Segmenting out Generic Objects in Monocular Videos

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F21%3AA2302APR" target="_blank" >RIV/61988987:17610/21:A2302APR - isvavai.cz</a>
Result on the web
<a href="http://ceur-ws.org/Vol-2962/paper49.pdf" target="_blank" >http://ceur-ws.org/Vol-2962/paper49.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Segmenting out Generic Objects in Monocular Videos
Original language description
We present an approach for generic object detection and segmentation in monocular videos. In this task, we want to segment objects from a background with no prior knowledge about the possible classes of objects which we may encounter. This makes this task much harder than the classical object detection and segmentation, which can be posed as a supervised learning problem. Our approach uses an ensemble of 3 different models which are trained by different objectives and have different failure modes and therefore complement each other. We demonstrate the usefulness of our approach on a custom dataset containing 18 classes of organic objects. Using our method, we were able to recover the classes of objects in a fully unsupervised way.
Czech name
—
Czech description
—

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 21st Conference Information Technologies ? Applications and Theory (ITAT 2021)
ISBN
—
ISSN
1613-0073
e-ISSN
—
Number of pages
7
Pages from-to
123-129
Publisher name
CEUR Workshop Proceedings
Place of publication
—
Event location
Nízke Tatry and Muránska planina, Slovakia
Event date
Jan 1, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)