Computer Vision and Machine Learning

Apratim Bhattacharyya (PhD Student)

Personal Information


  • 2016-present, Ph.D. candidate in Computer Science, Max Planck Institute for Informatics, Germany
  • 2014-2016, M.Sc.(Honors Degree) in Computer Science, Saarland University, Germany
  • 2010-2014, B.Tech. in Computer Engineering, National Institute of Technology, Karnataka, India



Google Scholar | CV




Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers,
A. Bhattacharyya, D. Reino, M. Fritz and B. Schiele,

Computer Vision and Pattern Recognition (CVPR), 2021.
Paper | arXivCode | Data | Video




Normalizing Flows with Multi-scale Autoregressive Priors,
A. Bhattacharyya*, S. Mahajan*, M. Fritz, B. Schiele​​​​ and S. Roth,

Computer Vision and Pattern Recognition (CVPR), 2020 and INNF+@ICML'20.
Paper | Workshop (improved results) | Code | Video (*Equal contribution)


Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning, 
A. Salem, A. Bhattacharyya, M. Backes, M. Fritz and Y. Zhang, 

USENIX Security Symposium (USENIX Security), 2020.


Haar Wavelet based Block Autoregressive Flows for Trajectories, 
A. Bhattacharyya, C. Straehle, M. Fritz and B. Schiele,

German Conference on Pattern Recognition, 2020 (oral) and ML4AD@NeurIPS’20.
arXivCode coming soon


SampleFix: Learning to Correct Programs by Sampling Diverse Fixes,
H. Hajipour, A. Bhattacharyya, M. Fritz,





Conditional Flow Variational Autoencoders for Structured Sequence Prediction,
A. Bhattacharyya, M. Hanselmann, M. Fritz, B. Schiele and C. Straehle,

Technical Report, 2019, BDL@NeurIPS’19 and ML4AD@NeurIPS’19 (oral).
arXiv | Video


"Best-of-Many-Samples" Distribution Matching,
A. Bhattacharyya, M. Fritz and B. Schiele,

Technical Report, 2019 and BDL@NeurIPS’19.


Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods,
A. Bhattacharyya, M. Fritz and B. Schiele, 

International Conference on Learning Representations (ICLR), 2019.
OpenReviewarXiv | Code+Data




Accurate and Diverse Sampling of Sequences based on a “Best of Many” Sample Objective,
A. Bhattacharyya, M. Fritz and B. Schiele,

Computer Vision and Pattern Recognition (CVPR), 2018 (oral).
Paper | arXiv | Code


Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty,
A. Bhattacharyya, M. Fritz and B. Schiele,  

Computer Vision and Pattern Recognition (CVPR), 2018.
Paper | arXiv | Code+Data


Long-Term Image Boundary Prediction,
A. Bhattacharyya, M. Malinowski, B. Schiele and M. Fritz, 

AAAI Conference on Artificial Intelligence, 2018.
Paper | arXiv




Long-Term On-Board Prediction of Pedestrians in Traffic Scenes,
A. Bhattacharyya, M. Fritz and B. Schiele,

Conference on Robot Learning (CoRL), 2017, Workshop Track.


Efficiently Summarising Event Sequences with Rich Interleaving Patterns,
A. Bhattacharyya and J. Vreeken,

SIAM International Conference on Data Mining (SDM), 2017.
Paper | arXiv




Long Term Boundary Extrapolation for Deterministic Motion,
A. Bhattacharyya, M. Malinowski and M. Fritz,

NIPS Workshop on Intuitive Physics, 2016.