Hi there! I'm Sena, a 4th year PhD Candidate in EPFL CVLAB. My research interests are mainly in computer vision and machine learning, more specifically, motion prediction and active human pose estimation. I am currently on an internship with the Autonomous Systems group at Microsoft, where I work on visual odometry.

My undergraduate is from Bilkent University, Electrical and Electronics Engineering. I graduated in 2017.

Publications:

Long Term Motion Prediction Using Keyposes

[Pdf][Code]

Sena Kiciroglu, Wei Wang, Mathieu Salzmann, Pascal Fua

Under Review

We predict diverse and realistic long term (5 second) human motion by making use of "keyposes", the set of poses which we can use to accurately reconstruct the complete sequence.

Motion Prediction Using Temporal Inception Module

[Pdf][Code]

Tim Lebailly, Sena Kiciroglu, Mathieu Salzmann, Pascal Fua, Wei Wang

ACCV 2020

We predict human motion accurately in the short and long term future by making use of a Temporal Inception Module (TIM). Using TIM, we produce input embeddings using convolutional layers, by using different kernel sizes for different input lengths.

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

[Pdf][Code]

Sena Kiciroglu, Helge Rhodin, Sudipta N. Sinha, Mathieu Salzmann, Pascal Fua

CVPR 2020 - Oral

Given a short video sequence, we introduce an algorithm that predicts which viewpoints should be chosen by a moving camera to capture future frames so as to maximize 3D human pose estimation accuracy.