- Human Pose and Action Recognition
- Remote-Sensing Image Classification
- Anomaly Detection Techniques and Applications
- Advanced Image Fusion Techniques
- Multimodal Machine Learning Applications
- Video Surveillance and Tracking Methods
- Domain Adaptation and Few-Shot Learning
- Video Analysis and Summarization
- Gait Recognition and Analysis
- Geochemistry and Geologic Mapping
- Remote Sensing and Land Use
- Topic Modeling
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Image and Signal Denoising Methods
- Remote Sensing in Agriculture
University of Electronic Science and Technology of China
2022-2024
Online action detection plays a vital role in video understanding and can be widely used various analysis applications. This task aims to detect actions at the current moment within long untrimmed streams. However, accurately identifying action-background transitions that are ambiguous terms of time during challenging due similarity between background clips, adding difficulty finding suitable division them. To address this issue, we propose hard clip mining method based on deep metric...
Although the convolutional neural network (CNN)-based and vision transformer (ViT)-based methods have achieved effective remote sensing scene classification results in past few years, CNN's inductive bias ViT's single spatial scale limit further improvement of accuracy. To address these problems, this paper, we proposed a novel multi-scale (MS-ViT) for image classification, consists two different information streams that extract information, hybrid attention module fuses classifier to...