Adults
Researchers at Zhejiang University in Hangzhou, People's Republic of China, have developed a Transformer-based method for estimating energy expenditure (EE) accurately and conveniently in sports science. The method, called Energy Expenditure Estimation Skeleton Transformer (E3SFormer), uses a novel approach that features dual Transformer branches for simultaneous action recognition
Adults
Researchers at Zhejiang University in Hangzhou, People's Republic of China, have developed a Transformer-based method for estimating energy expenditure (EE) accurately and conveniently in sports science. The method, called Energy Expenditure Estimation Skeleton Transformer (E3SFormer), uses a novel approach that features dual Transformer branches for simultaneous action recognition
Computer vision
Researchers at Purdue University have shed new light on the theoretical justification of knowledge distillation (KD), a widely used technique in machine learning that enables the transfer of predictive behavior from high-capacity teacher models to compact student models. With financial support from the National Science Foundation (NSF), the team conducted
Adults
Researchers at Zhejiang University in Hangzhou, People's Republic of China, have developed a Transformer-based method for estimating energy expenditure (EE) accurately and conveniently in sports science. The method, called Energy Expenditure Estimation Skeleton Transformer (E3SFormer), uses a novel approach that features dual Transformer branches for simultaneous action recognition
Robotics industry
Robots that navigate environments and detect humans in their vicinity require accurate knowledge of their surroundings, especially when it comes to human presence. Traditionally, computer vision has been the primary approach for detecting humans, but robotics researchers have now highlighted the potential of 2D range finders as an often-overlooked hardware
Artificial intelligence
Researchers at Boston University School of Dental Medicine have published a study exploring the impact of artificial intelligence (AI) on endodontic education and clinical practice. The investigation highlights the benefits of AI tools, such as machine learning, neural networks, and computer vision, in enhancing diagnostic accuracy, procedural skills, and personalized
Artificial intelligence
The partnership between Curv AI and the Pro Cheer League, along with Varsity Spirit, is set to transform the world of cheerleading by introducing the world's first AI Sport Scientist. This game-changing technology uses advanced computer vision and smartphone video analysis to measure athleticism, movement efficiencies, and cheer-specific
Artificial intelligence
Deep-tech company PointAI, formerly known as Try ND Buy, has successfully raised Rs. 47 crore in a Pre-Series A funding round led by Yali Capital, Lip-Bu Tan, and Tremis Capital. The company plans to utilize the funding to accelerate product innovation, expand its market presence, and strengthen its technological capabilities.
Artificial intelligence
A team of researchers at the Leibniz Institute for Evolution and Biodiversity Science has made significant progress in using Artificial Intelligence to automate taxonomic species descriptions. By combining Vision Transformers (ViTs) and Large Language Models (LLMs), they have created a Vision Language Model (VLM) that can approximate taxonomic species descriptions
Artificial intelligence
Research by Jiangsu University has led to groundbreaking advancements in artificial intelligence technology, transforming the way agricultural pest detection and control systems operate. The study, published in the Agriculture journal, highlights the effectiveness of deep-learning-based image recognition methods for pest identification and their integrated applications in drone-based remote sensing, spectral
Artificial intelligence
Patent application by inventor Raj, Benevan Susanna Antony, filed on April 1, 2024, and made available online on October 2, 2025, describes systems and methods for negative spacing labeling and shadow labeling for computer vision. The invention enables computers to derive meaningful information from digital images and videos by identifying
Artificial neural networks
Researchers in China have made significant strides in the field of free-space optical communication, developing a computer vision-assisted tracking system that maintains robust optical alignment in real-time. This innovative system, which combines a lightweight convolutional neural network (CNN) with a Kalman filter, achieves high tracking accuracy and reliable data transmission
