Zhengze Xu

ORCID: 0000-0001-9345-2273
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Neural Network Applications
  • Human Pose and Action Recognition
  • Neural Networks and Applications
  • Hand Gesture Recognition Systems
  • Brain Tumor Detection and Classification
  • Gait Recognition and Analysis
  • Automated Road and Building Extraction
  • Video Surveillance and Tracking Methods

Huazhong University of Science and Technology
2024

East China Normal University
2023

Shanghai Jian Qiao University
2023

Recent real-time semantic segmentation methods usually adopt an additional branch to pursue rich long-range context. However, the incurs undesirable computational overhead and slows inference speed. To eliminate this dilemma, we propose SCTNet, a single CNN with transformer information for segmentation. SCTNet enjoys representations of inference-free while retaining high efficiency lightweight CNN. utilizes as training-only considering its superb ability extract With help proposed...

10.1609/aaai.v38i6.28457 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2024-03-24

Previous studies are mainly focused on the works that depth image is treated as flat image, and then data tends to be mapped gray values during convolution processing features extraction. To address this issue, an approach of 3D CNN hand pose estimation with end-to-end hierarchical model physical constraints proposed. After reconstruction space structure from converted into voxel grid for further by CNN. The method makes improvements embedding algorithm networks, resulting train at fast...

10.14311/nnw.2023.33.003 article EN Neural Network World 2023-01-01

Recent real-time semantic segmentation methods usually adopt an additional branch to pursue rich long-range context. However, the incurs undesirable computational overhead and slows inference speed. To eliminate this dilemma, we propose SCTNet, a single CNN with transformer information for segmentation. SCTNet enjoys representations of inference-free while retaining high efficiency lightweight CNN. utilizes as training-only considering its superb ability extract With help proposed...

10.48550/arxiv.2312.17071 preprint EN other-oa arXiv (Cornell University) 2023-01-01
Coming Soon ...