Bahdanau Attention Based Bengali Image Caption Generation

被引:1
|
作者
Alam, Md Sahrial [1 ]
Rahman, Md Sayedur [1 ]
Hosen, Md Ikbal [1 ]
Mubin, Khairul Anam [1 ]
Hossen, Sharif [1 ]
Mridha, M. F. [2 ]
机构
[1] Bangladesh Univ Business & Technol BUBT, Dept Comp Sci & Engn, Dhaka 1216, Bangladesh
[2] Amer Int Univ Bangladesh, Dept Comp Sci, Dhaka 1229, Bangladesh
关键词
Bahdanau Attention; Bengali Image Caption; Mendeley Data; Gated Recurrent Unit;
D O I
10.1109/DASA54658.2022.9765268
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the past few years, many works are done in object detection using images and machine translation. Inspired by those works we introduced Bahdanau Attention Based Bengali Image Caption Generation (BABBICG) that generate automatically bangla caption based on images. The Conventional encoder-decoder architectures performance curse will reduce by Bahdanau Attention and achieving momentous improvements over encoder-decoder architectures. In this work, we extract features from images using InceptionV3 neural network and generate caption using RNN decoder. We used Gated Recurrent Unit (GRU) approach as RNN. We evaluate the model using BanglaLekhaImageCaptions dataset from Mendeley Data that can help to generate bangla caption.
引用
收藏
页码:1073 / 1077
页数:5
相关论文
共 50 条
  • [1] Image caption generation method based on adaptive attention mechanism
    Jin, Huazhong
    Wu, Yu
    Wan, Fang
    Hu, Man
    Li, Qingqing
    [J]. MIPPR 2019: PATTERN RECOGNITION AND COMPUTER VISION, 2020, 11430
  • [2] Image caption generation with dual attention mechanism
    Liu, Maofu
    Li, Lingjun
    Hu, Huijun
    Guan, Weili
    Tian, Jing
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2020, 57 (02)
  • [3] Image Caption Generation Using Attention Model
    Ramalakshmi, Eliganti
    Jain, Moksh Sailesh
    Uddin, Mohammed Ameer
    [J]. INNOVATIVE DATA COMMUNICATION TECHNOLOGIES AND APPLICATION, ICIDCA 2021, 2022, 96 : 1009 - 1017
  • [4] Neural Image Caption Generation with Global Feature Based Attention Scheme
    Wang, Yongzhuang
    Xiong, Hongkai
    [J]. IMAGE AND GRAPHICS (ICIG 2017), PT II, 2017, 10667 : 51 - 61
  • [5] Image Caption Description Generation Method Based on Reflective Attention Mechanism
    Qiao Pingan
    Yuan, Li
    Shen Ruixue
    [J]. ADVANCES IN NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, ICNC-FSKD 2022, 2023, 153 : 600 - 609
  • [6] A Deep Attention based Framework for Image Caption Generation in Hindi Language
    Dhir, Rijul
    Mishra, Santosh Kumar
    Saha, Sriparna
    Bhattacharyya, Pushpak
    [J]. COMPUTACION Y SISTEMAS, 2019, 23 (03): : 693 - 701
  • [7] Fine-grained attention for image caption generation
    Chang, Yan-Shuo
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (03) : 2959 - 2971
  • [8] Fine-grained attention for image caption generation
    Yan-Shuo Chang
    [J]. Multimedia Tools and Applications, 2018, 77 : 2959 - 2971
  • [9] Image caption generation using a dual attention mechanism
    Padate, Roshni
    Jain, Amit
    Kalla, Mukesh
    Sharma, Arvind
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [10] Attention based sequence-to-sequence framework for auto image caption generation
    Khan, Rashid
    Islam, M. Shujah
    Kanwal, Khadija
    Iqbal, Mansoor
    Hossain, Md Imran
    Ye, Zhongfu
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 43 (01) : 159 - 170