FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos

Author(s):  
Suyog Dutt Jain ◽  
Bo Xiong ◽  
Kristen Grauman
2021 ◽  
Vol 159 (6) ◽  
pp. 824-835.e1
Author(s):  
Rosalia Leonardi ◽  
Antonino Lo Giudice ◽  
Marco Farronato ◽  
Vincenzo Ronsivalle ◽  
Silvia Allegrini ◽  
...  

2016 ◽  
Vol 5 (2) ◽  
pp. 305-314 ◽  
Author(s):  
Tuomas Savolainen ◽  
Daniel Keith Whiter ◽  
Noora Partamies

Abstract. In this paper we describe a new and fully automatic method for segmenting and classifying digits in seven-segment displays. The method is applied to a dataset consisting of about 7 million auroral all-sky images taken during the time period of 1973–1997 at camera stations centred around Sodankylä observatory in northern Finland. In each image there is a clock display for the date and time together with the reflection of the whole night sky through a spherical mirror. The digitised film images of the night sky contain valuable scientific information but are impractical to use without an automatic method for extracting the date–time from the display. We describe the implementation and the results of such a method in detail in this paper.


Author(s):  
Michael Kohnen ◽  
Andreas H. Mahnken ◽  
Alexander S. Brandt ◽  
Rolf W. Günther ◽  
Berthold B. Wein

2016 ◽  
Author(s):  
Giovanni Jacopo J. Ughi ◽  
Michalina J. Gora ◽  
Anne-Fre Swager ◽  
Mireille Rosenberg ◽  
Jenny Sauk ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document