Search Results for author: Vladimir Risojević

Found 5 papers, 4 papers with code

Learning Localization of Body and Finger Animation Skeleton Joints on Three-Dimensional Models of Human Bodies

1 code implementation11 Jul 2024 Stefan Novaković, Vladimir Risojević

Given only a list of point coordinates and normal vector estimates as input, a dynamic graph convolutional neural network is used to predict the coefficients of the convex combinations.

Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classification

no code implementations29 Mar 2023 Dajana Dimitrić, Mitar Simić, Vladimir Risojević

In this paper we deal with the problem of detecting remote sensing images coming from a different distribution compared to the training data - out of distribution images.

Classification Image Classification +3

Do we still need ImageNet pre-training in remote sensing scene classification?

1 code implementation5 Nov 2021 Vladimir Risojević, Vladan Stojnić

Recently, the availability of larger high resolution remote sensing (HRRS) image datasets and progress in self-supervised learning have brought up the questions of whether supervised ImageNet pre-training is still necessary for remote sensing scene classification and would supervised pre-training on HRRS image datasets or self-supervised pre-training on ImageNet achieve better results on target remote sensing scene classification tasks.

Classification Multi-Label Classification +2

Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding

1 code implementation14 Apr 2021 Vladan Stojnić, Vladimir Risojević

We show that, for the downstream task of remote sensing image classification, using self-supervised pre-training on remote sensing images can give better results than using supervised pre-training on images of natural scenes.

Image Classification Remote Sensing Image Classification +2

A Method for Detection of Small Moving Objects in UAV Videos

1 code implementation11 Feb 2021 Vladan Stojnić, Vladimir Risojević, Mario Muštra, Vedran Jovanović, Janja Filipi, Nikola Kezić, and Zdenka Babić

To circumvent this problem, we propose training a CNN using synthetic videos generated by adding small blob-like objects to video sequences with real-world backgrounds.

 Ranked #1 on Small Object Detection on Bee4Exp Honeybee Detection (using extra training data)

object-detection Segmentation Of Remote Sensing Imagery +2

Cannot find the paper you are looking for? You can Submit a new open access paper.