Stage-oe-small.jpg

Neuigkeit110: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 2: Zeile 2:
 
|Titel DE=Best Paper Award - IEEE Intelligent Vehicles Symposium (IV)
 
|Titel DE=Best Paper Award - IEEE Intelligent Vehicles Symposium (IV)
 
|Titel EN=Best Paper Award - IEEE Intelligent Vehicles Symposium (IV)
 
|Titel EN=Best Paper Award - IEEE Intelligent Vehicles Symposium (IV)
|Beschreibung DE='''Michael Weber was awarded with the Best Paper Award for his paper named ''MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving'' at IV 2018.'''<br><br>'''Abstract'''<br>Abstract: While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second.
+
|Beschreibung DE='''Michael Weber wurde für seine Arbeit ''MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving'' auf der IV 2018 mit dem Best Paper Award ausgezeichnet.'''<br><br>'''Abstract'''<br>Abstract: While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second.
 
|Beschreibung EN='''Michael Weber was awarded with the Best Paper Award for his paper named ''MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving'' at IV 2018.'''<br><br>'''Abstract'''<br>Abstract: While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second.
 
|Beschreibung EN='''Michael Weber was awarded with the Best Paper Award for his paper named ''MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving'' at IV 2018.'''<br><br>'''Abstract'''<br>Abstract: While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second.
 
|Datum=2018/06/28
 
|Datum=2018/06/28
 
|Forschungsgruppe=Angewandte Technisch-Kognitive Systeme
 
|Forschungsgruppe=Angewandte Technisch-Kognitive Systeme
 
}}
 
}}

Aktuelle Version vom 18. Dezember 2018, 09:49 Uhr

Neuigkeit vom 28. Juni 2018


Best Paper Award - IEEE Intelligent Vehicles Symposium (IV)


Michael Weber wurde für seine Arbeit MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving auf der IV 2018 mit dem Best Paper Award ausgezeichnet.

Abstract
Abstract: While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second.



Aus der Forschungsgruppe Angewandte Technisch-Kognitive Systeme