Now showing items 1-3 of 3
Deep Learnıng Archıtectures for Collectıve Actıvıty Recognıtıon
(Fen Bilimleri Enstitüsü, 2019-09-30)
Collective activity recognition, which analyses the behavior of groups of people in videos, is an essential goal of video surveillance systems. In this thesis, we proposed three new solutions and one novel dataset for the ...
Recognızıng Human Interactıons In Stıll Images
(Fen Bilimleri Enstitüsü, 2020)
Recognizing human interactions in still images is quite a challenging problem since compared to videos, there is only a glimpse of interaction in a single image. In this thesis, we explore the role of two components that ...
An End-To-End Convolutional Neural Network Framework For Low-Resolution Attribute Recognition
(Fen Bilimleri Enstitüsü, 2022)
In video surveillance, visual person attributes such as gender, backpack, and type of clothing are crucial for searching and re-identification. For detecting and retrieving these attributes with high accuracy, the availability ...