no code implementations • 2 Aug 2020 • Alireza Abedin, Farbod Motlagh, Qinfeng Shi, Seyed Hamid Rezatofighi, Damith Chinthana Ranasinghe
Our ability to exploit low-cost wearable sensing modalities for critical human behaviour and activity monitoring applications in health and wellness is reliant on supervised learning regimes; here, deep learning paradigms have proven extremely successful in learning activity representations from annotated data.
no code implementations • CVPR 2016 • Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid
Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score.
no code implementations • CVPR 2016 • Trung T. Pham, Seyed Hamid Rezatofighi, Ian Reid, Tat-Jun Chin
We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion.
no code implementations • 13 Apr 2016 • Anton Milan, Seyed Hamid Rezatofighi, Anthony Dick, Ian Reid, Konrad Schindler
Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking.
1 code implementation • ICCV 2015 • Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid
In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program.
no code implementations • 23 Jul 2015 • Seyed Hamid Rezatofighi, Stephen Gould, Ba Tuong Vo, Ba-Ngu Vo, Katarina Mele, Richard Hartley
To deal with this, we propose a bootstrap filter composed of an estimator and a tracker.