Computer vision

Artificial intelligence

Breakthrough in Mushroom Image Classification using Artificial Intelligence

Researchers from the Haldia Institute of Technology have achieved significant breakthroughs in classifying mushroom images into multiple categories using deep learning-based models. The team, led by Bidesh Chakraborty, developed a novel approach that incorporates the convolutional block attention module (CBAM) with a transfer learning-based Xception architecture, resulting in superior performance

Computer vision

Breakthrough in Neuromorphic Computing: ASNA-Flow Accelerator for Real-Time Optical Flow Estimation

Neuromorphic vision systems have gained attention for their potential in edge deployment of optical flow estimation due to their ultralow power and resource efficiency. However, current neuromorphic computing platforms lack specialized architectures optimized for this problem domain. To address this limitation, researchers from Sun Yat-sen University have developed ASNA-Flow, an

Artificial intelligence

Tech Startups Secure Significant Venture Capital Funding Rounds to Drive Innovation and Growth

Several tech startups in the launchpad ecosystem have announced new venture capital funding rounds to bolster innovation and business growth. These funding rounds are expected to enable the companies to expand their product offerings, strengthen their technological capabilities, and increase their market presence. Launchpad, MatrixSpace, Prisma Photonics, Intelo.ai, and

Artificial intelligence

Artificial Intelligence Identifies Prognostic Markers for GI Cancers

Researchers from Emory University have employed machine learning and computer vision to quantify tumor-infiltrating lymphocytes (TILs) in gastrointestinal (GI) cancers, including esophagus, stomach, colon, rectum, pancreas, and liver cancers. The study, which included 1700 patients from four different sites, aimed to evaluate the prognostic significance of computational pathology features. The

Artificial intelligence

Lightweight Camouflaged Object Detection via Holistic Understanding of Local-Global Features and Multi-Scale Fusion

Researchers from Florida Atlantic University have proposed a novel approach to camouflaged object detection, dubbed LiteCOD, which showcases improved detection accuracy and computational efficiency. This breakthrough technique, detailed in their research paper, aims to overcome the limitations of existing methods in real-time applications, particularly on mobile devices and edge computing