1- Computing Turkish Movie Stars Screen Time Using Deep Convolutional Networks

Computer Engineering Undergraduate final project. Gained experience in Computer Vision and Image Processing. Presented the research at a conference through oral presentation by Senem Aktaş. Studied VGG16, InceptionV3, Xception, MobileNet, and DenseNet deep learning models.

  • Figure 1. Examples of frames from movies

    before MovieScreenTime

2- Beat Estimation From Musician Visual Cues

This paper aims to discover a robust technique that can identify musical phases (beats) through visual cues derived from a musician’s body movements captured through camera sensors.A multi-instrumental dataset was used to carry out a comparative study of two different approaches: (a) motiongram, and (b) pose estimation, to detect phase from body sway.

BeatEstimation

3- Comparison of Neural Network Models for Nostalgic Sentiment Analysis of YouTube Comments

  • Paper Link - Natural Language Processing - Journal
  • Postalcioglu, S , Aktas, S . (2020). Comparison of Neural Network Models for Nostalgic Sentiment Analysis of YouTube Comments . Hittite Journal of Science and Engineering , 7 (3) , 215-221 . DOI: 10.17350/HJSE19030000191

Before - After Preprocessing Dataset

before

System Architecture

before

4- Soon

  • [Paper Link]