no code implementations • 14 May 2023 • Maniratnam Mandal, Suna Gao
Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications.
no code implementations • 14 May 2023 • Maniratnam Mandal, Imran Khan
Compressing deep networks is highly desirable for practical use-cases in computer vision applications.
1 code implementation • 14 May 2023 • Maniratnam Mandal, Deepti Ghadiyaram, Danna Gurari, Alan C. Bovik
The photographs taken by visually impaired users often suffer from one or both of two kinds of quality issues: technical quality (distortions), and semantic quality, such as framing and aesthetic composition.
no code implementations • 14 May 2023 • Maniratnam Mandal
An approximate orthographic capture has been attributed to a small field of view and a closed form relationship has been derived for evaluating local orthographic capture region which varies depending on the point of capture on the surface.
no code implementations • 14 May 2023 • Maniratnam Mandal, Venkatesh K. Subramanian
Surveillance and surveying are two important applications of empirical research.
1 code implementation • CVPR 2021 • Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, Alan Bovik
No-reference (NR) perceptual video quality assessment (VQA) is a complex, unsolved, and important problem to social and streaming media applications.
Ranked #10 on Video Quality Assessment on LIVE-FB LSVQ (using extra training data)