2 code implementations • 28 Feb 2021 • Muhammad Umar Karim Khan
We apply our method to both structure-from-motion and stereo depth estimation.
no code implementations • 23 Jun 2020 • Saad Imran, Muhammad Umar Karim Khan, Sikander Bin Mukarram, Chong-Min Kyung
Small-baseline stereo pairs provide small depth range but handle occlusions well.
Monocular Depth Estimation Unsupervised Monocular Depth Estimation
no code implementations • 17 Jun 2020 • Rabia Ali, Muhammad Umar Karim Khan, Chong Min Kyung
The best performing image-based self-supervised representation learning method is then used for video anomaly detection to see the importance of spatial features in visual anomaly detection in videos.
no code implementations • 16 Jun 2020 • Muhammad Umar Karim Khan, Mishal Fatima, Chong-Min Kyung
With a single epoch of training, our method improves the AUC by 8. 03% compared to the convolutional LSTM-based approach.
no code implementations • 16 Jun 2020 • Mishal Fatima, Muhammad Umar Karim Khan, Chong Min Kyung
Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance.
no code implementations • 16 Jun 2020 • Muhammad Suhaib Tanveer, Muhammad Umar Karim Khan, Chong-Min Kyung
Our method offers a good trade-off between the number of parameters and classification accuracy.
Ranked #1 on Image Classification on Fashion-MNIST
1 code implementation • CVPR 2019 • Hyeji Kim, Muhammad Umar Karim Khan, Chong-Min Kyung
The better accuracy and complexity compromise, as well as the extremely fast speed of our method makes it suitable for neural network compression.