Sadegh Aliakbarian




I’m a research scientist at Microsoft Mixed Reality & AI Lab in Cambridge, UK.
I completed my PhD at the Australian National University under supervision of Lars Petersson,
Mathieu Salzmann, Stephen Gould, and Basura Fernando, where I received NICTA PhD scholarship.

During my PhD, I spent time at Amazon Science, FiveAI, and Qualcomm AI Research as a research intern
working on different aspects of machine learning and computer vision.

Over the past few years, I served the community as a peer reviewer for top-tier CV conferences
and journals, and in 2020, I have been awarded the Outstanding Reviewer Award at CVPR 2020.

My research interests are machine learning and computer vision, with the focus on generative
models and human motion/activity understanding.

Publications

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Fatemeh Saleh, Sadegh Aliakbarian, Hamid Rezatofighi, Mathieu Salzmann, Stephen Gould
Proceedings of the IEEE international conference on computer vision (CVPR), 2021 (Oral)
[project page / arXiv / video / code]
Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network
Mehrdad Shoeiby, Sadegh Aliakbarian, Saeed Anwar and Lars petersson
Machine Vision and Applications (MVA), 2021
[project page / arXiv / video / code]
Uncertainty Inspired RGB-D Saliency Detection
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Saleh, Sadegh Aliakbarian, Nick Barnes
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
[project page / arXiv / video / code]
A Stochastic Conditioning Scheme for Diverse Human Motion Prediction
Sadegh Aliakbarian, Fatemeh Saleh, Mathieu Salzmann, Lars Petersson, Stephen Gould
Proceedings of the IEEE international conference on computer vision (CVPR), 2020
[project page / arXiv / video / code]
Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network
Mehrdad Shoeiby, Lars Petersson, Ali Armin, Sadegh Aliakbarian
Winter Conference on Applications of Computer Vision (WACV), 2020
[project page / arXiv / Video / Code]
Mosaic Super-resolution via Sequential Feature Pyramid Networks
Mehrdad Shoeiby, Ali Armin, Sadegh Aliakbarian, Saeed Anwar, Lars Petersson
Proceedings of the IEEE international conference on computer vision Workshops (CVPRW), 2020
[project page / arXiv / Video / Code]
Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior
Sadegh Aliakbarian, Fatemeh Saleh, Mathieu Salzmann, Lars Petersson, Stephen Gould
ArXiv, 2019
[project page / arXiv / Video / Code]
VIENA2: A Driving Anticipation Dataset
Sadegh Aliakbarian, Fatemeh Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson
Asian Conference on Computer Vision (ACCV), 2018
[project page / arXiv / Video / Code]
Effective Use of Synthetic Data in Urban Scene Semantic Segmentation
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M Alvarez
European Conference on Computer Vision (ECCV), 2018
[project page / arXiv / Video / Code]
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M Alvarez, Stephen Gould
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
[project page / arXiv / Video / Code]
Encouraging LSTMs to Anticipate Actions Very Early
Sadegh Aliakbarian, Fatemeh Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson
International Conference on Computer Vision (ICCV), 2017
[project page / arXiv / Video / Code]
Bringing background into the foreground: Making all classes equal in weakly-supervised video semantic segmentation
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M Alvarez
International Conference on Computer Vision (ICCV), 2017
[project page / arXiv / Video / Code]
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Stephen Gould, Jose M Alvarez
European Conference on Computer Vision (ECCV), 2016
[project page / arXiv / Video / Code]
Patents:
Predicting subject body poses and subject movement intent using probabilistic generative models
Sadegh Aliakbarian, Amirhossein Habibian, Koen Erik Adriaan Van de Sande
US Patent, 10937173, 2021

Work Experience

Research Scientist | Microsoft Research

Working on human motion analysis for Hololens, as part of the Mixed Reality and AI Lab.

  • Cambridge, United Kingdom
  • March 2021 - Now
Research Intern | Amazon Science

Working on weakly-supervised representation learning, with the focus on learning disentangled representation. I also did a little bit of research on image manipulation using scene graph modification.

  • Adelaide, South Australia, Australia
  • October 2020 - February 2021
Research Intern | FiveAI Ltd

Working on adversarial machine learning and adaptive adversarial attacks, with the focus on designing a defense mechanism to stop adaptive attacks. FiveAI is a UK-based self-driving startup. Five raised $41 million just in 2020.

  • Oxford, United Kingdom
  • January 2020 - July 2020
Research Intern | Qualcomm AI Research

Working on sequence analysis for human intention forecasting via analysing motion. The project is used for pedestrian intention forecasting for autonomous cars.

  • Amsterdam, Netherlands
  • May 2018 - October 2018

Contact

Location:

21 Station Rd, Cambridge CB1 2FB, United Kingdom

Loading
Your message has been sent. Thank you!