no code implementations • CVPR 2023 • Zhixin Ling, Zhen Xing, Xiangdong Zhou, Manliang Cao, Guichun Zhou
In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion.
1 code implementation • 20 Jun 2023 • Haotian Chen, Bingsheng Chen, Xiangdong Zhou
Then, we conduct investigations and reveal the fact that: In contrast to humans, the representative state-of-the-art (SOTA) models in DocRE exhibit different decision rules.
no code implementations • 30 Jul 2022 • Zhen Xing, Yijiang Chen, Zhixin Ling, Xiangdong Zhou, Yu Xiang
In this paper, we present a Memory Prior Contrastive Network (MPCN) that can store shape prior knowledge in a few-shot learning based 3D reconstruction framework.
no code implementations • 2 Jun 2022 • Zhidan Liu, Zhen Xing, Xiangdong Zhou, Yijiang Chen, Guichun Zhou
We enhance the performance of image-based methods for category-agnostic object pose estimation by exploiting 3D knowledge learned by a multi-modal method.
no code implementations • 8 Mar 2022 • Yijiang Chen, Xiangdong Zhou, Zhen Xing, Zhidan Liu, Minyang Xu
Many previous works focus on the pretext task of self-supervised learning and usually neglect the complex problem of MTS encoding, leading to unpromising results.
no code implementations • 15 May 2021 • Lei Sun, Jia Wang, Kailun Yang, Kaikai Wu, Xiangdong Zhou, Kaiwei Wang, Jian Bai
A lightweight panoramic annular semantic segmentation neural network model is designed to achieve high-accuracy and real-time scene parsing.
Ranked #69 on Semantic Segmentation on Cityscapes val
1 code implementation • 7 Apr 2019 • Min Peng, Chongyang Wang, Tao Bi, Tong Chen, Xiangdong Zhou, Yu Shi
As researchers working on such topics are moving to learn from the nature of micro-expression, the practice of using deep learning techniques has evolved from processing the entire video clip of micro-expression to the recognition on apex frame.