Zero-Shot Image Classification with Rectified Embedding Vectors Using a Caption Generator
Although image recognition technologies are developing rapidly with deep learning, conventional recognition models trained by supervised learning with class labels do not work well when test inputs from untrained classes are given. For example, a recognizer trained to classify Asian bird species can...
Main Authors: | Chan Hur, Hyeyoung Park |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/12/7071 |
Similar Items
-
Enhancing Semantic-Consistent Features and Transforming Discriminative Features for Generalized Zero-Shot Classifications
by: Guan Yang, et al.
Published: (2022-12-01) -
Zero-Shot Learning with Joint Generative Adversarial Networks
by: Minwan Zhang, et al.
Published: (2023-05-01) -
Video Caption Based Searching Using End-to-End Dense Captioning and Sentence Embeddings
by: Akshay Aggarwal, et al.
Published: (2020-06-01) -
Parallel Dense Video Caption Generation with Multi-Modal Features
by: Xuefei Huang, et al.
Published: (2023-08-01) -
Fusion of Multi-Modal Features to Enhance Dense Video Caption
by: Xuefei Huang, et al.
Published: (2023-06-01)