no code implementations • 21 Mar 2023 • Khawar Islam
In the last couple of years, deep learning on video re-ID has continuously achieved surprising results on public datasets, with various approaches being developed to handle diverse problems in video re-ID.
1 code implementation • 21 Oct 2022 • Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood
A novel Face Pyramid Vision Transformer (FPVT) is proposed to learn a discriminative multi-scale facial representations for face recognition and verification.
no code implementations • 3 Mar 2022 • Khawar Islam
Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs).
2 code implementations • IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021 • Khawar Islam, L. Minh Dang, Sujin Lee, Hyeonjoon Moon
Image compression is a method to remove spatial redundancy between adjacent pixels and reconstruct a high-quality image.
no code implementations • 12 Jul 2020 • Khawar Islam, Uzma Afzal
Passengers still face bus waiting and seat unavailability issues which have adverse effects on traffic management and controlling authority.
no code implementations • Image and Vision Computing 2020 • Khawar Islam
Deep learning shows incredible performance in person (re-ID) and search.