4 papers
Benchmarking SAM2-based Trackers on FMOX
Senem Aktas, Charles Markham, John McDonald +1
Several object tracking pipelines extending Segment Anything Model 2 (SAM2) have been proposed in the past year, where the approach is to follow and segment the object from a singl…
Benchmarking EfficientTAM on FMO datasets
Senem Aktas, Charles Markham, John McDonald +1
Fast and tiny object tracking remains a challenge in computer vision and in this paper we first introduce a JSON metadata file associated with four open source datasets of Fast Mov…
Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces
Jeremy Chopin, Rozenn Dahyot
Data embeddings with CLIP and ImageBind provide powerful features for the analysis of multimedia and/or multimodal data. We assess their performance here for classification using a…
Automatic detection of passable roads after floods in remote sensed and social media data
Kashif Ahmad, Konstantin Pogorelov, Michael Riegler +4
This paper addresses the problem of floods classification and floods aftermath detection utilizing both social media and satellite imagery. Automatic detection of disasters such as…