Arsalan Mousavian

Address: Department of Computer Science
George Mason University
4400 University Dr
Fairfax, Virginia, USA
Email: amousavi AT gmu DOT edu

2004 - 2010 2010 - 2013 June-Aug 2015 June-Aug 2016 June-Aug 2017 Aug 2017 - May 2018 2013 - 2018 2018 - now


I joined NVIDIA Robotics Lab in Seattle.
I graduated from PhD at Computer Science department of George Mason University. I worked under supervision of Jana Kosecka. My research interests are computer vision, deep learning, and robotics. I worked on semantic and 3D understanding of the scene and how to use it to navigate in indoor environments. In my research, I have worked on Learning based navigation in indoor environments, 3D pose estimation, Semantic Segmentation, Depth Estimation, Instance detection, and Image based localization. I have done internship in StreetSmart team of Google inc and in perception team of Zoox inc where I worked with great team of researchers and engineers solving real computer vision problems for autonomous driving. I spent the last year of my PhD at Google Brain Robotics team where I worked on learning to navigate in indoor environments. Prior to my PhD, I got my masters in Robotics and Artificial Intelligence in University of Tehran.

News:


Publications:


Visual Represenatations for Semantic Target Driven Navigation
Arsalan Mousavian, Alexander Toshev, Marek Fiser, Jana Kosecka, James Davidson
ECCV Workshop (ECCVw) on Visual Learning and Embodied Agents in Simulation Environments, Munich, Germany, 2018
[Paper] [bibtex]

 
     

Synthesizing Training Data for Object Detection in Indoor Scenes
Georgios Georgakis, Arsalan Mousavian, Alexander C. Berg, Jana Kosecka
Robotics: Science and Systems Conference (RSS), Cambridge MA, 2017
[Paper] [bibtex]

 
     

3D Bounding Box Estimation Using Deep Learning and Geometry
Arsalan Mousavian, Dragomir Anguelov, John Flynn, Jana Kosecka
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu HI, 2017
[Paper] [Supplementary Material] [bibtex] [IEEE Spectrum][Forbes]
Estimated 3D Boxes on the split of 3DVP: [Download Link]

 
     

Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
Arsalan Mousavian, Hamed Pirsiavash, Jana Kosecka
International Conference on 3DVision(3DV), Stanford CA, 2016
[Paper] [bibtex]

 
     

Multiview RGB-D Dataset for Object Instance Detection
Georgios Georgakis, Md Alimoor Reza, Arsalan Mousavian, Phi-Hung Le, Jana Kosecka
International Conference on 3DVision(3DV), Stanford CA, 2016
[Paper] [Dataset Link] [bibtex]

 
     

Semantic Image Based Geolocation Given a Map
Arsalan Mousavian, Jana Kosecka
arXiv 2016
[Paper]

 
     

Deep Convolutional Features for Image Based Retrieval and Scene Categorization
Arsalan Mousavian, Jana Kosecka
arXiv 2015
[Paper] [bibtex]

 
     

Semantically Guided Location Recognition for Outdoors Scenes
Arsalan Mousavian, Jana Kosecka, Jyh-Ming Lien.
International Conference on Automation and Robotics (ICRA), Seattle WA, 2015
[Paper] [bibtex]

 
     

Semantically Aware Bag-of-words for Localization
Arsalan Mousavian, Jana Kosecka.
Computer Vision and Pattern Recognition 2015 workshop on Semantic for Visual Reconstruction, Localization, and Mapping (CVPRW), Boston, MA, 2015
[Paper] [bibtex]

 
     

Relevant Coursework: