Murtaza Taj

Murtaza Taj earned his Ph.D. and M.Sc. degrees in electronic engineering and computer science from the Queen Mary University of London (QMUL), United Kingdom, in 2009 and 2005, respectively. Currently, he is an Associate Professor at the Lahore University of Management Sciences (LUMS), Syed Babar Ali School of Science and Engineering, Pakistan. He also served as adjunct faculty at the Ontario Tech University, Canada. His research interest lies in the area of Computer Vision, Graphics and Image Processing. In particular, he is interested in detection and tracking of object in 2D and 3D scenes. He also works in the area of remote sensing on problems related to image matching, retrieval and extraction of socio-economic indicators. At LUMS he is a director of Computer Vision and Graphics Lab (a research group within LUMS computer science department) and a former director of Technology for People Initiative (TPI) (a research and development group at LUMS that develop solution to leverage technology to catalyze development in the public sector and improve data accessibility to facilitate good governance). He has served as a reviewer for for several international conference and journals including the IEEE Transaction on Image Processing, IEEE Signal Processing Letters, IEEE International Conference on Image Processing and IEEE Transactions on Circuits and Systems for Video Technology .

Teaching

• Fall 2012 – 2019: CS452 Computer Graphics
• Spring 2016 – 2019: CS436/CS5310 Computer Vision Fundamentals
• Spring 2019: CS437/CS5317 Deep Learning
• Spring 2012 – 2018: CS674/EE512 Digital Image Processing

Journals Papers

1. M. Tharani, N. Khurshid, and M. Taj, “A Residual-Dyad Encoder Discriminating Network for Remote Sensing Image Matching”,  IEEE Geosciences and Remote Sensing Letters, 2019 (accepted)

2. W. Abbas, M. F. Khan. M. Taj and A. Mahmood, “Simultaneous Multi-Task Learning (SCMTL) of Statistically Correlated Parameters Using Deep Learning for Autonomous Driving”, IEEE Transactions on Intelligent Transportation Systems, 2019 (submitted)

3. M. Taj and A. Cavallaro, “Distributed and decentralized multi-camera tracking: a survey”, in IEEE Signal Processing Magazine, Special issue: Distributed Image Processing and Communications, vol. 28, issue 3, pg. 46-58, May 2011.

4. F. Daniyal, M. Taj and A. Cavallaro, “Content and task-based view selection from multiple video streams”, in Data semantics from multi-media systems, Special issue: Semantic Multimedia, vol. 46, no. 2-3, pp. 235-258, 2009.

5. H. Zhou, M. Taj and A. Cavallaro, “Target detection and tracking with heterogeneous sensors”, in IEEE Journal of Selected Topics in Signal Processing, vol. 2, no. 4, pp. 503–513, August 2008.

6. E. Maggio, M. Taj and A. Cavallaro, “Efficient multi-target visual tracking using random finite sets”, in IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 8, pp. 1016–1027, August  2008.

7. S. Karlsson, M. Taj and A. Cavallaro, “Detection and tracking of humans and faces”, in EURASIP Journal on Image and Video Processing, vol. 2008, no. 1, 2008.

Patents

1. Method and apparatus for collaborative digital imaging, A. Zaheer, A. Rehan, M. Taj, A. Rehman US Patent App. 14/219,967, 2014, Pakistan Provisional application no. 20/2012, filed Jan 13, 2014.

2. Dynamically targeted ad augmentation in video, A. Zaheer, A. Rehan, M. Taj, A. Rehman, F. Hassan, US Patent App. 14/829,551, 2015.

Conference Papers

1. N. Khurshid, T. H. Butt, M. Tharani and M. Taj, “Cross-View Image Retrieval – Ground to Aerial Image Retrieval through Deep Learning”, In Proc. of 26th Int. Conf. on Neural Information Processing of the Asia Pacific Neural Network Society, Sydney, AU, 12-15 Dec 2019.

2. W. Abbas, M. H. Shakeel, N. Khurshid and M. Taj, “Patch-based Generative Adversarial Network Towards Retinal Vessel Segmentation”, In Proc. of 26th Int. Conf. on Neural Information Processing of the Asia Pacific Neural Network Society, Sydney, AU, 12-15 Dec 2019.

3. U. Nazir, I. Naqvi and M. Taj, “Accurate Localization Algorithm in Wireless Sensor Networks in the Presence of Cross Technology Interference”, In Proc. of 26th Int. Conf. on Neural Information Processing of the Asia Pacific Neural Network Society, Sydney, AU, 12-15 Dec 2019.

4. M. Tharani, T. Mukhtar, N. Khurshid and M. Taj, “Dimensionality Reduction Using Discriminative Autoencoders for Remote Sensing Image Retrieval” In Proc. of 20th Int. Conf. on Image Analysis and Processing, Trento, Italy, 9–13 Sep, 2019.

5. U. Nazir, N. Khurshid, M. A. Bhimra, M. Taj, “Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in  South Asia”, In Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recognition (workshop), Long Beach, CA, USA, June 16-21, 2019

6. M.A. Bhimra, U. Nasir and M. Taj, “Using 3D Residual Network For Spatio-Temporal Analysis of Remote Sensing Data”, in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Brighton, UK, 12-17 May 2019.

7. O. Hassaan, A. Shamail, Z. Butt and M. Taj, “Point Cloud Segmentation Using Hierarchical Tree For Architectural Models”, in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Brighton, UK, 12-17 May 2019.

8. W. Abbas and M. Taj, “Adaptively Weighted Multi-Task Learning Using Inverse Validation Loss”, in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Brighton, UK, 12-17 May 2019. 

9. O. Hassaan, A. Shamail, Z. Butt and M. Taj, “Outdoor scene segmentation and reconstruction using LiDAR data”, in 25th Pacific Conference on Computer Graphics and Applications (Pacific Graphics), Taipei, Taiwan, during October 16-19, 2017.

