1 code implementation • 23 Apr 2021 • Yang Liu, Luiz G. Hafemann, Michael Jamieson, Mehrsan Javan
Tracking players in sports videos is commonly done in a tracking-by-detection framework, first detecting players in each frame, and then performing association over time.
no code implementations • NeurIPS 2020 • Guiliang Liu, Oliver Schulte, Pascal Poupart, Mike Rudd, Mehrsan Javan
This paper develops a new approach for agent representations, based on a Markov game model, that is tailored towards applications in professional ice hockey.
no code implementations • 5 Sep 2020 • Alvin Chan, Martin D. Levine, Mehrsan Javan
We propose an end-to-end trainable ResNet+LSTM network, with a residual network (ResNet) base and a long short-term memory (LSTM) layer, to discover spatio-temporal features of jersey numbers over time and learn long-term dependencies.
no code implementations • 9 Aug 2020 • Madhu Kiran, Amran Bhuiyan, Louis-Antoine Blais-Morin, Mehrsan Javan, Ismail Ben Ayed, Eric Granger
Our Mutual Attention network relies on the joint spatial attention between image and optical flow features maps to activate a common set of salient features across them.
Optical Flow Estimation Video-Based Person Re-Identification
no code implementations • 21 Apr 2020 • Ryan Sanford, Siavash Gorji, Luiz G. Hafemann, Bahareh Pourbabaee, Mehrsan Javan
Group activity detection in soccer can be done by using either video data or player and ball trajectory data.
no code implementations • CVPR 2020 • Kirill Gavrilyuk, Ryan Sanford, Mehrsan Javan, Cees G. M. Snoek
This paper strives to recognize individual actions and group activities from videos.
1 code implementation • 17 Sep 2019 • Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles, Weiwei Sun, Mehrsan Javan, Kwang Moo Yi
We propose an optimization-based framework to register sports field templates onto broadcast videos.
no code implementations • 4 Jul 2019 • Hugo Masson, Amran Bhuiyan, Le Thanh Nguyen-Meidine, Mehrsan Javan, Parthipan Siva, Ismail Ben Ayed, Eric Granger
Then, these techniques are analysed according to their pruningcriteria and strategy, and according to different scenarios for exploiting pruningmethods to fine-tuning networks to target domains.