Tag: Featured
Camera Calibration through Camera Projection Loss
Talha Hanif Butt, Murtaza Taj Abstract: Camera calibration is a necessity in various tasks including 3D reconstruction, hand-eye coordination for a robotic interaction, autonomous driving, etc. In this work we propose a novel method to predict extrinsic (baseline, pitch, and translation), intrinsic (focal length and principal point offset) parameters using an image pair. Unlike existing […]
Teacher-Class Network: A Neural Network Compression Mechanism
Shaiq Munir Malik, Fnu Mohbat, Muhammad Umair Haider, Muhammad Musab Rasheed and Murtaza Taj Abstract: To reduce the overwhelming size of Deep Neural Networks, teacher-student techniques aim to transfer knowledge from a complex teacher network to a simple student network. We instead propose a novel method called the teacher-class network consisting of a single teacher […]
3xPapers accepted at ICONIP 2019
Three papers have been accepted at “International Conference on Neural Information Processing – 19 (ICONIP-19)”. This conference is ranked A by the CORE rating measure and is going to be held from 12th to 15th December 2019 in Sydney, Australia. “Cross-view Image Retrieval – Ground to Aerial Image Retrieval through Deep Learning” “Patch-based Generative Adversarial Network […]
ICIAP 2019 – Dimensionality Reduction Using Discriminative Autoencoders for Remote Sensing Image Retrieval
Mohbat, Tooba Mukhtar, Numan Khurshid, and Murtaza Taj International Conference on Image Analysis and Processing (ICAIP), Trento, Itlay, September 9-13, 2019 Abstract Advancements in deep learning techniques caused a paradigm shift in feature extraction for image perception from handcrafted methods to deep methods. However, these deep features if learned through unsupervised methods bear large memory […]
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 […]
3xPapers accepted at ICASSP 2019
“Using 3D Residual Network For Spatio-Temporal Analysis Of Remote Sensing Data”, “Adaptively Weighted Multi-Task Learning Using Inverse Validation Loss” and “Point Cloud Segmentation Using Hierarchical Tree for Architectural Models” have been accepted in “IEEE International Conference on Acoustic Speech and Signal Processing. This conference is going to be held from 12th to 17th May 2019 […]
Ph.D. Thesis Defense: Ijaz Akhter
Tuesday 20 Nov, 2012 at 5:50 pm in Smart Room 9-105 SSE. Abstract A variety of dynamic objects, such as faces, bodies, and cloth, are represented in computer vision and computer graphics as a collection of moving spatial landmarks. A number of tasks are performed on this type of data such as character animation, motion […]
ECCV 2012 – Shape from Angle Regularity
This paper presents a new Shape-from-X method which is applicable for typical man-made environments which have a profusion of orthogonal lines. A full single-view reconstruction method for multi-planar man-made scenes is demonstrated. Authors: Aamer Zaheer, Maheen Rashid, Sohaib Khan, ECCV 2012.
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 […]
ToG 2012 – Bilinear Spatiotemporal Basis Models
Our paper in ACM Transactions on Graphics April 2012 presents a fundamentally new way to model time-varying point clouds, that dramatically reduces processing times for common graphics pipeline tasks such as labeling, gap-filling, denoising, and motion touch-up. This is joint work with Carnegie Mellon University and Disney Research Pittsburgh, and has been presented at Siggraph 2012.
