HIGHLIGHTS
- who: ATTENTION et al. from the XXIV ISPRS Congress (, edition), June, Nice, France have published the research: EXPLAINING A DEEP SPATIOTEMPORAL LAND COVER CLASSIFIER WITH ATTENTION AND REDESCRIPTION MINING, in the Journal: (JOURNAL)
- what: The authors propose to characterize each pixel with such patterns by extracting them from each channel separately. Back to this paper, it is proposed to describe each pixel for which a ground truth is avail- able by indicating, for each channel, which are the most promising maximal GFS-patterns occurring in its symbolic series, if any. In this paper, objects are . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.