Follow
Sadegh Aliakbarian
Sadegh Aliakbarian
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
F Saleh, MS Aliakbarian, M Salzmann, L Petersson, S Gould, JM Alvarez
European Conference on Computer Vision (ECCV), 2016
1942016
Encouraging lstms to anticipate actions very early
M Sadegh Aliakbarian, F Sadat Saleh, M Salzmann, B Fernando, ...
Proceedings of the IEEE International Conference on Computer Vision, 280-289, 2017
1922017
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
FS Saleh, MS Aliakbarian, M Salzmann, L Petersson, JM Alvarez
Proceedings of the European Conference on Computer Vision (ECCV), 84--100, 2018
1812018
Uncertainty inspired RGB-D saliency detection
J Zhang, DP Fan, Y Dai, S Anwar, F Saleh, S Aliakbarian, N Barnes
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
1232021
A stochastic conditioning scheme for diverse human motion prediction
S Aliakbarian, FS Saleh, M Salzmann, L Petersson, S Gould
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
1072020
Probabilistic tracklet scoring and inpainting for multiple object tracking
F Saleh, S Aliakbarian, H Rezatofighi, M Salzmann, S Gould
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
90*2021
Bringing background into the foreground: Making all classes equal in weakly-supervised video semantic segmentation
FS Saleh, MS Aliakbarian, M Salzmann, L Petersson, JM Alvarez
2017 IEEE international conference on computer vision (ICCV), 2125-2135, 2017
482017
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
FS Saleh, MS Aliakbarian, M Salzmann, L Petersson, JM Alvarez, S Gould
IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (6), 1382-1396, 2018
422018
Contextually plausible and diverse 3d human motion prediction
S Aliakbarian, F Saleh, L Petersson, S Gould, M Salzmann
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
372021
VIENA: A driving anticipation dataset
MS Aliakbarian, FS Saleh, M Salzmann, B Fernando, L Petersson, ...
Asian Conference on Computer Vision, 449-466, 2018
312018
Flag: Flow-based 3d avatar generation from sparse observations
S Aliakbarian, P Cameron, F Bogo, A Fitzgibbon, TJ Cashman
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
252022
Predicting subject body poses and subject movement intent using probabilistic generative models
S ALIAKBARIAN, A HABIBIAN, KEA VAN DE SANDE
US Patent 10,937,173, 2021
242021
Deep action-and context-aware sequence learning for activity recognition and anticipation
MS Aliakbarian, F Saleh, B Fernando, M Salzmann, L Petersson, ...
arXiv preprint arXiv:1611.05520, 2016
162016
Imitator: Personalized speech-driven 3d facial animation
B Thambiraja, I Habibie, S Aliakbarian, D Cosker, C Theobalt, J Thies
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
152023
Optimal supervised feature extraction in internet traffic classification
MS Aliakbarian, A Fanian, FS Saleh, TA Gulliver
2013 IEEE Pacific Rim Conference on Communications, Computers and Signal …, 2013
14*2013
Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network
M Shoeiby, L Petersson, A Armin, S Aliakbarian
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020
8*2020
Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
S Zhang, Q Ma, Y Zhang, S Aliakbarian, D Cosker, S Tang
arXiv preprint arXiv:2304.06024, 2023
62023
Learning variations in human motion via mix-and-match perturbation
MS Aliakbarian, FS Saleh, M Salzmann, L Petersson, S Gould, ...
arXiv preprint arXiv:1908.00733, 2019
42019
Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders
MS Aliakbarian, FS Saleh, M Salzmann, L Petersson, S Gould
22019
3diface: Diffusion-based speech-driven 3d facial animation and editing
B Thambiraja, S Aliakbarian, D Cosker, J Thies
arXiv preprint arXiv:2312.00870, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20