Scene understanding based on visual and text data
In this project, the concept of scene understanding with visual and text data will be applied to the task of video captioning, and its effectiveness would be evaluated. A new dataset of videos and its accompanying captions, which aims to be an improvement over current datasets, will be collected for...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In this project, the concept of scene understanding with visual and text data will be applied to the task of video captioning, and its effectiveness would be evaluated. A new dataset of videos and its accompanying captions, which aims to be an improvement over current datasets, will be collected for training and analysis. After which, it will be put through a baseline for training and analysis. The output metrics and captions will be observed and recorded to gauge if the numbers correlate with human judgement, and whether would they be accurate or not. The possible reasons for the accuracy will also be analysed and perhaps proposed for future work as well. |
|---|