Results 61 to 70 of about 12,717 (259)

MFINet: A Novel Zero-Shot Remote Sensing Scene Classification Network Based on Multimodal Feature Interaction

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Zero-shot classification models aim to recognize image categories that are not included in the training phase by learning seen scenes with semantic information.
Xiaomeng Tan, Bobo Xi, Haitao Xu, Yunsong Li, Changbin Xue, Jocelyn Chanussot   +5 more
doaj   +1 more source

Zero‐shot learning by exploiting class‐related and attribute‐related prior knowledge

IET Computer Vision, 2016
The existing attribute‐based zero‐shot learning models at different levels ignore some necessary prior knowledge. It is essential to improve classification accuracy of zero‐shot learning that how to mine attribute‐related and class‐related prior ...
Xuesong Wang, Chen Chen, Yuhu Cheng
doaj   +1 more source

Ferroelectric Quantum Dots for Retinomorphic In‐Sensor Computing

Advanced Materials, EarlyView.
This work has provided a protocol for fabricating retinomorphic phototransistors by integrating ferroelectric ligands with quantum dots. The resulting device combines ferroelectricity, optical responsiveness, and low‐power operation to enable adaptive signal amplification and high recognition accuracy under low‐light conditions, while supporting ...
Tingyu Long, Huanyu Zhou, Jaewan Ko, Hongwei Tan, Jaemin Lim, Yanfei Zhao, Daehan Kang, Eojin Yoon, Gyeong‐Tak Go, Somin Kim, Seung‐Woo Lee, Chan‐Yul Park, Hyojun Choi, Hyeran Kim, Hyung Joong Yun, Sung Hyuk Park, Kwan Sik Park, Jeong Woo Park, Mungeun Kim, Yong Soo Cho, Ho Won Jang, Wenqiang Yang, Min Hyuk Park, Wan Ki Bae, Sebastiaan van Dijken, Joona Bang, Tae‐Woo Lee   +26 more
wiley   +1 more source

Label space reduction for transductive zero-shot classification with large language models

Discover Computing
Zero-shot classification enables models to assign labels to unseen classes without task-specific training and has become increasingly effective with the advent of Large Language Models (LLMs).
Nathan Vandemoortele, Bram Steenwinckel, Femke Ongenae, Sofie Van Hoecke   +3 more
doaj   +1 more source

Embedded Zero-Shot Image Classification Based on Bidirectional Feature Mapping

Applied Sciences
The zero-shot image classification technique aims to explore the semantic information shared between seen and unseen classes through visual features and auxiliary information and, based on this semantic information, to complete the knowledge migration ...
Huadong Sun, Zhibin Zhen, Yinghui Liu, Xu Zhang, Xiaowei Han, Pengyi Zhang   +5 more
doaj   +1 more source

Azobenzene's Cross‐Scale Optics and Photonics: Molecular Photoswitching, Mesoscopic Material Motions, and Adaptive Devices

Advanced Materials, EarlyView.
Azobenzene photoswitches translate molecular‐scale E/Z photoisomerization into macroscopic material responses and device‐level photonic functions. This Review highlights how azobenzene research has evolved from molecular photochemistry to photoalignment, mass migration, photomechanics, and heat release, ultimately enabling holography, reconfigurable ...
Heeju Son, Soyul Kwak, Heerin Noh, Minsang Kim, Doyeon Noh, Subhayan Chakraborty, Jaewon Lee, YongDeok Cho, Kyeongsoo Kim, Taewoong Eom, Moonyoung Kim, Jangwon Kim, Hoyoung Lee, Soyoung Lee, Jaehun Kim, Grace G. D. Han, Shin‐Tson Wu, Stefano Oscurato, Arri Priimagi, Marina Saphiannikova, Seungwoo Lee   +20 more
wiley   +1 more source

1‐D Collocated Dual‐Gradient Sensory Fibers for Comprehensive Sensing and Decoding of Complex Human Motion and Physiology

Advanced Materials, EarlyView.
Coupled materials design enables a monolithic fiber that integrates complementary sensing regimes into a single wearable strand. By preserving informative signal features across subtle physiological deformation, large body motion, and mixed mechanical inputs, the dual‐gradient architecture generates synchronized, less redundant outputs that improve ...
Yunheum Lee, Sungha Jeon, Min Kim, Joonhee Won, Jinwook Yeo, Kyunghyun Jo, Soyeon Lee, Kieun Park, Yechan Yang, Chul Kim, Gun‐Hee Lee, Seunghwa Ryu, Sungho Jo, Seongjun Park   +13 more
wiley   +1 more source

Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders

Scientific Reports
Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data.
Jongseong Jang, Daeun Kyung, Seung Hwan Kim, Honglak Lee, Kyunghoon Bae, Edward Choi   +5 more
doaj   +1 more source

Bioinspired Adaptive Surfaces for Intelligent Liquid Manipulation: Progressing From Passive and Active to Hybrid Strategies

Advanced Materials, EarlyView.
This review examines passive, active, and hybrid liquid manipulation strategies, highlighting hybrid approaches as an emerging route to reconcile energy efficiency with adaptive control. By actively reconstructing passive surfaces to store programmable interfacial energy, hybrid systems enable flexible yet low‐power liquid transport, with perspectives ...
Jiaqi Miao, Yiyuan Zhang, Liqiu Wang, Alan C. H. Tsang   +3 more
wiley   +1 more source

Illusion of competence: vision–language models provide confident but inaccurate explanations in cytological diagnostics

Scientific Reports
Large vision-language models (LVLMs) have shown impressive image-understanding capabilities across domains. However, their suitability for cytomorphological diagnostics remains unclear.
Ivan Kukuljan, Muhammed Furkan Dasdelen, Julia Schäfer, Michele Buck, Katharina S. Götze, Carsten Marr   +5 more
doaj   +1 more source