Xianpeng Liu

I received my Ph.D. degree in Electrical Engineering from North Carolina State University (NCSU), advised by Prof. Tianfu Wu.

Github  /  LinkedIn  /  Google Scholar  /  Resume

Email: xliu59 [at] ncsu.edu

profile photo
News

2024-02      One paper was accepted by CVPR 2024.

2023-12      I defended my Ph.D. dissertation.

2023-07      One paper was accepted by ICCV 2023.

2023-05      I passed my oral exam and proposal.

2023-02      One paper was accepted by CVPR 2023.

2022-05      I started my research internship at Innopeak Tech.

2022-01      One paper was accepted by AAAI 2022.

Research

I have a broad interest in 2D and 3D computer vision. My current research focuses on 3D Object Detection, 3D Reconstruction, Human Pose Estimation, etc. Below is a selected list of my works. Full publication can be found at my google scholar page.

Multi-View Attentive Contextualization for Multi-View 3D Object Detection.
Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Paper  /  Project Page

A simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection.

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver.
Xianpeng Liu, Ce Zheng, Kelvin Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu.
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Paper  /  Project Page

A monocular 3D object detection method with a novel 3D space top-down bounding box denoising paradigm.

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
Ce Zheng, Xianpeng Liu, Guo-Jun Qi, Chen Chen.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Paper  /  Project page

A lightweight pure transformer architecture named POoling aTtention TransformER (POTTER) for the HMR task from single images.

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection.
Xianpeng Liu, Nan Xue, Tianfu Wu.
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022
Paper  /  Code

Leverage Monocular Contexts (MonoCon) to achieve rapid and precise 3D object detection from a single image.

Toward Effective Automated Content Analysis via Crowdsourcing.
Jiele Wu, Chau-Wai Wong, Xinyan Zhao, Xianpeng Liu.
IEEE International Conference on Multimedia and Expo (ICME), 2021
Paper

Design a quality-aware semantic data annotation system to achieve high annotation quality for crowdsourcing.

Video-Based Wetting Detection For Blended Fabrics.
Xianpeng Liu, Chau-Wai Wong.
Asilomar Conference on Signals, Systems, and Computers, 2019
Paper  /  Poster

Perform Likelihood-ratio test to achieve precise wetting detection from videos.

Service
Journal Reviewer: Image and Vision Computing, Neurocomputing, Neural Networks, IEEE/CAA Journal of Automatica Sinica, Frontiers of Computer Science
Conference Reviewer: CVPR, ICCV, ECCV