Napredna pretraga

Pregled bibliografske jedinice broj: 901612

An overview of action recognition in videos


Burić, Matija; Pobar, Miran; Ivašić-Kos, Marina
An overview of action recognition in videos // 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) / Biljanović, Petar (ur.).
Rijeka: IEEE, 2017. str. 1310-1315 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
An overview of action recognition in videos

Autori
Burić, Matija ; Pobar, Miran ; Ivašić-Kos, Marina

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) / Biljanović, Petar - Rijeka : IEEE, 2017, 1310-1315

ISBN
978-953-233-090-8

Skup
2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)

Mjesto i datum
Opatija, Hrvatska, 22-26.5.2017.

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Action recognition ; Feature extraction ; Videos ; Image recognition ; Semantics ; Trajectory

Sažetak
Action recognition in videos is currently in the focus of scientific research due to improvements made in automatic analysis of static images and greater availability of processing power. The paper provides an overview of the key models and methods for action recognition that comprise human models and methods based on estimation of joint trajectories, silhouettes and template matching and spatio-temporal local descriptors. To deal with compound actions and activities, action semantic models are proposed with help of expert knowledge. Since the action recognition task is domain dependent, the methods and models are built and tested on domain specific databases. The paper provides an overview and description of recent video datasets that were created for developing action recognition methods, with an emphasis on datasets with additional modalities such as depth images or accelerometer data.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekt / tema
HRZZ-IP-2016-06-8345 - Automatsko raspoznavanje akcija i aktivnosti u multimedijalnom sadržaju iz domene sporta (Marina Ivašić-Kos, )

Ustanove
Sveučilište u Rijeci - Odjel za informatiku