1 code implementation • 13 Feb 2024 • Muhammad Waleed, Abdul Rauf, Murtaza Taj
The process of camera calibration involves estimating the intrinsic and extrinsic parameters, which are essential for accurately performing tasks such as 3D reconstruction, object tracking and augmented reality.
no code implementations • 4 Oct 2023 • Osama Ahmad, Omer Abdul Jalil, Usman Nazir, Murtaza Taj
In recent work, [1] introduced the concept of using a Block Adjacency Matrix (BA) for the representation of spatio-temporal data.
no code implementations • 21 Mar 2023 • Usman Nazir, Murtaza Taj, Momin Uppal, Sara Khalid
Industrial air pollution has a direct health impact and is a major contributor to climate change.
2 code implementations • 22 Nov 2022 • Talha Hanif Butt, Murtaza Taj
As far as we are aware, our approach is the first one that uses an approach to multi-task learning that includes mathematical formulas in a framework for learning to estimate camera parameters to predict both the extrinsic and intrinsic parameters jointly.
no code implementations • 16 Oct 2021 • Shehryar Malik, Muhammad Umair Haider, Omer Iqbal, Murtaza Taj
In this work, we propose a general methodology for pruning neural networks.
2 code implementations • 7 Oct 2021 • Talha Hanif Butt, Murtaza Taj
To the best of our knowledge, ours is the first method to jointly estimate both the intrinsic and extrinsic parameters via a multi-task learning methodology that combines analytical equations in learning framework for the estimation of camera parameters.
no code implementations • 11 Jun 2021 • Usman Nazir, He Wang, Murtaza Taj
In this survey paper, we analyze image based graph neural networks and propose a three-step classification approach.
no code implementations • 18 Mar 2021 • Muhammad Usman Qadeer, Salar Saeed, Murtaza Taj, Abubakr Muhammad
Our combined strategy outperforms both classical as well as recent DCNN based methods in terms of classification accuracy by 2% while maintaining a minimum number of parameters and the lowest inference time.
no code implementations • 6 Oct 2020 • Muhammad Umair Haider, Murtaza Taj
One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements.
no code implementations • 9 Jul 2020 • Mohbat Tharani, Abdul Wahab Amin, Mohammad Maaz, Murtaza Taj
This paper proposes a method for the detection of visible trash floating on the water surface of the canals in urban areas.
no code implementations • 2 May 2020 • Numan Khurshid, Talha Hanif, Mohbat Tharani, Murtaza Taj
To train, compare, and evaluate the performance of cross-view image retrieval, we present a new 6 class cross-view image dataset termed as CrossViewRet which comprises of images including freeway, mountain, palace, river, ship, and stadium with 700 high-resolution dual-view images for each class.
1 code implementation • 9 Apr 2020 • M. Hammad Masood, Habiba Saim, Murtaza Taj, Mian M. Awais
Many existing techniques provide automatic estimation of crop damage due to various diseases.
2 code implementations • 7 Apr 2020 • Shaiq Munir Malik, Muhammad Umair Haider, Mohbat Tharani, Musab Rasheed, Murtaza Taj
To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network.
no code implementations • 22 Dec 2019 • Waseem Abbas, Muhammad Haroon Shakeel, Numan Khurshid, Murtaza Taj
Retinal blood vessels are considered to be the reliable diagnostic biomarkers of ophthalmologic and diabetic retinopathy.
no code implementations • 25 Sep 2019 • Ammar Ahmad, Oneeb Babar, Murtaza Taj
As an example we reuse these smaller networks to develop larger and a more complex network to solve n-digit multiplication, n-digit division, and cross product.
no code implementations • 12 Jul 2019 • Usman Nazir, Numan Khurshid, Muhammad Ahmed Bhimra, Murtaza Taj
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.
no code implementations • 15 Oct 2018 • Mohbat Tharani, Numan Khurshid, Murtaza Taj
Results demonstrate that our technique supersedes the state-of-the-art methods used for unsupervised image matching with mean average precision (mAP) of 81%, and image retrieval with an overall improvement in mAP score of about 12%.
no code implementations • 22 Jun 2018 • Omair Hassaan, Abeera Shamail, Zain Butt, Murtaza Taj
Recent developments in the 3D scanning technologies have made the generation of highly accurate 3D point clouds relatively easy but the segmentation of these point clouds remains a challenging area.