Emad Bahrami

emadbr.jpg

I am a PhD Student at Computer Vision Group at University of Bonn supervised by Prof. Jürgen Gall. My current research focuses on video understanding including temporal action segmentation. I am interested in developing methods for untrimmed video understanding.

Previously, I was a researcher at Deep MI lab developing deep learning-based methods for semantic segmentation of brain MRI scans. Prior to starting my PhD, I was a visiting researcher at the Computer Vision Group working on action recognition and future frame prediction under supervision of Prof. Jürgen Gall. Before University of Bonn, I completed my undergraduate degree at the University of Tehran.

selected publications[view all]

  1. Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation
    Olga Zatsarynna*, Emad Bahrami*, Yazan Abu Farha, and 2 more authors
    * Indicates equal contribution.
    European Conference on Computer Vision (ECCV) 2024
  2. How Much Temporal Long-Term Context is Needed for Action Segmentation?
    Emad Bahrami, Gianpiero Francesca, and Juergen Gall
    IEEE International Conference on Computer Vision (ICCV) 2023
  3. CerebNet: A fast and reliable deep-learning pipeline for detailed cerebellum sub-segmentation
    Jennifer Faber*, David Kügler*, Emad Bahrami*, and 14 more authors
    * Indicates equal contribution.
    NeuroImage 2022
  4. Robust Action Segmentation from Timestamp Supervision
    Yaser Souri*, Yazan Abu Farha*, Emad Bahrami*, and 2 more authors
    * Indicates equal contribution.
    British Machine Vision Conference (BMVC) 2022
  5. TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
    Saber* Pourheydari, Emad Bahrami*, Mohsen Fayyaz*, and 3 more authors
    * Indicates equal contribution.
    British Machine Vision Conference (BMVC) 2022
  6. 3D CNNs With Adaptive Temporal Feature Resolutions
    Mohsen Fayyaz*, Emad Bahrami*, Ali Diba, and 4 more authors
    * Indicates equal contribution.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021