no code implementations • 3 Mar 2023 • Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani, Fatih Porikli
Specifically, we propose cross-task distillation from an instance segmentation teacher (X-IS) in the PV feature extraction stage providing supervision without ambiguous error backpropagation through the view transformation.
no code implementations • CVPR 2023 • Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani, Fatih Porikli
Specifically, we propose cross-task distillation from an instance segmentation teacher (X-IS) in the PV feature extraction stage providing supervision without ambiguous error backpropagation through the view transformation.
Ranked #5 on 3D Object Detection on nuscenes Camera-Radar
1 code implementation • 22 Mar 2020 • Amirreza Farnoosh, Behnaz Rezaei, Eli Zachary Sennesh, Zulqarnain Khan, Jennifer Dy, Ajay Satpute, J. Benjamin Hutchinson, Jan-Willem van de Meent, Sarah Ostadabbas
This results in a flexible family of hierarchical deep generative factor analysis models that can be extended to perform time series clustering or perform factor analysis in the presence of a control signal.
1 code implementation • ECCV 2020 • Behnaz Rezaei, Amirreza Farnoosh, Sarah Ostadabbas
Our model, called generative low-dimensional background model (G-LBM) admits variational operations on the distribution of the manifold coordinates and simultaneously generates a low-rank structure of the latent manifold given the data.
no code implementations • 20 Sep 2019 • Behnaz Rezaei, Yiorgos Christakis, Bryan Ho, Kevin Thomas, Kelley Erb, Sarah Ostadabbas, Shyamal Patel
Over the past decade, significant advances have been made in the use of wearable technology for continuously monitoring human motor behavior in free-living conditions.
1 code implementation • 3 Feb 2019 • Amirreza Farnoosh, Behnaz Rezaei, Sarah Ostadabbas
This paper presents a novel unsupervised probabilistic model estimation of visual background in video sequences using a variational autoencoder framework.
no code implementations • 3 Nov 2017 • Behnaz Rezaei, Sarah Ostadabbas
In this regard, our paper addresses the problem of background modeling in a computationally efficient way, which is important for current eruption of "big data" processing coming from high resolution multi-channel videos.
no code implementations • 13 Jun 2016 • Katie Hoemann, Behnaz Rezaei, Stacy C. Marsella, Sarah Ostadabbas
Human interactions are characterized by explicit as well as implicit channels of communication.
no code implementations • 1 Jun 2016 • Maria S. Perez-Rosero, Behnaz Rezaei, Murat Akcakaya, Sarah Ostadabbas
Furthermore, in order to avoid information redundancy and the resultant over-fitting, a feature reduction method is proposed based on a correlation analysis to optimize the number of features required for training and validating each weak learner.