A Review of Methods for Video Captioning

Deep Learning (DL) has gained huge popularity due to its efficiency and its great performance on solving some specific problem regarding to Artificial Intelligence. Also substantial progress has been made in the field of Computer Vision (CV) and Natural Language Processing (NLP). The computer vision market is expected to grow from USD 10.9 billion in 2019 to USD 17.4 billion by 2024-growing at a CAGR of 7.8% during the forecast period. Because of this, the task of video captioning has emerged and it is believed that the mixture of DL, CV, NLP can provide great results. Video captioning refers to the process of automatic generation of natural language sentences that describes the contents of a given video. This paper talks about techniques like CNN, RNN, LSTM, 3D CNN, etc which are used to solve various problems.