Activity Recognition Using Video Captioning and Summarization
Deepanshi Bansal1, Kshitij Gupta2, Aayush Gupta3, Pooja Gupta4

1Deepanshi Bansal, CSE Dept., Maharaja Agrasen Institute of Technology (MAIT), GGSIPU, New Delhi, India.
2Kshitij Gupta, CSE Dept., Maharaja Agrasen Institute of Technology (MAIT), GGSIPU, New Delhi, India.
3Aayush Gupta, CSE Dept., Maharaja Agrasen Institute of Technology (MAIT), GGSIPU, New Delhi, India.
4Pooja Gupta, Assistant Prof. CSE Dept., Maharaja Agrasen Institute of Technology (MAIT), GGSIPU, New Delhi, India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 661-666 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6775068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: As the technology is improving every day, people are getting more inclined towards it.The busy schedule of people could not let them spare enough time to watch long videos whether it is related to some cricket match or some teaching or some glimpse of some video. Hence, there is a need to build a system to generate a summary of any video for having approximate glimpse without seeing the video. Also, everyday thousands of videos are uploaded on youtube and thus filtering is really necessary when we are searching for a particular video. There also, Video summarisation comes into action where one could skip multiple videos which may not be what the user want by just looking at the summary without watching it and investing time on it. The report discusses about how captioning and summarisation could be done using convolutional and recurrent neural networks and natural language processing.
Keyword: Captioning, Neural networks, Summary, Video summarization.
Scope of the Article: Image Processing and Pattern Recognition.