Scholar
xiaoguang li
Google Scholar ID: RP7frMoAAAAJ
University of South Carolina
Citations & Impact
Citations
353
H-index
7
i10-index
6
Publications
13
Co-authors
9
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications:
- - DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation, CVPR, 2025
- - Crossmodal Few-shot 3D Point Cloud Semantic Segmentation via View Synthesis, ACM MM, 2024
- - SAIR: Learning Semantic-aware Implicit Representation, ECCV, 2024
- - Orthogonal Dictionary Guided Shape Completion Network for Point Cloud, AAAI, 2024
- - Leveraging Inpainting for Single-Image Shadow Removal, ICCV, 2023
- - CLIP-Driven Unsupervised Learning for Multi-Label Image Classification, ICCV, 2023
- - MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting, CVPR, 2022
- - JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting, ACM MM, 2021
- - Deep Learning for Object Detection in Materials-Science Images, IEEE SPM, 2021
Research Experience
- Currently working at eBay as an applied researcher.
Education
- 2020 - 2024, Ph.D. in Computer Science, University of South Carolina, United States
- 2020 - 2022, M.S. in Computer Science, University of South Carolina, United States
- 2009 - 2013, B.S. in Computer Science, Zhengzhou University, China
Background
- Currently working at eBay as an applied researcher. Research focuses on computer vision, particularly for (1) multi-modal retrieval, (2) restoration tasks such as image and video inpainting, point cloud completion, shadow removal, and super-resolution, and (3) object detection, image classification, and segmentation, including open-vocabulary semantic segmentation and point cloud segmentation.
