IEEE

A Lightweight Network of CNN and Transformer Feature Fusion for Image Super-Resolution

Abstract: Currently, many super-resolution (SR) methods based on CNNs and Transformers have become increasingly complex, which imposes significant limitations on their application in mobile platforms.
IEEE

A Hybrid Approach Using CNN Feature Extraction and SVM/XGBoost for Lung Nodule Classification

Abstract: Early detection of lung cancer is highly beneficial for patient survival. This paper proposes a hybrid deep learning diagnostic pipeline for pulmonary nodules in chest CT. We constructed a ...
IEEE

High-Accuracy Mapping of Coastal and Wetland Areas Using Multisensor Data Fusion and Deep Feature Learning

Abstract: Coastal and wetland regions play vital roles in ecosystem stability, economic development, and climate regulation, particularly along the rapidly changing coastline of eastern Asia. Timely ...

(CNW) Ecopia AI and Nearmap Launch Off-the-Shelf Advanced Transportation Feature Data Across North America

High-precision transportation intelligence, powered by Nearmap high-recency aerial imagery and Ecopia's AI feature extraction, delivers decision-ready geospatial context at scale SALT LAKE CITY, Jan.
IEEE

Classifying Nutritional Deficiencies in Coffee Leaf Using Transfer Learning and Gradient-Weighted Class Activation Mapping (Grad-CAM) Visualization

Abstract: Coffee is a very popular beverage around the world. The production coffee can be affected by nutrition deficiencies and result in massive underproduction. This makes early detection of ...
IEEE

Human Age Group Classification Using CNN and Vision Transformer-Based Feature Extraction

Abstract: The human face reveals significant information about an individual’s identity, age, gender, emotion, and ethnicity. In face-to-face communication, age plays a vital role, influencing ...
IEEE

CNN-Transformer Based Image Emotion Recognition with Multi-Scale Feature Enhancement

Abstract: Image emotion recognition aims to analyze and understand the emotions conveyed by images. Due to the high similarity of features between different emotion categories, the model is prone to ...
IEEE

A Dynamic Feature Caching Mechanism for Accelerating CNN Real-time Inference

Abstract: To address the computational efficiency bottle-neck faced by large-scale convolutional neural networks when deployed on edge devices, this paper proposes a dynamic feature caching mechanism ...
IEEE

Mapping Deprived Urban Areas with an Optimized Loss-weight Feature-guided Deep Learning Model

Abstract: The growth of deprived urban areas (DUA), often associated with slums or informal settlements, is one of the consequences of rapid urbanization. Earth Observation (EO) data provides valuable ...
IEEE

Deep Learning for Accurate Classification of Pulmonary Edema Severity in Chest X-Rays: A Comparative Evaluation of CNN Models with Grad-CAM Feature Visualization

Abstract: Accurate classification of pulmonary edema severity is essential for timely diagnosis and effective management, as each severity level requires distinct therapeutic interventions.
GitHub

SLAMTEC Aurora Remote SDK in Python

This is a Python implementation of the SLAMTEC Aurora Remote SDK which is based on the Aurora SDK for C++. It provides comprehensive Python bindings for Aurora's 3D SLAM device including pose tracking ...
IEEE

A CNN-Transformer Hybrid Network with Boundary Guidance for Mapping Cropland Field Parcels from High-Resolution Remote Sensing Imagery

Abstract: Accurate mapping of cropland field parcels (CFPs) is essential for efficient agricultural production and management. However, CFPs in high-resolution remote sensing imagery exhibit ...