Open Access

Using Text and Visual Cues for Fine-Grained Classification

Zaryab Shaker

Zaryab Shaker

School of Computer Science and Engineering Xian Technological UniversityXian, China
Search for this author on
Sciendo|Google Scholar
Shaker, Zaryab
, 
Xiao Feng

Xiao Feng

School of Computer Science and Engineering Xian Technological UniversityXian, China
Search for this author on
Sciendo|Google Scholar
Feng, Xiao
 and 
Muhammad Adeel Ahmed Tahir

Muhammad Adeel Ahmed Tahir

School of Computer Science and Engineering Xian Technological UniversityXian, China
Search for this author on
Sciendo|Google Scholar
Tahir, Muhammad Adeel Ahmed
  
Feb 22, 2021
Using Text and Visual Cues for Fine-Grained Classification's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Feb 22, 2021
Page range: 42 - 49
DOI: https://doi.org/10.21307/ijanmc-2021-026
Keywords
© 2021 Zaryab Shaker et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

T-SNE Plot for word Embedding
T-SNE Plot for word Embedding

Figure 2.

Proposed Model Pipeline_ Text and Visual features are attended and Combined for Fine Grained Classification.
Proposed Model Pipeline_ Text and Visual features are attended and Combined for Fine Grained Classification.
undefined
undefined
undefined

Figure 3.

Visualization of Epoch vs Loss with different window size and dimension
Visualization of Epoch vs Loss with different window size and dimension

Figure 4.

Parameters visualization with different window size and dimension
Parameters visualization with different window size and dimension
Language:
English
Publication timeframe:
4 times per year
Journal Subjects:
Computer Sciences, Computer Sciences, other
Journal RSS Feed