GitHub

OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts [NeurIPS 2025]

OpenWorldSAM pushes the boundaries of SAM2 by enabling open-vocabulary segmentation with flexible language prompts. [2026-1-4]: Demo release: we’ve added simple demos to run OpenWorldSAM on images ...
IEEE

Probabilistic Forecasting for Battery Health Estimation Using CNN-LSTM on Augmented Multi-Operation Data

Abstract: Ensuring the safety and reliability of electric vehicles and energy storage systems requires an effective evaluation of lithium-ion battery State of Health (SOH). Most current methods are ...
IEEE

An Ensemble Deep Learning Model Using CNN, LSTM and Autoencoder for EEG-Based Parkinson’s Disease Classification

Abstract: Parkinson's disease is a neurological disorder hat effects the movements including shaking, stiffness, difficulty while walking and speaking. This condition will occur when the nerve cells ...
IEEE

Semi-Supervised Breast Lesion Segmentation Using Confidence-Ranked Features and Bi-Level Prototypes

Abstract: Automated lesion segmentation through breast ultrasound (BUS) images is an essential prerequisite in computer-aided diagnosis. However, the task of breast segmentation remains challenging, ...
IEEE

Rainfall Prediction over India using a hybrid CNN-LSTM model

Abstract: In agricultural planning and water management, accurate rainfall forecasting is critical, especially for a country like India. The current study explores the application of a hybrid deep ...
IEEE

Cinematic Scene Classification and Shot Boundary Detection Using Hybrid CNN-LSTM Networks

Abstract: Cinematic scene classification and shot border recognition are two important tasks that are used to automate the analysis and division of video content. This makes it easier to find and ...
IEEE

Enhanced Pneumonia Diagnosis using Mask R-CNN and ResNet50-Based Deep Learning on Chest X-Rays

Abstract: This study proposes a robust and efficient two-stage deep learning framework aimed at the accurate classification of Chest X-ray images into NORMAL and PNEUMONIA categories. The methodology ...
IEEE

MobileUNETR+: An Efficient Medical Image Segmentation Network Integrating Self-Attention and Dual-Pathway Strategies

Abstract: Accurate medical image segmentation is essential for clinical diagnosis and treatment planning, especially in the early detection of skin cancer. Although U-Net-based architectures have ...
IEEE

A Lightweight Spatial–Spectral Deformable CNN for UAV Hyperspectral Image Classification

Abstract: In recent years, uncrewed aerial vehicle (UAV) technology has shown great potential for application in hyperspectral image (HSI) classification tasks due to its advantages of flexible ...
CNN

How to avoid getting into trouble when using AI at work

Love it or hate it, AI is increasingly becoming integral to the way we work. So, like a lot of employees, you’ve started using it for your assignments. That’s great – unless you’re not clear on what ...
IEEE

Custom Dataset-Driven Unsupervised Low-Light Image Enhancement Using 2D CNN

Abstract: Low-light image augmentation, which seeks to improve image visibility and quality under low illumination, is an important job in computer vision. We investigate underexposure image ...
IEEE

Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation

Abstract: Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to ...