Amir  Roshan Zamir

About Me:

I'm a postdoctoral researcher at Stanford University, CS department, Computational Vision and Geometry Lab. My primary area of research is Computer Vision (more specifically, self-supervised/unsupervised representation learning, video understanding, geo-spatial analysis, and graph theory). I received my PhD under supervision of Mubarak Shah in 2014.

Please feel free to contact me with any comments or questions.

Latest News:

Jun. 2016: We received CVPR Best Student Paper Award for Structural-RNN.

Jun. 2016: New paper: Generic 3D Representations via Pose Estimation and Matching,
Amir R. Zamir, Pulkit Agrawal, Tilman Wekel, Jitendra Malik, Silvio Savarese,
In ECCV 2016.
[see 3D Representation Website (Demo, Models, Data) | Visualization and Accuracy Analysis of TEST SET ]

Jun. 2016: I will be instructing CS331B: Representation Learning in Computer Vision course in autumn 2016 (along with Silvio Savarese).
[see Course Webpage | Stanford ExploreCourses ]

Jun. 2016: Along with A. Hakeem, L. Van Gool, M. Shah, and R. Szeliski, I published the book Large-Scale Visual Geo-Localization, with Springer.
[Front Matter | Cover | Springer Page]

Jun. 2016: I was selected as a recipeint of Institute for Computational and Mathematical Engineering seed grant award for our work on Generic Representation Learning. Thank you Stanford ICME and NVIDIA GPU Center of Excellence!

Mar. 2016: Two papers accepted to CVPR'16:
1) Structural-RNN: Deep Leaning on Spatio-Temporal Graphs [Best Student Paper Award, Oral]
2) 3D Semantic Parsing of Large-Scale Indoor Spaces [Oral]
[see the 3D PC Parser website]

Mar. 2016: I'll give an invited talk at Google Mountain View on Generic Representation Learning, on May 10th.

Dec. 2015: Invited talk at ICCV'15 Workshop Computer Vision for Converging Perspectives on Low-Level 3D.

Dec. 2015: I will be the tutorial and workshop chair of International Conference on 3DVision, 2016.

Aug. 2015: Two papers accepted to ICCV'15:
1) Unsupervised Semantic Parsing of Video Collections
2) Action Recognition by Hierarchical Mid-level Action Elements

Jun. 2015: Invited talk at CVPR15 3D from a Single Image workshop.

May 2015: Talk on June 11 in CVPR15's THUMOS Challenge workshop.

Dec. 2014: High resolution Google Street View dataset of our PAMI'14 paper, along with GPS coordinates and pre-extracted features, is made available to public: LINK.

Spet. 2014: Annotations of the test set of THUMOS'14 Challenge are released: LINK.

Jul. 2014: The details of the THUMOS'14 Challenge (in conjunction with ECCV'14), development kit, and data is available here.

Jun. 2014: Two papers accepted to ECCV'14:
1) DaMN - Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition
2) GIS-Assisted Object Detection and Geospatial Localization
One minute spotlight videos: [DaMN Classification! | GIS-Assisted Object Detection]

Apr. 2014: I will be giving a talk at Google Research on April 24th. Title: Geo-spatial Analysis of Consumer Images and Videos.

Apr. 2014: I will be giving a talk at UC Berkeley on April 23th. Title: Visual Geo-localization and Location-aware Image Analysis.

Apr. 2014: Two papers accepted to CVPR'14:
1) GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor
2) Video Classification using Semantic Concept Co-occurrences
One minute spotlight videos: [Tag Refinement | Video Classification]

Apr. 2014: I was selected as the recipient of Graduate Research Forum award for my research on "Location-aware Image Understanding". [Link]

Feb. 2014: The second THUMOS Challenge will take place in conjunction with ECCV 2014.

Dec. 2013: Paper accepted to TPAMI: "Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching using Generalized Graphs", in IEEE Transactions on Pattern Analysis and Machine Intelligence. [PDF]

Nov. 2013: The results of THUMOS'13 challenge are released here.

Sept. 2013: We were selected as the recipient of National Geospatial-Intelligence Agency NARP-SW best research poster award.

Sept. 2013: I'll give a talk at Cornell, Dept. of CS, on Location-aware Image Understanding and Large Scale Image and Video Geo-localization on Sept. 13. [Flyer]

Jul. 2013: I was selected as the recipient of UCF Research Excellence Award.

Jun. 2013: I'll give a talk at Georgia Tech, College of Computing, on Global Multi-object Tracking using Generalized Graphs on July 5.

Jun. 2013: Paper accepted to ACM MM'13: "Visual Business Recognition - A Multimodal Approach". [PDF| Video | Project Page]

Jun. 2013: I'm the program chair of the ICCV'13 international workshop on Action Recognition with Large Number of Classes (THUMOS). [Workshop Website | Call for Papers]

Mar. 2013: I'll give a talk at the University of Maryland-College Park, Department of ECE, on Large Scale Image and Video Geo-localization using Street View Imagery on March 26.

