• Rucha Ravindra Shaiva
• Dr. Bhagwan D. Phulpagar
• Mrs. Yogita P. Narwadkar

The notion of automated information retrieval and text summarization is challenging in natural language processing due to the great complexity and irregular structure of the texts. A lengthy text is paraphrased during the text summarizing process to provide a summary. The automatic generation of a phrase to describe an image is known as image captioning, and it is a field that combines natural language processing with computer vision. The study of picture captioning has a significant influence on how visually impaired individuals comprehend their environment and may prove advantageous for sentence-level photo organizing. Convolution neural networks (CNN) and recurrent neural networks (RNN) were the primary building blocks of contemporary techniques. Making precise and evocative subtitles is still a difficult endeavor, though. Sentences that match the visual material are referred to as accurate captions; sentences that provide a variety of descriptions, as opposed to simple, everyday language, are referred to as descriptive captions. Generally speaking, the language model must consistently translate the graphical representation into a legible phrase, and the vision model must encode the context completely.

Information retrieval, text summarization, deep learning, word2vec, dense captioning, Stanford, NLP

"Multi Modal Text and Image Summarization using Deep Learning and Natural Language Processing Techniques – A Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.f104-f108, April-2024, Available :http://www.jetir.org/papers/JETIR2404511.pdf

"Multi Modal Text and Image Summarization using Deep Learning and Natural Language Processing Techniques – A Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppf104-f108, April-2024, Available at : http://www.jetir.org/papers/JETIR2404511.pdf