• Chandan Shukla
• Aditya Agarwal
• Harshit Kumar Rai
• Rishabh Joshi
• Prabhat Singh

There has been a significant increase in interest in bringing together computer vision and natural language processing since the announcement of deep learning. Picture captioning serves as a representation for this field; it uses one or more sentences to teach a computer how to understand the visual information in an image. In order to provide meaningful descriptions for high-level image semantics, one must also be able to analyze the state, attributes, and relationships between these objects. Though picture captioning remains a difficult and complex task, several researchers have made significant progress. Three deep neural network- based image captioning techniques—RNN, CNN- CNN, and reinforcement learning frameworks—are the main topics of discussion in this study. Next, we outline the key benefits and challenges, go over the assessment criteria in brief, and offer sample work for each of the top three techniques.

Image Captioning, Deep Learning, CNN, RNN, LSTM, Encoder-decoder architectures, Training Methodologies, Flickr8k Dataset, Performance Benchmarks

"Exploring Deep Learning Paradigms for Image Captioning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.j500-j506, March-2024, Available :http://www.jetir.org/papers/JETIR2403967.pdf

"Exploring Deep Learning Paradigms for Image Captioning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppj500-j506, March-2024, Available at : http://www.jetir.org/papers/JETIR2403967.pdf