10. U. Shafiq, M. Taj and A. Mohsen, “More for less: Insights into convolutional nets for 3D Point Cloud Recognition”, in Proc. of IEEE Int. Conf. on Image Processing, Beijing, CN, 17-20 September 2017.

11. A. K. Nasir, M. Taj and M. F. Khan, “Evaluation of Microsoft Kinect Sensor for Plant Health Monitoring”, IFAC Conf.  on Sensing, Control and Automation Technologies for Agriculture AGRICONTROL Seattle, WA, USA, Aug 2016.

12. R. Bajwa, S. R. Gilani and M. Taj, “3D Architectural Modeling: Coarse-to-fine model fitting on point cloud“, Computer Graphics International, Crete, GR, 2016.

13. A. Abdullah, R. Bajwa, S. R. Gilani, Z. Agha, S. B. Boor, M. Taj and S. A. Khan, “3D Architectural Modeling: Efficient RANSAC for n-gonal primitive fitting”, Eurographics, Zurich, CH, 2015.

14. A. Inam, M. Taj, S. Khan, U. Nadeem, Z. Mansoor, and Z. K. Bhatti, “Leveraging Smartphones to Monitor Attendance in Public Facilities”. In Proc. of the ACM Annual Symposium on Computing for Development, NY, USA, 2015.

15. A. Hassan and M. Taj, “2D articulated human pose tracking: A hybrid approach”, in Proc. of IEEE Int. Conf. on Image Processing, Paris, FR, 27 October 2014.

16. A. Rafay Khalid, A. Hassan and M. Taj, “Efficient 2D human pose estimation using mean-shift”, in Proc. of IEEE Int. Conf. on Image Processing, Paris, FR, 27 October 2014.

17. M. Taj, and A. Cavallaro, “Interaction recognition in wide areas using audiovisual sensors”, in Proc. of IEEE Int. Conf. on Image Processing, Orlando, FL, USA, 30 September 2012.

18. M. Taj and A. Cavallaro, “Multi-camera track-before-detect”, in ACM/IEEE Int. Conf. on Dist. Smart Cameras, Como, IT, 30 August–02 September 2009.

19. M. Taj and A. Cavallaro, “Audio-assisted trajectory estimation in non-overlapping multi-camera networks”, in IEEE  Int. Conf. on Acoustics, Speech, and Signal Processing, Taipei, TW, 19–24 April 2009.

20. F. Daniyal, M. Taj and A. Cavallaro, “Content-aware ranking of video segments”, in ACM/IEEE Int. Conf. on Dist. Smart Cameras, Stanford, CA, USA, 07–11 September 2008.

21. M. Taj and A. Cavallaro, “Object and scene-centric activity detection using state occupancy duration modeling”, in IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, Santa Fe, NM, USA, 1–3 September 2008.

22. G. Kayumbi, P. Mazzeo, P. Spagnolo, M. Taj and A. Cavallaro, “Distributed visual sensing for virtual top-view trajectory generation in football videos”, in Proc. of ACM Int. Conf. on Image and Video Retrieval, Niagara Falls, CA, 7–9 July 2008.

23. H. Zhou, M. Taj, and A. Cavallaro, “Audiovisual tracking using STAC sensors”, in ACM/IEEE Int. Conf. on Dist. Smart Cameras, Vienna, AT, 25–28 September 2007.

24. M. Taj and A. Cavallaro, “Multi-camera scene analysis using an object-centric continuous distribution hidden Markov model”, in Proc. of IEEE Int. Conf. on Image Processing, San Antonio, TX, USA, 16–19 September 2007.

25. M. Bregonzio, M. Taj, and A. Cavallaro, “Multi-modal particle filtering tracking using appearance, motion and audio likelihoods”, in Proc. of IEEE Int. Conf. on Image Processing, San Antonio, TX, USA, 16–19 September 2007.

26. M. Taj, E. Maggio, and A. Cavallaro, “Objective evaluation of pedestrian and vehicle tracking on the CLEAR surveillance dataset”, in Classification of Events, Activities and Relationships Workshop, Springer LNCS 4625, Baltimore, MD, USA, 8–11 May 2007.

27. N. Anjum, M. Taj, and A. Cavallaro, “Relative position estimation of non-overlapping cameras”, in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Honolulu, HI, USA, 15–20 April 2007.

28. A. Cavallaro, R. Chandrasekera, and M. Taj, “Hands-on experience in image processing: the automated lecture cameraman”, in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Proc., Honolulu, USA, 15–20 April 2007.

29. M. Taj, E. Maggio, and A. Cavallaro, “Multi-feature graph-based object tracking”, in Classification of Events, Activities and Relationships Workshop, Springer LNCS 4122, pp. 190–199, Southampton, UK, 6–7 April 2006.

Book Chapters

1. M. Taj, A. Hassan and A. R. Khalid. “2D Human Pose Estimation and Tracking in Non-overlapping Cameras“, Human Behavior Understanding in Networked Sensing, Springer Verlag GmbH, 2014.

2. M. Taj and A. Cavallaro. “Simultaneous Detection and Tracking with Multiple Cameras“, Computer Vision and Machine Learning for Image and Video Analysis, Springer Verlag GmbH, 2012.

3. M. Taj and A. Cavallaro. “Multi-view multi-object detection and tracking”, Computer Vision: Detection, Recognition and Reconstruction, pages 263-280, chapter 8, Springer Verlag GmbH, July 2010.

4. M. Taj and A. Cavallaro. “Recognizing Interactions in Video“. Intelligent Multimedia Analysis for Security Applications, pages 29-57, chapter 2, Springer Verlag GmbH, April 2010.