Profesor dr. Alptekin Temizelm, ki poučuje na Middle East Technical University (METU) bo v torek, 9. 1. 2018, od 13.00 do 14.00 v predavalnici P04 predaval na temo računalniške razpoznave dejavnosti oseb na podlagi videa in zvoka.

First-Person Activity Recognition using Video and Audio Features

Povzetek

In typical third-person perspective videos, the camera is usually stationary and situated away from the actors involved in the events. On the other hand, egocentric (first-person) videos are captured using a camera on a person and reflect the first person perspective. In these videos, the observer is involved in the events and the camera undergoes large amounts of ego-motion. These different characteristics of first-person videos make it difficult to use the existing approaches for activity recognition directly and necessitate different approaches to the problem. In addition to the different global and local features from video, further features bringing complementary information can be obtained from audio. On the other hand, fusion of different features from video and other data sources brings new challenges.

In the first part of this talk, I will give some examples of our recent research outputs. Then, I will discuss the particular challenges regarding activity recognition from egocentric data and data-driven selection and weighting of different features.

O predavatelju

Alptekin Temizel Assoc. Prof., Graduate School of Informatics, Middle East Technical University (METU); He received his B.Sc. in Electrical and Electronics Engineering, METU, Turkey in 1999 and his Ph.D. 2006-Centre of Vision, Speech and Signal Processing, University of Surrey, UK. He co-founded Visioprime Ltd, UK, a company specialized in Intelligent Video Systems for Security, where he worked as senior research engineer in 2001-2006 and acquired a number of patents. He started as an Assistant Professor at METU in 2007 where he is currently an Associate Professor. He is the principal investigator of “Virtual Reality and Computer Vision Research Group”, “GPU Education and Research Centre” and a Deep Learning Institute Certified Instructor and University Ambassador. He collaborated with and advised several companies on video analytics, video surveillance systems/algorithms and GPU computing. He was a visiting researcher at Microsoft MLDC-Lisbon in the summers of 2014 and 2015 and ISCTE University Institute of Lisbon in 2017. He was on sabbatical leave at University of Birmingham, UK in 2016-2017. He has been expert evaluator of EU H2020 and EUREKA research programs and nationally funded programs. His main research interests are video surveillance, computer vision, machine learning, deep learning, GPU programming and CUDA.