no code implementations • 1 Mar 2024 • Goirik Chakrabarty, Aditya Chandrasekar, Ramya Hebbalaguppe, Prathosh AP
Our experiments against existing state-of-the-art methods demonstrate the improved effectiveness of our approach in terms of both image editing quality and inference speed.
1 code implementation • CVPR 2023 • Shubh Maheshwari, Rahul Narain, Ramya Hebbalaguppe
Animating a virtual character based on a real performance of an actor is a challenging task that currently requires expensive motion capture setups and additional effort by expert animators, rendering it accessible only to large production houses.
no code implementations • 20 Dec 2022 • Ramya Hebbalaguppe, Rishabh Patra, Tirtharaj Dash, Gautam Shroff, Lovekesh Vig
Contemporary model calibration techniques mitigate the problem of overconfident predictions by pushing down the confidence of the winning class while increasing the confidence of the remaining classes across all test samples.
1 code implementation • CVPR 2022 • Ramya Hebbalaguppe, Jatin Prakash, Neelabh Madan, Chetan Arora
We show that training with MDCA leads to better-calibrated models in terms of Expected Calibration Error ( ECE ), and Static Calibration Error ( SCE ) on image classification, and segmentation tasks.
no code implementations • 31 Oct 2021 • Mrinal Rawat, Ramya Hebbalaguppe, Lovekesh Vig
While Out-of-distribution (OOD) detection has been well explored in computer vision, there have been relatively few prior attempts in OOD detection for NLP classification.
no code implementations • 4 Nov 2019 • Varun Jain, Shivam Aggarwal, Suril Mehta, Ramya Hebbalaguppe
The goal of this work is to introduce a framework capable of generating photo-realistic videos that have labelled hand bounding box and fingertip that can help in designing, training, and benchmarking models for hand-gesture recognition in AR/VR applications.
no code implementations • 26 Oct 2019 • Srinidhi Hegde, Ranjitha Prasad, Ramya Hebbalaguppe, Vishwajith Kumar
We demonstrate that the marriage of KD and the VI techniques inherits compression properties from the KD framework, and enhances levels of sparsity from the VI approach, with minimal compromise in the model accuracy.
no code implementations • 19 Apr 2019 • Varun Jain, Gaurav Garg, Ramakrishna Perla, Ramya Hebbalaguppe
The overall framework works in real-time on mobile devices and achieves a classification accuracy of 80% on EgoGestAR video dataset with an average latency of only 0. 12 s.
no code implementations • 12 Apr 2019 • Varun Jain, Ramya Hebbalaguppe
Hand gestures are an intuitive, socially acceptable, and a non-intrusive interaction modality in Mixed Reality (MR) and smartphone based applications.
Human-Computer Interaction