Results 231 to 240 of about 12,717 (259)

Attribute relation learning for zero-shot classification

Neurocomputing, 2014
In computer vision and pattern recognition communities, one often-encountered problem is that the limited labeled training data are not enough to cover all the classes, which is also called the zero-shot learning problem. For addressing that challenging problem, some visual and semantic attributes are usually used as mid-level representation to ...
Mingxia Liu 0001, Daoqiang Zhang, Songcan Chen   +2 more
openaire   +1 more source

Adaptive Relation-Aware Network for zero-shot classification

Neural Networks, 2023
Supervised learning-based image classification in computer vision relies on visual samples containing a large amount of labeled information. Considering that it is labor-intensive to collect and label images and construct datasets manually, Zero-Shot Learning (ZSL) achieves knowledge transfer from seen categories to unseen categories by mining ...
Xun Zhang, Yang Liu 0069, Yuhao Dang, Xinbo Gao 0001, Jungong Han, Ling Shao 0001   +5 more
openaire   +3 more sources

Attribute Driven Zero-Shot Classification and Segmentation

2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2018
Zero-shot classification and segmentation aims to recognize and segment objects of unseen classes. The attribute information, such as color, shape, part and material, is usually used for zero-shot classification. Moreover, we observe that this kind of attribute information could also be helpful in the segmentation task.
Shu Yang 0007, Yemin Shi 0001, Yaowei Wang 0001, Jing Wang 0037, Zesong Fei   +4 more
openaire   +2 more sources

Cross-Modal Representation Reconstruction for Zero-Shot Classification

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Zero-shot learning (ZSL) aims to recognize novel classes without training samples through transferring knowledge from seen classes, based on the assumption that both the seen and unseen classes share a latent semantic space. Previous works either focus on directly learning various mapping functions between visual space and semantic space, or searching ...
Yu Wang 0174, Shenjie Zhao
openaire   +2 more sources

Multimodal Ensembling for Zero-Shot Image Classification

Proceedings of the AAAI Conference on Artificial Intelligence
Artificial intelligence has made significant progress in image classification, an essential task for machine perception to achieve human-level image understanding. Despite recent advances in vision-language fields, multimodal image classification is still challenging, particularly for the following two reasons.
openaire   +2 more sources

Vision-Language Models for Zero-Shot Classification of Remote Sensing Images

Applied Sciences (Switzerland), 2023
Yakoub Bazi, Hebah Elgibreen, Mohamad Al Rahhal   +2 more
exaly  

Zero-shot Classification at Different Levels of Granularity

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
openaire   +1 more source

Zero-Shot Image Classification Based on a Learnable Deep Metric

Sensors, 2021
Yazhi Liu, Caijuan Shi
exaly  

Robust deep alignment network with remote sensing knowledge graph for zero-shot and generalized zero-shot remote sensing image scene classification

ISPRS Journal of Photogrammetry and Remote Sensing, 2021
Yansheng Li, Yongjun Zhang, Yihua Tan
exaly  

Zero-Shot Learning for Audio Classification

2020
Zero-shot learning has received increasing attention in recent years. In this thesis, we study zero-shot learning for general audio classification through the usage of class labels and sentence descriptions being the semantic side information of acoustic classes. The goal is to obtain audio classifiers that are capable of recognizing audio instances of
openaire   +1 more source