Apratim Bhattacharyya (PhD Student)

Apratim Bhattacharyya

Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
E1 4 - Room 627
+49 681 9325 2027
+49 681 9325 2099
Get email via email

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


Accurate and Diverse Sampling of Sequences based on a “Best of Many” Sample Objective
A. Bhattacharyya, M. Fritz and B. Schiele
31st IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018
(Accepted/in press)
Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
A. Bhattacharyya, M. Fritz and B. Schiele
31st IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018
(Accepted/in press)
Long-Term Image Boundary Prediction
A. Bhattacharyya, M. Malinowski, B. Schiele and M. Fritz
Thirty-Second AAAI Conference on Artificial Intelligence, 2018
Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
A. Bhattacharyya, M. Fritz and B. Schiele
Technical Report, 2018
(arXiv: 1806.06939)
For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem can be formalized as a sequence prediction problem, where a number of observations are used to predict the sequence into the future. However, real-world scenarios demand a model of uncertainty of such predictions, as future states become increasingly uncertain and multi-modal -- in particular on long time horizons. This makes modelling and learning challenging. We cast state of the art semantic segmentation and future prediction models based on deep learning into a Bayesian formulation that in turn allows for a full Bayesian treatment of the prediction problem. We present a new sampling scheme for this model that draws from the success of variational autoencoders by incorporating a recognition network. In the experiments we show that our model outperforms prior work in accuracy of the predicted segmentation and provides calibrated probabilities that also better capture the multi-modal aspects of possible future states of street scenes.
Long-Term On-Board Prediction of Pedestrians in Traffic Scenes
A. Bhattacharyya, M. Fritz and B. Schiele
1st Conference on Robot Learning (CoRL 2017), 2017
Efficiently Summarising Event Sequences with Rich Interleaving Patterns
A. Bhattacharyya and J. Vreeken
Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), 2017
Long Term Boundary Extrapolation for Deterministic Motion
A. Bhattacharyya, M. Malinowski and M. Fritz
NIPS Workshop on Intuitive Physics, 2016