.png){kind=icon}
Return
Zero-Shot Object Recognition System Based on Topic Model
.png){kind=icon}
OA
AI
DOI：10.1109/THMS.2014.2358649.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Object recognition systems usually require fully complete manually labeled training data to train classifier. In this paper, we study the problem of object recognition, where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot learning strategy that utilizes the topic model and hierarchical class concept. Our proposed method advanced where cumbersome human annotation stage (i.e., attribute-based classification) is eliminated. We achieve comparable performance with state-of-the-art algorithms in four public datasets: PubFig (67.09%), Cifar-100 (54.85%), Caltech-256 (52.14%), and Animals with Attributes (49.65%), when unseen classes exist in the classification task.
Keywords:
Image understanding
object recognition
topic model
zero-shot learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.4
Papers:
1.1K
Citations:
3.5K
Organization
Cited Papers
A review of the Irish crustal structure and signatures from the Caledonian and Variscan Orogenies.png)
Terra Nova
Terra NovaIF0
PREAI
ShareSaveShareSaveShareSave
ShareSaveCharacterization of Hemangioblastic Traits within Endothelial Progenitor Cells of Multiple Myeloma PatientsBlood
BloodIF0
PREAI
ShareSave
View more