NCA2021 – Statistically Correlated Multi-task Learning for  Autonomous Driving
|

NCA2021 – Statistically Correlated Multi-task Learning for Autonomous Driving

Waseem Abbas, M. Fakhir Khan, Murtaza Taj, and Arif Mahmood Abstract Autonomous driving research is an emerging domain in computer vision and machine learning areas. Most existing methods perform Single Task Learning (STL) from one or more images while Multi-Task Learning (MTL) is more efficient due to the leverage of shared information between different tasks….

CVPRW2019 – Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in  South Asia
|

CVPRW2019 – Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in South Asia

Usman Nazir, Numan Khurshid, Muhammad Ahmed Bhimra, Murtaza Taj International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, June 16-21, 2019 Abstract This paper proposes to employ a Inception-ResNet inspired deep learning architecture called Tiny-Inception-ResNet-v2 to eliminate bonded labor by identifying brick kilns within “Brick-Kiln-Belt” of South Asia. The framework is developed…

ICASSP 2019 – Using 3D Residual Network For Spatio-Temporal Analysis Of Remote Sensing Data
|

ICASSP 2019 – Using 3D Residual Network For Spatio-Temporal Analysis Of Remote Sensing Data

Muhammad Ahmed Bhimra, Usman Nazir, Murtaza Taj International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 12-17, 2019 Abstract In this paper, we propose an approach to recognize spatio-temporal changes from remote sensing data. Instead of performing independent analysis on each instance of satellite imagery, we proposed a 3D Convolutional Neural Network…

ICASSP 2019 – Adaptively Weighted Multi-Task Learning Using Inverse Validation Loss
|

ICASSP 2019 – Adaptively Weighted Multi-Task Learning Using Inverse Validation Loss

Waseem Abbas and Murtaza Taj International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 12-17, 2019 Abstract Multi-task learning aims to enhance the performance of a model by inductive transfer of information among tasks. However, joint optimization of multiple tasks is challenging due to unbalanced data ranges and variations in task difficulties…

ICASSP 2019- Point Cloud Segmentation Using Hierarchical Tree for Architectural Models
|

ICASSP 2019- Point Cloud Segmentation Using Hierarchical Tree for Architectural Models

Omair Hassaan, Abeera Shamail, Zain Butt, Murtaza Taj International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 12-17, 2019 Abstract Over the past few years, gathering massive volume of 3D data has become straightforward due to the proliferation of laser scanners and acquisition devices. Segmentation of such large data into meaningful segments,…

PacificGraphics 2017 – Outdoor scene segmentation and reconstruction using LiDAR data
|

PacificGraphics 2017 – Outdoor scene segmentation and reconstruction using LiDAR data

Omair Hassaan, Abeera Shamail, Zain Butt, Murtaza Taj The 25th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2017), Taipei, Taiwan, Oct 16 – 19, 2017 Abstract Recent advancements in 3D scanning technologies have paved way for generation of highly accurate 3D scenes in the form of point cloud data. For the segmentation and…

CGI 2016 – Coarse-to-fine model fitting on point cloud
|

CGI 2016 – Coarse-to-fine model fitting on point cloud

Reema Bajwa, Syed Rizwan Gilani, Murtaza Taj Short Paper Proceedings of the 33rd Computer Graphics International, Heraklion, Greece, June 28 – July 1, 2016 Abstract We present a coarse-to-fine model fitting approach that automatically generates a detailed CAD like model from a point cloud. We first developed a library of detailed parametric models for each…

Eurographics 2015 – Efficient RANSAC for n-gonal Primitive Fitting
|

Eurographics 2015 – Efficient RANSAC for n-gonal Primitive Fitting

Ahsan Abdullah, Reema Bajwa, Syed Rizwan Gilani, Zuha Agha, Saeed Boor Boor, Murtaza Taj, Sohaib Ahmed Khan The 36th Annual Conference of the European Association for Computer Graphics, 2015 Kongresshaus in Zürich, Switzerland, 4th – 8th May, 2015 Abstract We present a modeling approach to automatically fit 3D primitives to point clouds in order to…

ICIP 2012 – Interaction Recognition in Wide Areas Using Audiovisual Sensors
|

ICIP 2012 – Interaction Recognition in Wide Areas Using Audiovisual Sensors

Murtaza Taj, Andrea Cavallaro International Conference on Image Processing, ICIP 2012 Abstract We present an event recognition framework to detect interactions among objects, for example people, using a network of cameras and associated microphone pairs. The complementarity of the video and audio modalities is exploited to cover wide areas. In particular, object movements in portions of the scene that…