Pei Wang

I am an applied scientist with AWS AI Labs, where I work on computer vision and machine learning. I received my Ph.D. degree from UC San Diego, advised by Nuno Vasconcelos.

I have fortunately worked as a research scientist intern at Adobe Research and an applied scientist intern at Amazon AWS.

Email: peiwang062[at]gmail[dot]com, pwwng[at]amazon[dot]com

Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo

Recent News
  • [03/2023] One paper was accepted by CVPR2023.
  • [02/2023] One paper was accepted by T-PAMI.
  • [11/2022] I have successfully defended my phd thesis.

Research

I am interested in computer vision and machine learning, especially object detection, image segmentation, semi- and self-supervised learning, human-in-the-loop learning, explainable AI, image synthesis, etc.

Towards Professional Level Crowd Annotation of Expert Domain Data
Pei Wang, and Nuno Vasconcelos
CVPR, 2023
code / video

A Generalized Explanation Framework for Visualization of Deep Learning Model Predictions
Pei Wang and Nuno Vasconcelos
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
paper

Omni-DETR: Omni-Supervised Object Detection with Transformers
Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele and Stefano Soatto
CVPR, 2022
paper / code / video

A Machine Teaching Framework for Scalable Recognition
Pei Wang and Nuno Vasconcelos
ICCV, 2021
paper / code / video

Gradient-Based Algorithms for Machine Teaching
Pei Wang, Kabir Nagrecha and Nuno Vasconcelos
CVPR, 2021
paper / code / video

Rethinking and Improving the Robustness of Image Style Transfer
Pei Wang, Yijun Li and Nuno Vasconcelos
CVPR (Oral, Best paper candidate), 2021
paper / code / video

IMAGINE: Image Synthesis by Image-Guided Model Inversion
Pei Wang, Yijun Li, Krishna Kumar Singh, Jingwan Lu, and Nuno Vasconcelos
CVPR, 2021
paper / code / video

Dynamic Transfer for Multi-Source Domain Adaptation
Yunsheng Li, Lu Yuan, Yinpeng Chen, Pei Wang, Nuno Vasconcelos
CVPR, 2021
paper / code / video

Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
Tz-Ying Wu, Pedro Morgado, Pei Wang, Chih-Hui Ho, and Nuno Vasconcelos
ECCV, 2020
paper / code / video

SCOUT: Self-aware Discriminant Counterfactual Explanations
Pei Wang and Nuno Vasconcelos
CVPR, 2020
paper / code / video

Deliberative Explanations: visualizing network insecurities
Pei Wang and Nuno Vasconcelos
NeurIPS, 2019
paper / code

Towards Realistic Predictors
Pei Wang and Nuno Vasconcelos
ECCV (Oral), 2018
paper / code / video

Context-dependent random walk graph kernels and tree pattern graph matching kernels with applications to action recognition
Weiming Hu, Baoxin Wu, Pei Wang, Chunfeng Yuan, Yangxi Li, and Stephen Maybank
IEEE Transactions on Image Processing, 2018
paper

Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition
Pei Wang Chunfeng Yuan, Weiming Hu, Bing Li and Yanning Zhang
ECCV, 2016
paper


Service
  • Journal Reviewer: T-PAMI, IJCV, T-IP
  • Conference Reviewer: CVPR23, NeurIPS22, ICML22, CVPR22, ICLR22, NeurIPS21, ICCV21, ICML21, CVPR21, ICLR21, NeurIPS20, ICML20, ECCV20, CVPR20, NeurIPS19, ICCV19, CVPR19


template credit to Jon Barron