming via reduced calculation costs; ii) data/label-efficient lea...Show More

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

Yuxi Ren;Jie Wu;Peng Zhang;Manlin Zhang;Xuefeng Xiao;Qian He;Rui Wang;Min Zheng;Xin Pan

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

Ming Li;Jie Wu;Xionghui Wang;Chen Chen;Jie Qin;Xuefeng Xiao;Rui Wang;Min Zheng;Xin Pan

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

Cited by: Papers (8)

HTML

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector’s performance, generalization ability, and convergence speed. To this end, we propose...Show More

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

Ming Li;Jie Wu;Xionghui Wang;Chen Chen;Jie Qin;Xuefeng Xiao;Rui Wang;Min Zheng;Xin Pan

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2023 | Conference Paper |

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Yuexiao Ma;Huixia Li;Xiawu Zheng;Xuefeng Xiao;Rui Wang;Shilei Wen;Xin Pan;Fei Chao;Rongrong Ji

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Year: 2023 | Conference Paper |

Cited by: Papers (9)

HTML

Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. In this paper, we take the initiative to explore and present a theoretical proof to explain why such a problem is essential in PTQ. And then, we try to...Show More

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Yuexiao Ma;Huixia Li;Xiawu Zheng;Xuefeng Xiao;Rui Wang;Shilei Wen;Xin Pan;Fei Chao;Rongrong Ji

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Year: 2023 | Conference Paper |

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Oin;Jie Wu;Pengxiang Yan;Ming Li;Ren Yuxi;Xuefeng Xiao;Yitong Wang;Rui Wang;Shilei Wen;Xin Pan;Xingang Wang

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Year: 2023 | Conference Paper |

Cited by: Papers (29)

HTML

Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote to designing specialized architectures or parameters for specific segmentation tasks. These customized design paradigms lead to fragmentation between v...Show More

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Oin;Jie Wu;Pengxiang Yan;Ming Li;Ren Yuxi;Xuefeng Xiao;Yitong Wang;Rui Wang;Shilei Wen;Xin Pan;Xingang Wang

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Year: 2023 | Conference Paper |

Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search

Xin Xia;Xuefeng Xiao;Xing Wang;Min Zheng

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Year: 2022 | Conference Paper |

Cited by: Papers (14)

HTML

Neural Architecture Search (NAS) has attracted growing interest. To reduce the search cost, recent work has explored weight sharing across models and made major progress in One-Shot NAS. However, it has been observed that a model with higher one-shot model accuracy does not necessarily perform better when stand-alone trained. To address this issue, in this paper, we propose Progressive Automatic D...Show More

Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search

Xin Xia;Xuefeng Xiao;Xing Wang;Min Zheng

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Year: 2022 | Conference Paper |

Online Multi-Granularity Distillation for GAN Compression

Yuxi Ren;Jie Wu;Xuefeng Xiao;Jianchao Yang

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2021 | Conference Paper |

Cited by: Papers (29)

HTML

Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images, however, they are burdensome to deploy on resource-constrained devices due to ponderous computational costs and hulking memory usage. Although recent efforts on compressing GANs have acquired remarkable results, they still exist potential model redundancies and can be further compressed. To sol...Show More

Online Multi-Granularity Distillation for GAN Compression

Yuxi Ren;Jie Wu;Xuefeng Xiao;Jianchao Yang

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Year: 2021 | Conference Paper |

Box-Level Tube Tracking and Refinement for Vehicles Anomaly Detection

Jie Wu;Xionghui Wang;Xuefeng Xiao;Yitong Wang

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Year: 2021 | Conference Paper |

Cited by: Papers (6)

HTML

Traffic Anomaly detection is an essential computer vision task and plays a critical role in video structure analysis and urban traffic analysis. In this paper, we propose a box-level tracking and refinement algorithm to identify anomaly detection in road scenes. We first link the detection results to construct candidate spatio-temporal tubes via greedy search. Then the box-level refinement scheme ...Show More

Box-Level Tube Tracking and Refinement for Vehicles Anomaly Detection

Jie Wu;Xionghui Wang;Xuefeng Xiao;Yitong Wang

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Year: 2021 | Conference Paper |

Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report

Andrey Ignatov;Grigory Malivenko;Radu Timofte;Sheng Chen;Xin Xia;Zhaoyan Liu;Yuwei Zhang;Feng Zhu;Jiashi Li;Xuefeng Xiao;Yuan Tian;Xinglong Wu;Christos Kyrkou;Yixin Chen;Zexin Zhang;Yunbo Peng;Yue Lin;Saikat Dutta;Sourya Dipta Das;Nisarg A. Shah;Himanshu Kumar;Chao Ge;Pei-Lin Wu;Jin-Hua Du;Andrew Batutin;Juan Pablo Federico;Konrad Lyda;Levon Khojoyan;Abhishek Thanki;Sayak Paul;Shahid Siddiqui