Feb. 2013: I'm in the program committee of the CVPR'13 international workshop on Visual Analysis and Geo-Localization of Large-Scale Imagery. [Workshop Website | Call for Papers]

Jun. 2012: Paper accepted to ECCV12: "GMCP-Tracker: Global Multi-object Tracking using Generalized Minimum Clique Graphs". [PDF | Project Page]

Feb. 2012: Paper accepted to CVPR12: "City Scale Geo-spatial Trajectory Estimation of a Moving Camera". [PDF | Project Page]

Dec. 2011: We participated in StreetView Recognition Challenge. [Report]

Jul. 2010: I won ECCV10 travel award for the paper "Accurate Image Localization Based on Google Maps Street View". [ECCV Travel Award]

Jun. 2010: Paper accepted to ECCV10: "Accurate Image Localization Based on Google Maps Street View". [PDF | Project Page]



Selected Publications:

19. Generic 3D Representations via Pose Estimation and Matching,
Amir R. Zamir, Pulkit Agrawal, Tilman Wekel, Jitendra Malik, Silvio Savarese,
In ECCV, 2016.
[PDF | 3DRepresentation website (Demo, Models, Data) ]

18. Structural-RNN: Deep Leaning on Spatio-Temporal Graphs, Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena,
In CVPR, 2016 - [Oral],[Best Student Paper Award]
[PDF | Project Page ]

17. 3D Semantic Parsing of Large-Scale Indoor Spaces , Iro Armeni, Ozan Sener, Amir R. Zamir, Martin Fischer, Silvio Savarese,
In CVPR, 2016 - [Oral] (acceptance rate ~3%)
[PDF | 3D PC Parser website (Demo, Code, Data)]

16. Book: Large-Scale Visual Geo-Localization,
Amir R. Zamir, Asaad Hakeem, Luc Van Gool, Mubarak Shah, Richard Szeliski,
Springer, 2016 [Front Matter | Cover | Springer Page]

15. Unsupervised Semantic Parsing of Video Collections, Ozan Sener, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena,
In Proceedings of International Conference on Computer Vision (ICCV), 2015 [PDF | Project Page ]

14. Action Recognition by Hierarchical Mid-level Action Elements, Tian Lan, Yuke Zhu, Amir R. Zamir, Silvio Savarese,
In Proceedings of International Conference on Computer Vision (ICCV), 2015 [PDF | Project Page | 1 min Summary]

13. DaMN - Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition, Rui Hou, Amir Roshan Zamir, Rahul Sukthankar, and Mubarak Shah,
In Proceedings of European Conference on Computer Vision (ECCV), 2014 [PDF | BibTeX | Project Page | 1 min Summary]
@inproceedings{DaMN_2014,
   Author = { Hou, R. and Roshan Zamir, A. and Sukthankar R. and Shah, M.},
   Booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
   Title = {{DaMN \96 Discriminative and Mutually Nearest}: Exploiting Pairwise Category Proximity for Video Action Recognition},
   Year = {2014}}

12. GIS-Assisted Object Detection and Geospatial Localization, Shervin Ardeshir, Amir Roshan Zamir and Mubarak Shah,
In Proceedings of European Conference on Computer Vision (ECCV), 2014 [PDF | BibTeX | Project Page | 1 min Summary]
@inproceedings{GIS_Assisted_ECCV14,
   Author = { Ardeshir, S. and Roshan Zamir, A. and Shah, M.},
   Booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
   Title = {{GIS}-Assisted Object Detection and Geospatial Localization},
   Year = {2014}}

11. GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor, Amir Roshan Zamir, Shervin Ardeshir and Mubarak Shah,
in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2014. [PDF | 1 min Summary | 20 min Presentation | BibTeX | Project Page]
@inproceedings{ZamirCVPR14,
   Author = {Roshan Zamir, A. and Ardeshir S. and Shah, M.},
   Booktitle = {27th IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
   Title = {GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor},
   Year = {2014}}

10. Video Classification using Semantic Concept Co-occurrences, Shayan Modiri, Amir Roshan Zamir and Mubarak Shah,
in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2014. [PDF | 1 min Summary | BibTeX | Project Page]
@inproceedings{GMCP_Classification,
   Author = {Modiri S., Roshan Zamir, A. and Shah, M.},
   Booktitle = {27th IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
   Title = {Video Classification using Semantic Concept Co-occurrences},
   Year = {2014}}

9. Invited Book Chapter: "Action Recognition in Realistic Sports Videos", Khurram Soomro and Amir Roshan Zamir,
in Computer Vision in Sports, Springer, 2014. [PDF | BibTeX ]
                @incollection{ActionRecognitionSports_2014Springer,
				  title={Action Recognition in Realistic Sports Videos},
				  author={Soomro, Khurram and Roshan Zamir, Amir},
				  booktitle={Computer Vision in Sports},
				  year={2014},
				  publisher={Springer}
				  }

8. Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching using Generalized Graphs, Amir Roshan Zamir and Mubarak Shah,
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014 [Preprint PDF | BibTeX | Web Page]
@null{6710175,
author={Zamir, A.R. and Shah, M.},
journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on},
title={Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching using Generalized Graphs},
year={2014},
volume={PP},
number={99},
pages={1-1},
keywords={Generalized Minimum Clique Problem (GMCP);Generalized Minimum Spanning Tree (GMST);Geo-location;feature correspondence;feature matching;generalized graphs;image localization;multiple nearest neighbor feature matching},
doi={10.1109/TPAMI.2014.2299799},
ISSN={0162-8828},}

7. Visual Business Recognition - A Multimodal Approach, Amir Roshan Zamir, Afshin Dehghan and Mubarak Shah,
In Proceeding of ACM International Conference on Multimedia (ACM MM), 2013 [PDF | Video | BibTeX | Project Page]
@inproceedings{ZamirACMMM13,
   Author = {Roshan Zamir, A. and Dehghan, A. and Shah M.},
   Booktitle = {Proceeding of ACM International Conference on Multimedia ({ACM MM})},
   Title = {{Visual Business Recognition} - A Multimodal Approach},
   Year = {2013}}

6. GMCP-Tracker: Global Multi-object Tracking using Generalized Minimum Clique Graphs, Amir Roshan Zamir, Afshin Dehghan and Mubarak Shah,
In Proceedings of European Conference on Computer Vision (ECCV), 2012 [PDF | Project Page | 20 min Presentation | BibTeX ]
@inproceedings{ZamirECCV12,
   Author = {Roshan Zamir, A. and Dehghan, A. and Shah, M.},
   Booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
   Title = {{GMCP-Tracker}: Global Multi-object Tracking using Generalized Minimum Clique Graphs},
   Year = {2012}}

5. City Scale Geo-spatial Trajectory Estimation of a Moving Camera, Gonzalo Vaca, Amir Roshan Zamir and Mubarak Shah,
in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2012 [PDF | BibTeX | Project Page]
@inproceedings{VacaZamir12,
   Author = {Vaca, G. and Roshan Zamir, A. and Shah, M.},
   Booktitle = {25th IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
   Title = {City Scale Geo-spatial Trajectory Estimation of a Moving Camera},
   Year = {2012}}

4. Accurate Image Localization Based on Google Maps Street View, Amir Roshan Zamir and Mubarak Shah,
In Proceedings of European Conference on Computer Vision (ECCV), 2010 [PDF | BibTeX | Project Page]
@inproceedings{Zamir10,
   Author = {Roshan Zamir, A., and Shah,  M.},
   Booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
   Title = {Accurate Image Localization Based on Google Maps Street View},
   Year = {2010}}

3. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild, Khurram Soomro, Amir Roshan Zamir and Mubarak Shah,
CRCV-TR-12-01, November, 2012. [PDF | BibTeX | Project Page | PDF2]
@inproceedings{UCF101,
   Author = {Soomro, k. and Roshan Zamir, A. and Shah, M.},
   Booktitle = {CRCV-TR-12-01},
   Title = {{UCF101}: A Dataset of 101 Human Actions Classes From Videos in The Wild},
   Year = {2012}}

2. Automatic Detection and Tracking of Pedestrians in Videos with Various Crowd Densities, Afshin Dehghan, Haroon Idrees, Amir Roshan Zamir and Mubarak Shah,
In Proceedings of PED, June 2012 [PDF | BibTeX | Project Page]
@incollection{
year={2014},
isbn={978-3-319-02446-2},
booktitle={Pedestrian and Evacuation Dynamics 2012},
editor={Weidmann, Ulrich and Kirsch, Uwe and Schreckenberg, Michael},
doi={10.1007/978-3-319-02447-9_1},
title={Automatic Detection and Tracking of Pedestrians in Videos with Various Crowd Densities},
url={http://dx.doi.org/10.1007/978-3-319-02447-9_1},
publisher={Springer International Publishing},
keywords={Human detection; Tracking; Data association; Crowd density; Crowd analysis; Automatic surveillance},
author={Dehghan, Afshin and Idrees, Haroon and Zamir, AmirRoshan and Shah, Mubarak},
pages={3-19},
language={English}}

1. Street View Challenge: Identification of Commercial Entities in Street View Imagery, Amir Roshan Zamir, Alexander Darino, Ryan Patrick and Mubarak Shah,
In Proceedings of ICMLA, 2011

Visual Geo-localization and Location-aware Image Understanding, Amir Roshan Zamir, Ph.D. Dissertation, 2014. [PDF | BibTeX]
@inproceedings{ZamirThesis2014,
   Author = {Roshan Zamir, A.},
   Booktitle = {Ph.D. Dissertation, University of Central Florida},
   Title = {{Visual Geo-localization and Location-aware Image Understanding}},
   Year = {2014}}

Contact

Email:
zamir@cs.stanford.edu

Address:
Gates Computer Science, #133
353 Serra Mall
Stanford, CA 94305




Press Coverage