H
Hala Lamdouar
Researcher at University of Oxford
Publications - 5
Citations - 65
Hala Lamdouar is an academic researcher from University of Oxford. The author has contributed to research in topics: Segmentation & Optical flow. The author has an hindex of 2, co-authored 4 publications receiving 14 citations.
Papers
More filters
Book ChapterDOI
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
TL;DR: A novel architecture that consists of two essential components for breaking camouflage, namely, a differentiable registration module to align consecutive frames based on the background, and a motion segmentation module with memory that discovers the moving objects, while maintaining the object permanence even when motion is absent at some point.
Proceedings Article
Self-Supervised Video Object Segmentation by Motion Grouping
TL;DR: In this article, a simple variant of the Transformer is introduced to segment optical flow frames into primary objects and the background, which achieves superior or comparable results to previous state-of-the-art self-supervised methods, while being an order of magnitude faster.
Deep-SWIM: A few-shot learning approach to classify Solar WInd Magnetic field structures
Hala Lamdouar,Sairam Sundaresan,Anna Jungbluth,S. Boro Saikia,Amanda Joy Camarata,N. D. Miles,Marcella Scoczynski,Mavis Stone,Anthony Sarah,Andrés Muñoz-Jaramillo,A. A. Narock,Adam Szabo +11 more
TL;DR: Deep-SWIM as discussed by the authors is an approach leveraging advances in contrastive learning, pseudo-labeling and online hard example mining to robustly identify discontinuities in solar wind magnetic field data.
Posted Content
Self-supervised Video Object Segmentation by Motion Grouping
TL;DR: In this paper, a simple variant of the Transformer is introduced to segment optical flow frames into primary objects and the background, and the architecture is trained in a self-supervised manner without using any manual annotations.
Posted Content
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
TL;DR: Zhang et al. as discussed by the authors proposed a differentiable registration module to align consecutive frames based on the background, which effectively emphasises the object boundary in the difference image and a motion segmentation module with memory that discovers the moving objects, while maintaining the object permanence even when motion is absent at some point.