This story was originally published on HackerNoon at: https://hackernoon.com/video-scene-location-recognition-using-ai-methodology).
This study explores scene recognition in TV series using neural networks, tested on The Big Bang Theory, with various layers like LSTM and pooling methods.
Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning).
You can also check exclusive content about #neural-networks), #scene-recognition), #tv-series-analysis), #convolutional-networks), #lstm-layers), #video-classification), #machine-learning), #big-bang-theory-dataset), and more.
This story was written by: [@rendering](https://hackernoon.com/u/rendering)). Learn more about this writer by checking [@rendering's](https://hackernoon.com/about/rendering)) about page,
and for more stories, please visit [hackernoon.com](https://hackernoon.com)).
The input consists of video files and a text file. The video files are divided into independent episodes. The textfile is contains manually created metainformation about every scene. The scene is understand as sequence of frames, that are not interrupted by another frame with different scene location label.
