23
Deep learning features and similarity of movies based on their video content Summer Camp - Show Max - Lukáš Lopatovský

Deep learning features and similarity of movies based on their video content

  • Upload
    showmax

  • View
    260

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Deep learning features and similarity of movies based on their video content

Deep learning features and similarity of movies based on their

video content

Summer Camp - Show Max - Lukáš Lopatovský

Page 2: Deep learning features and similarity of movies based on their video content

Assignment

● Deep learning allows extracting useful features from video frames. Your task is to apply new deep learning frameworks to extract features from video frames of selected movies available in the ShowMax streaming platform.

● Goals:● Extract deep features from video frames. Explore similar

movies in the space of latent features and adjust the extraction process in order to create clusters of video assets (eg. TV episodes).

Page 3: Deep learning features and similarity of movies based on their video content

Residual Networks

● Enable to build deeper (convolutional) neural network. (State of the art method for the image recognition.)

Page 4: Deep learning features and similarity of movies based on their video content

Residual Networks

● To enable to build deeper network, the residual nets use the simple trick. They maintain the residuum from the previous layer ( so do not loose the previously known information )

Page 5: Deep learning features and similarity of movies based on their video content

Torch

- Efficient Tensor library (like NumPy) with an efficient CUDA backend

- Neural Networks package -- build arbitrary acyclic computation graphs with automatic differentiation

- fast CUDA and CPU backends

- Good community and industry support - several hundred community-built and maintained packages.

Page 6: Deep learning features and similarity of movies based on their video content

● Torch example of ‘nn’ library

Page 7: Deep learning features and similarity of movies based on their video content

What has been done

● The movies were classified using arbitrary number of picture frames.

● We have used already trained ImageNet FB- resnet network and own data set trained and fine-tuned networks to classify movies.

● To detect the object in the image, we have classify the whole image, as well as we have made the various crops to get more accurate predictions. (Cropping showed better results)

Page 8: Deep learning features and similarity of movies based on their video content

Classification output

● By classification of frames in the movie, the special file is produced (.res). It is in a form to contain all the important data. It can be later post-process according to the special needs of the user:

- To create Object detection .srt file.

- To get various cumulative classification results.

- To trace the appearance of the object at the time-line.

Page 9: Deep learning features and similarity of movies based on their video content

Object classification exmple

Page 10: Deep learning features and similarity of movies based on their video content

Object classification exmple

Page 11: Deep learning features and similarity of movies based on their video content

Object classification exmple

Page 12: Deep learning features and similarity of movies based on their video content

False positive

Page 13: Deep learning features and similarity of movies based on their video content

False positive

Page 14: Deep learning features and similarity of movies based on their video content

False positive

Page 15: Deep learning features and similarity of movies based on their video content

Own datasets

● The network was successfully trained and fine-tuned from the ResNet network

● However, it showed some problems based from improper dataset. - Some categories contain many irrelevant pictures in second half of the search. (Special case: “The doctor House”)

- The style of the images in the search is often very different to the style found in the movie. (kitchen, car)

- Movies mostly contain images full of people, so the categories containing people make false positive prediction. (cinema, theater)

Page 16: Deep learning features and similarity of movies based on their video content

Classification example

⊙ω⊙

Page 17: Deep learning features and similarity of movies based on their video content

Classification example

⊙ω⊙

Page 18: Deep learning features and similarity of movies based on their video content

Object detection

Page 19: Deep learning features and similarity of movies based on their video content

Object detection

Page 20: Deep learning features and similarity of movies based on their video content

Object detection

Page 21: Deep learning features and similarity of movies based on their video content

Object detection

Page 22: Deep learning features and similarity of movies based on their video content

Object detection

Page 23: Deep learning features and similarity of movies based on their video content

Next step

● After the discussion in the company, the programs were transformed to the easily usable form.

● The feature vectors of the classification will be used to find similarities among movies. Compared to the existing algorithms and if successful, incorporated into the current recommendation system.