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Year: 2021 | Conference Paper |

Cited by: Papers (15)

HTML

Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions th...Show More

Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report

Andrey Ignatov;Grigory Malivenko;Radu Timofte;Sheng Chen;Xin Xia;Zhaoyan Liu;Yuwei Zhang;Feng Zhu;Jiashi Li;Xuefeng Xiao;Yuan Tian;Xinglong Wu;Christos Kyrkou;Yixin Chen;Zexin Zhang;Yunbo Peng;Yue Lin;Saikat Dutta;Sourya Dipta Das;Nisarg A. Shah;Himanshu Kumar;Chao Ge;Pei-Lin Wu;Jin-Hua Du;Andrew Batutin;Juan Pablo Federico;Konrad Lyda;Levon Khojoyan;Abhishek Thanki;Sayak Paul;Shahid Siddiqui

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Year: 2021 | Conference Paper |

Accelerating and Compressing LSTM Based Model for Online Handwritten Chinese Character Recognition

Yafeng Yang;Kaihuan Liang;Xuefeng Xiao;Zecheng Xie;Lianwen Jin;Jun Sun;Weiying Zhou

2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Year: 2018 | Conference Paper |

Cited by: Papers (12)

HTML

With the development of deep learning tools, the online handwritten Chinese character recognition (HCCR) performance has been greatly improved by using deep neural networks (DNNs) especially for long short-term memory (LSTM). However, DNNs suffer from large consumption of computation and storage resources, which may cause problems for service providers, such as server pressure, longer service late...Show More

Accelerating and Compressing LSTM Based Model for Online Handwritten Chinese Character Recognition

Yafeng Yang;Kaihuan Liang;Xuefeng Xiao;Zecheng Xie;Lianwen Jin;Jun Sun;Weiying Zhou

2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Year: 2018 | Conference Paper |

Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling

Xuefeng Xiao;Yafeng Yang;Tasweer Ahmad;Lianwen Jin;Tianhai Chang

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

Year: 2017 | Conference Paper |

Cited by: Papers (13)

HTML

Currently, owing to the ubiquity of mobile devices, online handwritten Chinese character recognition (HCCR) has become one of the suitable choice for feeding input to cell phones and tablet devices. Over the past few years, larger and deeper convolutional neural networks (CNNs) have extensively been employed for improving character recognition performance. However, its substantial storage requirem...Show More

Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling

Xuefeng Xiao;Yafeng Yang;Tasweer Ahmad;Lianwen Jin;Tianhai Chang

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

Year: 2017 | Volume: 01 | Conference Paper |

A Comprehensive Analysis of Misclassified Handwritten Chinese Character Samples by Incorporating Human Recognition

Kaihuan Liang;Lianwen Jin;Zecheng Xie;Xuefeng Xiao;Weiguo Huang

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

Year: 2017 | Conference Paper |

Cited by: Papers (2)

HTML

The development of convolutional neural networks (CNN) has led to revolutionary progress in the resolution of the offline handwritten Chinese character recognition (HCCR) problem. As the recognition rate on a standard offline HCCR testbed is outstanding, a few samples that remain misclassified have kindled our interest. In this paper, with the help of human recognition results, we present a compre...Show More

A Comprehensive Analysis of Misclassified Handwritten Chinese Character Samples by Incorporating Human Recognition

Kaihuan Liang;Lianwen Jin;Zecheng Xie;Xuefeng Xiao;Weiguo Huang

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

Year: 2017 | Volume: 01 | Conference Paper |

IEEE Personal Account

Change username/password

Purchase Details

Payment Options
View Purchased Documents

Profile Information

Communications Preferences
Profession and Education
Technical interests

Need Help?

US & Canada: +1 800 678 4333
Worldwide: +1 732 981 0060
Contact & Support

Follow

About IEEE Xplore | Contact Us | Help | Accessibility | Terms of Use | Nondiscrimination Policy | IEEE Ethics Reporting | Sitemap | IEEE Privacy Policy

A public charity, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.

© Copyright 2025 IEEE - All rights reserved, including rights for text and data mining and training of artificial intelligence and similar technologies.

IEEE Account

Change Username/Password
Update Address

Purchase Details

Payment Options
Order History
View Purchased Documents

Profile Information

Communications Preferences
Profession and Education
Technical Interests

Need Help?

US & Canada: +1 800 678 4333
Worldwide: +1 732 981 0060
Contact & Support

About IEEE Xplore
Contact Us
Help
Accessibility
Terms of Use
Nondiscrimination Policy
Sitemap
Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Test Whats new message.