MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS

May 2023
Vol-9, Issue-3
Paper ID: 20462
ISSN: 2395-4396
Downloads: 61
Download PDF

Abstract & Details

Research Area
Computer Engineering
Keywords
MS-COCO LSTM MLAIC
Abstract
we present a Multi-task Learning Approach for Image Captioning (MLAIC), which is motivated by the observation that humans can easily complete this task since they are skilled in a variety of disciplines. MLAIC is made up of three essential parts in particular:(i)A multi-object classification model that learns detailed category-aware picture representations by employing a CNN image encoder (ii) An image captioning model that generates text descriptions of images by sharing its CNN encoder and LSTM decoder with the object classification task and the syntax that learns better syntax aware LSTM based decoder.The added object classification and grammar knowledge is especially generation task, respectively. (ii) A syntax generation model that improves syntax aware LSTM based decoder. (iii) A syntax generation model advantageous for the picture captioning model. The experimental outcomes on the MS-COCO dataset show that our model outperforms other formidable rivals in terms of performance.

Author Information

# Name Institute / Affiliation
1 Tasmiya Khanum HKBK college of engineering
2 Saniya Sultana HKBK college of engineering
3 Shabreen Taj HKBK college of engineering
4 Shikhar HKBK college of engineering
5 Sreekantha B HKBK college of engineering

How to Cite

Use the following formats to cite this article in your research.

APA Style
Khanum, Tasmiya, Sultana, Saniya, Taj, Shabreen, Shikhar, & B, Sreekantha (2023). MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS. International Journal of Advance Research and Innovative Ideas In Education, 9(3), 2369-2373.
MLA Style
Khanum, Tasmiya, et al. "MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS." International Journal of Advance Research and Innovative Ideas In Education, vol. 9, no. 3, 2023, pp. 2369-2373.
IEEE Style
Tasmiya Khanum, Saniya Sultana, Shabreen Taj, Shikhar, and Sreekantha B, "MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS," International Journal of Advance Research and Innovative Ideas In Education, vol. 9, no. 3, pp. 2369-2373, 2023.
Vancouver Style
Khanum Tasmiya, Sultana Saniya, Taj Shabreen, Shikhar, B Sreekantha. MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS. International Journal of Advance Research and Innovative Ideas In Education. 2023;9(3):2369-2373.
Harvard Style
Khanum, Tasmiya, Sultana, Saniya, Taj, Shabreen, Shikhar, & B, Sreekantha (2023) 'MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS', International Journal of Advance Research and Innovative Ideas In Education, 9(3), pp. 2369-2373.
Chicago Style
Khanum, Tasmiya, et al. "MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS." International Journal of Advance Research and Innovative Ideas In Education 9, no. 3 (2023): 2369-2373.
Turabian Style
Khanum, Tasmiya, et al. "MULTI TASK LEARNING FOR CAPTIONING IMAGES WITH NOVEL WORDS." International Journal of Advance Research and Innovative Ideas In Education 9, no. 3 (2023): 2369-2373.

Export Citation

Related Research

PReFace : AI -Assisted Plausible Facial Restoration and Damage Reconstruction System
Syeda Arbeena Kausar et al. 2026 Computer Science and Engineering (Computer Vision, Deep Learning and Image Processing)
Download PDF
Customer Churn Prediction Using Machine Learning
Dr. Roshni Khlhe et al. 2026 Machine Learning, Artificial Intelligence, Data Analytics, and Customer Churn Prediction.
Download PDF
Automated web vulnerability scanner
Jitendra Sahu et al. 2026 Computer science
Download PDF
BLOOD BANK DEMAND PREDICTION SYSTEM: MACHINE LEARNINGBASED BLOOD DEMAND FORECASTING
Uday Dharmapal Wankhede et al. 2026 Computer Science & Engineering
Download PDF