• Pranay Rana
• Pavitar Khatri
• Praveen Dahiya

An important area of research in recent years has been video captioning, the process of creating textual descriptions of video content. It can be used for a variety of useful purposes, such as helping the blind, enhancing video search capabilities, and enhancing comprehension of video content. The state-of the-art methods for video captioning using encoder-decoder architectures are thoroughly reviewed in this paper. We go over the various encoder-decoder model parts and the most recent developments in each one. On benchmark datasets, we compare the effectiveness of various encoder-decoder models and pinpoint the difficulties and promising directions for the future. This study aims to develop an encoder-decoder and deep learning algorithms-based model that automates the process of video captioning. First, pick out the most important frames from the video and leave the rest. Second, combining the LSTM and CNN deep learning algorithms. The CNN algorithm extracts the visual features from the video frames, while the Long Short-Term Memory (LSTM) algorithm generates the caption.

Deep learning, Video captioning, Encoder-Decoder, CNN, RNN, LSTM, KATNA.

"Video Captioning using Encoder-Decoder Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.i598-i600, May-2023, Available :http://www.jetir.org/papers/JETIR2305902.pdf

"Video Captioning using Encoder-Decoder Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppi598-i600, May-2023, Available at : http://www.jetir.org/papers/JETIR2305902.pdf