Results 91 to 100 of about 103,551 (264)

Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions

Advanced Science, EarlyView.
Long‐Tea‐CLIP (Contrastive Language‐Image Pre‐training) presents a multimodal AI framework that integrates visual, metabolomic, and sensory knowledge to grade green tea across appearance, soup color, aroma, taste, and infused leaf. By combining expert‐guided modeling with CLIP‐supervised learning, the system delivers fine‐grained quality evaluation and
Yanqun Xu, Zhengfang Xue, Qing Luo, Xu Liu, Yongquan Xu, Jing Huang, Xingcai Zhang, Xinyuan Zhang, Zhonghua Liu, Zisheng Luo   +9 more
wiley   +1 more source

Ambipolar Organic–Inorganic Heterostructure Transistor Array for Integrated Visual Information Processing

Advanced Science, EarlyView.
We present an organic–inorganic heterostructure transistor array for neuromorphic computing, achieving 95.6% MNIST accuracy and 1.2 fJ per operation, with dynamic spatiotemporal encoding and precise vehicle direction detection under combined optical and electrical stimulation.
Wen‐Min Zhong, Wenbin Zhang, Yu‐Xiang Zeng, JiYu Zhao, Ziqi Jia, Loganathan Veeramuthu, Guanglong Ding, Yan Yan, Meng Zhang, Su‐Ting Han, Vellaisamy A. L. Roy, Fengyun Wang, Chi‐Ching Kuo, Ye Zhou   +13 more
wiley   +1 more source

Dynamic Self‐Clickable Decellularized Matrix Hydrogels for Regulating Vascularity and Enhancing Muscle Regeneration

Advanced Science, EarlyView.
Dynamic decellularized hydrogels are prepared using bovine decellularized small intestine submucosa (SIS) norbornene (dSIS‐NB). Bovine dSIS contained significant amounts of disulfide‐rich fibrillin‐I, enabling ‘self‐clickable’ thiol‐norbornene gelation and spatiotemporal tuning of hydrogel physicochemical properties.
Van Thuy Duong, Tuba Marjan, Ngoc Ha Luong, Taimoor H. Qazi, Chien‐Chi Lin   +4 more
wiley   +1 more source

Learning 3D-Gaussian Simulators from RGB Videos

Realistic simulation is critical for applications ranging from robotics to animation. Learned simulators have emerged as a possibility to capture real world physics directly from video data, but very often require privileged information such as depth information, particle tracks and hand-engineered features to maintain spatial and temporal consistency.
Zhobro, Mikel, Geist, Andreas René, Martius, Georg   +2 more
openaire   +2 more sources

Smart Exploration of Perovskite Photovoltaics: From AI Driven Discovery to Autonomous Laboratories

Advanced Energy Materials, EarlyView.
In this review, we summarize the fundamentals of AI in automated materials science, and review AI applications in perovskite solar cells. Then, we sum up recent progress in AI‐guided manufacturing optimization, and highlight AI‐driven high‐throughput and autonomous laboratories.
Wenning Chen, Zheyu Zhang, Kelvian T. Mularso, Bonghyun Jo, Hyun Suk Jung   +4 more
wiley   +1 more source

Interactive Prompt‐Guided Robotic Grasping for Arbitrary Objects Based on Promptable Segment Anything Model and Force‐Closure Analysis

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
A laser pointer‐guided robotic grasping method for arbitrary objects based on promptable segment anything model and force‐closure analysis is presented. Grasp generation methods based on force‐closure analysis can calculate the optimal grasps for objects through their appearances. However, the limited visual perception ability makes robots difficult to
Yan Liu, Yaxin Liu, Ruiqing Han, Kai Zheng, Yufeng Yao, Ming Zhong   +5 more
wiley   +1 more source

Accurate and Anti‐Interference Control of Computer Vision‐Assisted Light‐Driven Liquid Crystal Elastomer Actuator

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
This article introduces a computer vision‐assisted control strategy for light‐driven liquid crystal elastomer actuators. Through negative feedback regulation, the liquid crystal elastomer actuator exhibits accurate and stable bending deformation in complex environments.
Wei Zhang, Zongxuan Wu, Li Lin, Yanjun Liu, Xiaoying Tang, Yajing Shen, Dan Luo   +6 more
wiley   +1 more source

BMPCQA: Bioinspired Metaverse Point Cloud Quality Assessment Based on Large Multimodal Models

Advanced Intelligent Systems, EarlyView.
This study presents a bioinspired metaverse point cloud quality assessment metric, which simulates the human visual evaluation process to perform the point cloud quality assessment task. It first extracts rendering projection video features, normal image features, and point cloud patch features, which are then fed into a large multimodal model to ...
Huiyu Duan, Kang Fu, Sijing Wu, Yunhao Li, Zicheng Zhang, Qiang Hu, Xiongkuo Min, Guangtao Zhai   +7 more
wiley   +1 more source

Context Awareness and Human–Robot Interaction Optimization for Museum Intelligent Guide Robot

Advanced Intelligent Systems, EarlyView.
This study presents a context‐aware human–robot interaction framework designed for intelligent museum guide robots. The system features a three‐layer architecture—perception, understanding, and behavior execution—that enables adaptive and meaningful interactions with museum visitors.
Anna Zou, Yue Meng, Shijing Tong
wiley   +1 more source

A comprehensive survey on RGB-D-based human action recognition: algorithms, datasets, and popular applications

EURASIP Journal on Image and Video Processing
Due to the rapid advances in computer vision and deep learning, human action recognition has become one of the most important representative tasks for video understanding.
Yumin Zhang, Yanyong Wang
doaj   +1 more source