3 papers
cs.RO2025
Explicit Memory through Online 3D Gaussian Splatting Improves Class-Agnostic Video Segmentation
Anthony Opipari, Aravindhan K Krishnan, Shreekant Gayaka +4
Remembering where object segments were predicted in the past is useful for improving the accuracy and consistency of class-agnostic video segmentation algorithms. Existing video se…
cs.RO2024
Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentation
Anthony Opipari, Aravindhan K Krishnan, Shreekant Gayaka +4
This paper presents a method for generating large-scale datasets to improve class-agnostic video segmentation across robots with different form factors. Specifically, we consider t…
cs.DC2019
A Scalable Platform for Distributed Object Tracking across a Many-camera Network
Aakash Khochare, Aravindhan K, Yogesh Simmhan
Advances in deep neural networks (DNN) and computer vision (CV) algorithms have made it feasible to extract meaningful insights from large-scale deployments of urban cameras. Track…