Search Results for author:
Found 8 papers, 1 papers with code
When SAM Meets Sonar Images
Notably, there is a lack of research on the application of SAM to sonar imaging.
A Lightweight Reconstruction Network for Surface Defect Inspection
Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics.
IDMS: Instance Depth for Multi-scale Monocular 3D Object Detection
Firstly, to enhance the model's processing ability for different scale targets, a multi-scale perception module based on dilated convolution is designed, and the depth features containing multi-scale information are re-refined from both spatial and channel directions considering the inconsistency between feature maps of different scales.
Data Augmentation Vision Transformer for Fine-grained Image Classification
Recently, the vision transformer (ViT) has made breakthroughs in image recognition.
Pedestrian Spatio-Temporal Information Fusion For Video Anomaly Detection
Aiming at the problem that the current video anomaly detection cannot fully use the temporal information and ignore the diversity of normal behavior, an anomaly detection method is proposed to integrate the spatiotemporal information of pedestrians.
Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance
Then, the semantic features of the motion representation are obtained through the local attention mechanism in the motion guidance module to obtain the high-level semantic features of the appearance representation.
Spatio-Temporal-based Context Fusion for Video Anomaly Detection
Motion features are used multiple targets in the video frame to construct spatial context simultaneously, re-encoding the target appearance and motion features, and finally reconstructing the above features through the spatio-temporal dual-stream network, and using the reconstruction error to represent the abnormal score.
Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression
To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps.
