Hi, I have been working as a postdoctoral researcher at the Torr Vision Group (University of Oxford) since 1st Aug 2016. I am also associated with an amazing startup based in Cambridge (U.K.) called FiveAI where we are trying to build driverless cars.
I work in the field of machine learning (optimization, deep learning, generative models etc.) and its applications to vision and language. Please find below few research areas (and related articles) that I am currently excited about.
- Incremental Learning: RWalk
- Generative Models: MAD-GAN (CVPR18)
- Vision and Language: Flip-Dial (CVPR18)
- Weakly supervised semantic segmentation: BMVC17, EMMCVPR17
- High-Order Inference: Parsimonious Labeling (ICCV15)
- Structured Prediction: HOAP-SVM (ECCV14), ECCV16, ICML16
Students (jointly with Prof. Philip Torr)
- Arslan Chaudhry (PhD student since Jan 2017)
- Arnab Ghosh (Intern, Jan-July 2017)
- Anuj Sharma (Masters thesis intern, Feb-Aug 2017), [Masters Thesis]
[NEW] Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
arXiv, Jan 2018
Arslan Chaudhry*, Puneet K. Dokania*, Thalaiyasingam Ajanthan*, Philip H. S. Torr
[NEW] Multi-Agent Diverse Generative Adversarial Networks
Arnab Ghosh, Viveka Kulharia, Vinay Namboodiri, Philip H. S. Torr, Puneet K. Dokania
In CVPR 2018 (Spotlight), Salt Lake, USA
[NEW] FlipDial: A Generative Model for Two-Way Visual Dialogue
Daniela Massiceti, N. Siddharth, Puneet K. Dokania, Philip H.S. Torr
In CVPR 2018 (Oral), Salt Lake, USA
09) Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
A. Chaudhry, Puneet K. Dokania, Philip H. S. Torr
In BMVC 2017 (Oral), London, U.K.
08) Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
Q. Hou, D. Massiceti, P. K. Dokania, Y. Wei, M-M. Cheng, Philip H. S. Torr
In EMMCVPR 2017, Venice, Italy.
07) Deformable Registration through Learning of Context-Specific Metric Aggregation
E. Ferrante*, P. K. Dokania*, R. Marini, N. Paragios
In MLMI MICCAI 2017, Quebec, Canada.
06) Partial Linearization based Optimization for Multi-class SVM
P. Mohapatra, P. K. Dokania, C. V. Jawahar, M. P. Kumar
In ECCV 2016, Amsterdam, the Netherlands.
Supplementary | Poster
05) Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
A. Osokin, JB Alayrac, I. Lukasewitz, P. K. Dokania, S. Lacoste-Julien
In ICML 2016, New York City, USA.
02) Learning-Based Approach for Online Lane Change Intention Prediction
P. Kumar , M. Perrollaz, S. Lefevre and C. Laugier
In IEEE Intelligent Vehicle Symposium (IV) 2013, Gold Coast City, Australia.
Video-1 (Best viewed in VLC) | Video-2 (Best viewed in VLC)
01) Discriminative parameter estimation for random walks segmentation
P. Y. Baudin, D. Goodman, P. Kumar , N. Azzabou, P. G. Carlier, N. Paragios, M. Pawan Kumar
In MICCAI 2013, Nagoya, Japan.
03) Rounding-based Moves for Semi-Metric Labeling
M. Pawan Kumar and Puneet K. Dokania
In JMLR 2016.
02) High Dynamic Range Fuzzy Color Image Enhancement Using Ant Colony System
O. P. Verma, P. Kumar , M. Hanmandlu, S. Chhabra
In Journal of Applied Soft Computing, 2012.
01) A Novel Bacterial Foraging Technique for Edge Detection
O. P. Verma, M. Hanmandlu, P. Kumar , S. Chhabra, A. Jindal
In Pattern Recognition Letters, 2011.
Technical Reports and Thesis
02) High-Order Inference, Ranking, and Regularization Path for Structured SVM
Puneet Kumar Dokania, PhD Thesis 2016
01) Learning-Based Approach for Online Lane Change Intention Prediction
Puneet Kumar, Master Thesis 2012.