no code implementations • 5 May 2023 • Ekta Prashnani, Koki Nagano, Shalini De Mello, David Luebke, Orazio Gallo
This allows us to link the synthetic video to the identity driving the expressions in the video, regardless of the facial appearance shown.
no code implementations • 17 Nov 2022 • Ekta Prashnani, Michael Goebel, B. S. Manjunath
Overall, with PhaseForensics, we show improved distortion and adversarial robustness, and state-of-the-art cross-dataset generalization, with 91. 2% video-level AUC on the challenging CelebDFv2 (a recent state-of-the-art compares at 86. 9%).
1 code implementation • 7 Oct 2022 • Satish Kumar, ASM Iftekhar, Ekta Prashnani, B. S. Manjunath
This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings.
Ranked #1 on Zero-Shot Learning on MIT-States
1 code implementation • 16 Apr 2021 • Ekta Prashnani, Orazio Gallo, Joohwan Kim, Josef Spjut, Pradeep Sen, Iuri Frosio
We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene.
1 code implementation • CVPR 2018 • Ekta Prashnani, Hong Cai, Yasamin Mostofi, Pradeep Sen
Our key observation is that our trained network can then be used separately with only one distorted image and a reference to predict its perceptual error, without ever being trained on explicit human perceptual-error labels.
Ranked #1 on Video Quality Assessment on MSU SR-QA Dataset