Paper accepted at BMVC 2021
Our paper titled “Teacher-Class Network: A Neural Network Compression Mechanism” accepted at BMVC 2021.
This work was an outcome of MS Thesis by Shaiq Munir
More info: Click here
Our paper titled “Teacher-Class Network: A Neural Network Compression Mechanism” accepted at BMVC 2021.
This work was an outcome of MS Thesis by Shaiq Munir
More info: Click here
Two of our papers accepted at ICIP 2021 1. “Spatio-Temporal Crop Classification On Volumetric Data”, More info: Click here 2. “Comprehensive Online Network Pruning via Learnable Scaling Factors”, More info: Click here
Our NRPU proposal on “Analyzing and Forecasting Socio-economic development using Satellite Imagery of Districts of Punjab” has been approved for funding by HEC. Acceptance rate among CS & IT related proposals in NRPU call for 2017-18 was only 3% and the overall acceptance rate was only 28%. Our is amongĀ 1104 accepted proposals out of total…
Three papers have been accepted atĀ “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…
Our paper titled “Camera Calibration through Camera Projection Loss” accepted at ICASSP 2022. This work was an outcome of MS Thesis by Talha Hanif Butt More info: Click here
Our paper titled “Stereoential Net: Deep Network for Learning Building Height Using Stereo Imagery” accepted at ICONIP 2023. This work was an outcome of PhD Thesis by Sana Jabbar More info: Click here
Spatio-Temporal Analysis of Landuse-Landcover Change Using Satellite Imagery Thursday 28 Feb, 2019 at 10:00 am in Smart Room 9-105 SBASSE. Abstract We propose an approach to recognize large scale, rapid spatio-temporal analysis of satellite remote sensing data. This technique can be used to measure longitudinal changes and yearly changes. Most of the existing methods either…