2 citations · 12 across the 12 of their papers we have counts for
6 papers · 1 filter
When SAM Meets Sonar Images
Lin Wang, Xiufen Ye, Liqiang Zhu +4
Segment Anything Model (SAM) has revolutionized the way of segmentation. However, SAM's performance may decline when applied to tasks involving domains that differ from natural ima…
A Lightweight Reconstruction Network for Surface Defect Inspection
Chao Hu, Jian Yao, Weijie Wu +2
Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes…
IDMS: Instance Depth for Multi-scale Monocular 3D Object Detection
Chao Hu, Liqiang Zhu, Weibing Qiu +1
Due to the lack of depth information of images and poor detection accuracy in monocular 3D object detection, we proposed the instance depth for multi-scale monocular 3D object dete…
Data Augmentation Vision Transformer for Fine-grained Image Classification
Chao Hu, Liqiang Zhu, Weibin Qiu +1
Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different…
Spatio-Temporal-based Context Fusion for Video Anomaly Detection
Chao Hu, Weibin Qiu, Weijie Wu +1
Video anomaly detection aims to discover abnormal events in videos, and the principal objects are target objects such as people and vehicles. Each target in the video data has rich…
Normal Learning in Videos with Attention Prototype Network
Chao Hu, Fan Wu, Weijie Wu +2
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstructio…