Affiliation:
1. Sona College of Technology, India
2. Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, India
Abstract
Video captions help people to understand in a noisy environment or when the sound is muted. It helps people having impaired hearing to understand much better. Captions not only support the content creators and translators but also boost the search engine optimization. Many advanced areas like computer vision and human-computer interaction play a vital role as there is a successful growth of deep learning techniques. Numerous surveys on deep learning models are evolved with different methods, architecture, and metrics. Working with video subtitles is still challenging in terms of activity recognition in video. This paper proposes a deep structured model that is effective towards activity recognition, automatically classifies and caption it in a single architecture. The first process includes subtracting the foreground from the background; this is done by building a 3D convolutional neural network (CNN) model. A Gaussian mixture model is used to remove the backdrop. The classification is done using long short-term memory networks (LSTM). A hidden Markov model (HMM) is used to generate the high quality data. Next, it uses the nonlinear activation function to perform the normalization process. Finally, the video captioning is achieved by using natural language.
Subject
Computer Science Applications
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献