Hi!
I am working as a research engineer in R&D team at Keeptruckin, a San Francisco based startup helping trucking companies manage their fleets. My research interest lies in solving practical problems entailing Computer Vision, Machine Learning and Deep Learning, specifically on the problems related to object detection, segmentation and affective computing. My current research is focused on building and training a unified deep architecture for vehicle and lane detection tasks by employing cost-sensitive multi-task learning approach.
Earlier, I was a research associate at Intelligent Machines Lab at Information Technology University, Pakistan (ITU) where I worked with Dr. Mohsen Ali on affective analysis of images and oriented object detection using Convolutional Neural Networks. Related to affective computing, I have two paper publications in WACV 2017 and BMVC 2017. My work on oriented object detection is also under review at IEEE Transactions on Image Processing (TIP).
I am a 2016 Masters graduate from Information Technology University where I was advised by Dr. Mohsen Ali. My MS thesis was on problem of affective understanding of images i.e., analyzing underlying stimuli in images responsible for the induced emotion in viewers. Apart from research, I have also been a Teaching Assistant for the graduate level courses of 'Computer Vision' and ‘Deep Learning’ at ITU.
Previously, I worked as a research fellow at Center for Language Engineering where I conducted extensive research on speech recognition and developed speech recognition systems and voice activity detectors for Mobile based Urdu Spoken Dialog system. I completed my undergraduate degree in Computer Engineering from University of Engineering and Technology in 2013 under advisement of Dr. Tania Habib. In my final year project there, I worked on the problem of speech recognition for Urdu Language.
I am working as a research engineer in R&D team at Keeptruckin, a San Francisco based startup helping trucking companies manage their fleets. My research interest lies in solving practical problems entailing Computer Vision, Machine Learning and Deep Learning, specifically on the problems related to object detection, segmentation and affective computing. My current research is focused on building and training a unified deep architecture for vehicle and lane detection tasks by employing cost-sensitive multi-task learning approach.
Earlier, I was a research associate at Intelligent Machines Lab at Information Technology University, Pakistan (ITU) where I worked with Dr. Mohsen Ali on affective analysis of images and oriented object detection using Convolutional Neural Networks. Related to affective computing, I have two paper publications in WACV 2017 and BMVC 2017. My work on oriented object detection is also under review at IEEE Transactions on Image Processing (TIP).
I am a 2016 Masters graduate from Information Technology University where I was advised by Dr. Mohsen Ali. My MS thesis was on problem of affective understanding of images i.e., analyzing underlying stimuli in images responsible for the induced emotion in viewers. Apart from research, I have also been a Teaching Assistant for the graduate level courses of 'Computer Vision' and ‘Deep Learning’ at ITU.
Previously, I worked as a research fellow at Center for Language Engineering where I conducted extensive research on speech recognition and developed speech recognition systems and voice activity detectors for Mobile based Urdu Spoken Dialog system. I completed my undergraduate degree in Computer Engineering from University of Engineering and Technology in 2013 under advisement of Dr. Tania Habib. In my final year project there, I worked on the problem of speech recognition for Urdu Language.