Sadegh Aliakbarian

I'm a senior research scientist at Microsoft Mesh Labs - Cambridge (UK), working on Microsoft Mesh, with the focus on next generation of avatars and motion generation for avatars.
I did my PhD at the Australian National University, working on generative modeling of human motion. During my PhD, I interned at Amazon AI, Five AI, and Qualcomm AI Research, working on generative models, representation learning, and adversarial examples.

           

profile photo
Latest News

We shipped Microsoft Mesh. Huge congratulations to the team!
We shipped audio-driven Mesh Avatars! Huge congratulations to the team!
From March 2021, I joined Microsoft Mixed Reality and AI Lab-Cambridge (UK) as a research scientist.
Finished my PhD on Deep Sequence Learning for Video Anticipation at the Australian National University.
Selected for Outstanding Reviewer Award at CVPR 2020.

Research

I'm interested in computer vision and machine learning, with the focus on generative AI, video understanding, and 3D vision.

2024
SimpleEgo: Predicting probabilistic body pose from egocentric cameras
Hanz Cuevas Velasquez, Charlie Hewitt, Sadegh Aliakbarian, Tadas Baltrusaitis
International Conference on 3D Vision (3DV), 2024
[project page / arXiv / Video / code]
2023
HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations
Sadegh Aliakbarian, Fatemeh Saleh, David Collier, Pashmina Cameron, Darren Cosker
International Conference on Computer Vision (ICCV), 2023
[project page / arXiv / Video / code]
Imitator: Personalized Speech-driven 3D Facial Animation
Balamurugan Thambiraja, Ikhsanul Habibie, Sadegh Aliakbarian, Darren Cosker, Christian Theobalt, Justus Thies
International Conference on Computer Vision (ICCV), 2023
[project page / arXiv / Video / code]
Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
Siwei Zhang, Qianli Ma, Yan Zhang, Sadegh Aliakbarian, Darren Cosker, Siyu Tang
International Conference on Computer Vision (ICCV), 2023 (Oral Presentation)
[project page / arXiv / Video / code]
2022
FLAG: Flow-based Avatar Generation from Sparse Observations
Sadegh Aliakbarian, Pashmina Cameron, Federica Bogo, Andew Fitzgibbon, Thomas J. Cashman
International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[ project page / arXiv / Talk / code]
2021
Contextually Plausible and Diverse 3D Human Motion Prediction
Sadegh Aliakbarian, Fatemeh Saleh, Lars Petersson, Stephen Gould, Mathieu Salzmann
International Conference on Computer Vision (ICCV), 2021 (Oral Presentation)
[project page / arXiv / video / code]
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 Presentation)
[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]
2020
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]
2019
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]
2018
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]
2017
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]
2016
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]

           

 

Thanks for the template