M
Majid Mirmehdi
Researcher at University of Bristol
Publications - 247
Citations - 6104
Majid Mirmehdi is an academic researcher from University of Bristol. The author has contributed to research in topics: Image segmentation & Active contour model. The author has an hindex of 38, co-authored 237 publications receiving 5523 citations. Previous affiliations of Majid Mirmehdi include City University London & Vision Institute.
Papers
More filters
Proceedings Article
Generic motion based object segmentation for assisted navigation
TL;DR: A robust approach to annotating independently moving objects captured by head mounted stereo cameras that are worn by an ambulatory (and visually impaired) user is proposed.
Book ChapterDOI
Visual Homing of an Upper Torso Humanoid Robot Using a Depth Camera
TL;DR: A system which can automatically home an upper torso humanoid robot so that its true joint angles are known using only information from a depth camera, coupled with incremental encoders, is presented.
Posted Content
Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance
TL;DR: In this paper, a holistic attention network based super-resolution approach and a custom-built altitude data exploitation network are integrated into standard recognition pipelines for animal detection in real-world settings.
Journal ArticleDOI
Use Your Head: Improving Long-Tail Video Recognition
TL;DR: In this article , Long-Tail Mixed Reconstruction (LMR) is proposed, which reduces overfitting to instances from few-shot classes by reconstructing them as weighted combinations of samples from head classes.