Emre Aksan

PhD Student
emre.aksan@inf.ethz.ch

About me

I am a PhD student at ETH Zurich, working in the Advanced Interactive Technologies lab with Professor Otmar Hilliges. I received my BSc (2013) and MSc (2015) degrees from Middle East Technical University (METU) in Computer Engineering. Prior to joining ETH, I worked on pattern analysis of functional magnetic resonance imaging at METU.


Research Interests

My research interests lie at the intersection of machine learning, computer vision, and human-computer interaction, with a primary focus on the perception and synthesis of human activities, aiming to digitize humans in various aspects. Technically, I am interested in deriving new machine learning algorithms, particularly generative temporal models to capture human dynamics and generate human-like interactions. My current research focuses on deep generative temporal models with applications in the tasks of 3D motion modeling and prediction, building 3D face avatars, and modeling and synthesis of free-form human actions such as digital representations of drawings and handwritten text.

You can also find me on Twitter, Linkedin, and Google scholar.

Publications

Physically Plausible Full-Body Hand-Object Interaction Synthesis
Jona Braun, Sammy Christen, Muhammed Kocabas, Emre Aksan, Otmar Hilliges
International Conference on 3D Vision 2024 (3DV), 2024
Accepted as Spotlight Presentation
Video Paper Code
LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space
Emre Aksan, Shugao Ma, Akin Caliskan, Stanislav Pidhorskyi, Alexander Richard, Shih-En Wei, Jason Saragih, Otmar Hilliges
European Conference on Computer Vision (ECCV), 2022
Video Paper
Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors
Xi Wang*, Gen Li*, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan, Otmar Hilliges * Equal contribution
International Conference on 3D Vision (3DV), 2022
Video Paper
D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
Sammy Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo, Jie Song, Otmar Hilliges
Computer Vision and Pattern Recognition (CVPR), 2022
Video Paper Code
A Spatio-temporal Transformer for 3D Human Motion Prediction
Emre Aksan, Manuel Kaufmann, Peng Cao, Otmar Hilliges
International Conference on 3D Vision (3DV), 2021
Video Paper Code
Learning Functionally Decomposed Hierarchies for Continuous Control Tasks With Path Planning
Sammy Christen*, Lukas Jendele*, Emre Aksan, Otmar Hilliges * Equal contribution
IEEE Robotics and Automation Letters (Volume: 6, Issue: 2), 2021
Accepted as Oral Presentation at the Deep RL Workshop at NeurIPS
Video Paper Code
CoSE: Compositional Stroke Embeddings
Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges
Advances in Neural Information Processing Systems, 2020
Paper Code
Convolutional Autoencoders for Human Motion Infilling
Manuel Kaufmann, Emre Aksan, Jie Song, Fabrizio Pece, Remo Ziegler, Otmar Hilliges
2020 International Conference on 3D Vision (3DV), 2020
Video Paper Code
Towards End-to-end Video-based Eye-Tracking
Seonwook Park, Emre Aksan, Xucong Zhang, Otmar Hilliges
European Conference on Computer Vision (ECCV), 2020
Paper Data Code
Structured Prediction Helps 3D Human Motion Modelling
Emre Aksan*, Manuel Kaufmann*, Otmar Hilliges * Equal contribution
The IEEE International Conference on Computer Vision (ICCV), 2019
Video Paper Code
STCN: Stochastic Temporal Convolutional Networks
Emre Aksan, Otmar Hilliges
International Conference on Learning Representations (ICLR), 2019
Paper Code
Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time
Yinghao Huang*, Manuel Kaufmann*, Emre Aksan, Michael Black, Otmar Hilliges, Gerard Pons-Moll * Equal contribution
ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 2018
Video Paper Data Code
DeepWriting: Making Digital Ink Editable via Deep Generative Modeling
Emre Aksan, Fabrizio Pece, Otmar Hilliges
SIGCHI Conference on Human Factors in Computing Systems, 2018
Honorable Mention Best Paper Award
Video Paper Code
Learning human motion models for long-term predictions
Partha Ghosh, Jie Song, Emre Aksan, Otmar Hilliges
2017 International Conference on 3D Vision (3DV), 2017
Best Paper Award
Video Paper Code
Guiding InfoGAN with Semi-Supervision
Adrian Spurr, Emre Aksan, Otmar Hilliges
ECML PKDD, 2017
Paper Code

Theses

An fMRI Segmentation Method Under Markov Random Fields for Brain Decoding — MSc Thesis, METU


Academic Activities

Reviewing

2022
CVPR, SIGGRAPH, TMLR, T-PAMI
2021
CVPR, ICCV, ICLR, NeurIPS (Outstanding Reviewer Award)
2020
CVPR, ECCV, ICLR, T-PAMI
2019
ICCV

Student Theses

2020
Doruk Çetin Master Thesis
Learning in-the-wild Temporal 3D Pose Estimation from MoCap Data
2019
Şahan Ayvaz Master Thesis
A Study of Sparse Policy Networks for Deep Reinforcement Learning
Lukas Jendele Master Thesis
Learning Functionally Decomposed Hierarchies for Continuous Navigation Tasks
Sami Hamdan Master Thesis
Stochastic Temporal Convolutional Networks for Speech Enhancement
2018
Andreas Blöchliger Master Thesis
Representation Learning for Sketch Suggestions based on the Combination of CNNs and RNNs
Şahan Ayvaz Bachelor Thesis
Emergence and Imitation of Locomotion in 2D and 3D Environments
Martin Blapp Bachelor Thesis
Evaluation of Human Motion Models
2017
Manuel Kaufmann Master Thesis
A Deep Learning Approach to Human Motion Sequences Infilling
Adrian Spurr Master Thesis
Semi-supervised Information Maximising Generative Adversarial Networks

Teaching