Jie Lei

ORCID: 0009-0002-5642-4745
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Video Surveillance and Tracking Methods
  • Advanced Image and Video Retrieval Techniques
  • Digital Media Forensic Detection
  • Advanced Chemical Sensor Technologies
  • Image and Object Detection Techniques
  • Analytical chemistry methods development
  • Advanced Memory and Neural Computing
  • Domain Adaptation and Few-Shot Learning
  • Geological and Geochemical Analysis
  • Robotics and Sensor-Based Localization
  • Infrared Target Detection Methodologies
  • Adversarial Robustness in Machine Learning
  • Crystal Structures and Properties
  • Laser Design and Applications
  • Human Pose and Action Recognition
  • Optical measurement and interference techniques
  • Advanced Neural Network Applications
  • Intermetallics and Advanced Alloy Properties
  • High-pressure geophysics and materials
  • Various Chemistry Research Topics
  • Advanced Measurement and Detection Methods
  • Collaborative and Sustainable Housing Initiatives
  • Anomaly Detection Techniques and Applications
  • Inertial Sensor and Navigation
  • Semiconductor materials and interfaces

Zhejiang University of Technology
2022-2025

China Agricultural University
2023

Fudan University
2020

Anhui University of Technology
2018

China Shenhua Energy (China)
2015

Binghamton University
2015

Mongolian University of Science and Technology
2013

10.1109/icassp49660.2025.10888850 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025-03-12

10.1109/icassp49660.2025.10890455 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025-03-12

Scrap steel grading is a vital stage of production. Thickness an important indicator to determine the grade scrap steel. Existing methods based on 2D vision cannot accurately estimate thickness due lack 3D information. Consequently, estimation results from satisfy requirements industry. To solve this problem, we propose vision-based system. We introduce novel feature descriptor that can perform edge detection organized point clouds. It detect pairs points points. Once all features completed,...

10.1109/tim.2023.3328089 article EN IEEE Transactions on Instrumentation and Measurement 2023-01-01

This paper adapts to carrying on studies document sustainable community and practice of in recent years, defines the communities, reveals origin evolution concept community, has summarized research progress community.

10.4028/www.scientific.net/amm.361-363.102 article EN Applied Mechanics and Materials 2013-08-08

Amphiboles have played a leading role in metamorphic petrology, from helping to define several facies forming the basis of geothermobarometry, if their thermodynamic mixing properties can be calibrated temperature and pressure formation. Compositional variations sodium- sodium-calcium-amphiboles may reveal important information about paleo-subduction zones but not been studied as much more common calcium-amphiboles. In this study we investigate amphibole solid solutions between...

10.2138/am-2015-5026 article EN American Mineralogist 2015-02-01

10.1109/icme57554.2024.10687937 article EN 2022 IEEE International Conference on Multimedia and Expo (ICME) 2024-07-15

Few-shot video object detection focuses on finding all the objects in a given query that belong to same class, only few support images of target an unseen class. Unfortunately, due blur or occlusion frames, using single-frame directly will greatly limit accuracy. The issue is significantly worse few-shot settings insufficient and timedomain information. In this paper, we propose temporal aggregation with context focusing framework (TACF) for detection, which aims fully use information...

10.1109/smc53992.2023.10394197 article EN 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2023-10-01

Virology is a basic biological science which takes virus as the research object.By introducing structure and detection technology of virus, especially function SARS-CoV-2 in course Analytical Chemistry, students can understand role chemistry development virology.At same time, introduction relevant knowledge create meaningful learning experience; it also be combined with ideology politics, so that realize importance concepts value orientation interdisciplinarity.

10.3866/pku.dxhx202004148 article EN University Chemistry 2020-01-01

In the field of weakly supervised Semantic segmentation (WSSS), Class Activation Maps (CAM) are typically adopted to generate pseudo masks. Yet, we find that crux unsatisfactory masks is incomplete CAM. Specifically, as convolutional neural networks tend be dominated by specific regions in high-confidence channels feature maps during prediction, extracted CAM contains only parts object. To address this issue, propose Disturbed (DCAM), a simple yet effective method for WSSS. We adopt binary...

10.2139/ssrn.4310669 article EN SSRN Electronic Journal 2022-01-01
Coming Soon ...