Bowei Chen

I am a second-year MSR student in Robotics Institute at Carnegie Mellon University, supervised by Prof. Srinivasa Narasimhan. I also work with Prof. Martial Hebert, Dr. Sing Bing Kang, and Dr. Tiancheng Zhi.

I did my bachelors at Northeastern University , where I worked with Prof. Jean-Fran├žois Lalonde, Prof. Guibing Guo, and Dr. Fajie Yuan.

Email  /  CV  /  Google Scholar  / 

profile photo
Research

My research interests lie at the intersection of computer vision and graphics, including neural rendering, inverse rendering and 3D reconstruction. Previously, I worked on developing recommender systems methods.

Publication
Neural Repeated Texture Field (NeRTF): Learning Continuous Implicit Representation for Near-Periodic Patterns.
Bowei Chen, Tiancheng Zhi, Martial Hebert, Srinivasa Narasimhan,
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 (Under Review)

Presented a single image based framework to learn Near-Periodic Patterns (NPP) representation, which was adapted to various applications including completion, resolution-enhanced remapping, and segmentation.

Leveraging Title-Abstract Attentive Semantics for Paper Recommendation
Guibing Guo, Bowei Chen (only student researcher), Xiaoyan Zhang, Zhirong Liu, Zhenhua Dong, Xiuqiang He.
The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020

Propose a two-level attentive neural network to capture title-abstract semantics relationships for paper recommendation.

IPGAN: Generating Informative Item Pairs by Adversarial Sampling
Guibing Guo, Huan Zhou, Bowei Chen, Zhirong Liu, Xiao Xu,
IEEE Transactions on Neural Networks and Learning Systems, TNNLS.

Propose an Item Pair Generative Adversarial Network to to sample effective positive and negative instances for representation learning.

BiGAN: Collaborative Filtering with Bidirectional Generative Adversarial Networks
Rui Ding, Guibing Guo, Xiaochun Yang, Bowei Chen, Zhirong Liu, Xiuqiang He.
SIAM International Conference on Data Mining, SDM 2020

Introduce a bidirectional adversarial recommendation method to learn user and item representations.

Adversarial Path Sampling for Recommender Systems
Rui Ding, Bowei Chen, Guibing Guo, Xiaochun Yang.
IEEE Intelligent Systems.

Introduce a novel adversarial path-based recommendation model to address these limitations of existing GAN-based methods in recommendation task by naturally incorporating auxiliary information.

Multi-view visual Bayesian personalized ranking for restaurant recommendation
Xiaoyan Zhang, Haihua Luo, Bowei Chen, Guibing Guo.
Applied Intelligence 2020

Present a new factorization model that combines multi-view visual information with the implicit feedback data for restaurant prediction and ranking.

Project
Learning High Dynamic Range from Indoor Panoramas
Supervised by Prof. Jean-Fran├žois Lalonde.
On progress,

Propose a deep learning method using SLAM to generate HDR image given a LDR video.

Non-autoregressive Sequence Generation Method Based on Bi-directional Dilated Convolutional Neural Network
Supervised by Dr. Fajie Yuan.
Patent,

Propose a non-autoregressive generative method based on bi-directional dilated convolutional neural network to generate sequences of items (words). A mask iteration algorithm is introduced to refine the generated sequences.

Recommender Systems Methods Based on Deep Learning
Supervised by Prof. Guibing Guo.

Propose recommender systems methods based on deep learning architectures such as GAN, CNN, RNN.


The website's style is borrowed from this amazing guy.