Results 251 to 260 of about 59,151 (296)

Towards cross-domain few-shot modulation classification: a feature transformation graph neural network approach. [PDF]

Sci Rep
Shi Y, Xu H, Qi Z, Wang D, Meng Q.
europepmc   +1 more source

Large Language Models and Machine Learning Framework for Predicting Dental Ceramics Performance. [PDF]

Int Dent J
Zhou H, Bai Y, Chen Y, Fan D, Wang P, Ji P, Chen T.   +6 more
europepmc   +1 more source

Chinese spatial relation extraction model by integrating geographic semantic features. [PDF]

Sci Rep
Ye P, Wang Y, Jiang Y, Xiao W.
europepmc   +1 more source

BECA: A Computer Vision Dataset for Long-Term Recognition In Beef Cattle. [PDF]

Sci Data
Zhang Y, Li L, Li C, Wang S, Rong Y, Niu K, He Z.   +6 more
europepmc   +1 more source

Local-Global Aware Concept Bottleneck Models for Interpretable Image Classification. [PDF]

Sensors (Basel)
Liu C, Lin Z, Tang C.
europepmc   +1 more source

Machine Learning for Intelligent and Adaptive Communication Systems: From Optimization to Emerging Paradigms. [PDF]

Sensors (Basel)
Lee H, Sun Y, Simpson O.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Few-Shot Pill Recognition

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Pill image recognition is vital for many personal/public health-care applications and should be robust to diverse unconstrained real-world conditions. Most existing pill recognition models are limited in tackling this challenging few-shot learning problem due to the insufficient instances per category.
Suiyi Ling, Andreas Pastor, Jing Li 0026, Zhaohui Che, Junle Wang, Jieun Kim, Patrick Le Callet   +6 more
openaire   +1 more source

Self-Prompt Mechanism for Few-Shot Image Recognition

Proceedings of the AAAI Conference on Artificial Intelligence
Few-shot learning poses a formidable challenge as it necessitates effective recognition of novel classes based on a limited set of examples. Recent studies have sought to address the challenge of rare samples by tuning visual features through the utilization of external text prompts.
Mingchen Song, Huiqiang Wang, Guoqiang Zhong 0001   +2 more
openaire   +2 more sources