HIGHLIGHTS
- who: Zhiquan He from the University of Missouri, United States have published the research work: Accurate few-shot object counting with Hough matching feature enhancement, in the Journal: (JOURNAL)
- what: Methods: To overcome the problem, the authors propose a novel Hough matching feature enhancement network. And the authors design an exemplar feature aggregation module to enhance the commonality of the exemplar feature. The authors propose an object-to-object Hough matching module that votes in the Hough space, which optimizes the similarity map in the form of convolutions. Inspired by the successful application of point . . .
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.