Sirnam Swetha

Bio


Hello, I'm a PhD student at the Center for Research in Computer Vision (CRCV), University of Central Florida advised by Prof. Mubarak Shah. Previously, I graduated with Bachelor in Technology (B.Tech) with Honors and MS by research from International Institute of Information Technology, Hyderabad (IIIT-H), where I was advised by Prof. C. V. Jawahar (Center for Visual Information Technology [CVIT], IIIT-H) and Prof. Vineeth N Balasubramanian, IIT-H.

Google Scholar

Email

Projects


Contrastive Learning of Video Foreground Segmentation as a Self-Supervised Pretext Task

Sirnam Swetha*,Rohit Gupta*, Yogesh Rawat
* denotes equal contribution
We attempt to perform constrastive learning for video segmentation as a self-supervised pretext task by exploiting the temporal dimension of videos. We also evaluate the transfer learning capability of the learned representations.

Consistency based Semi-Supervised Learning for Action Detection in Videos

Sirnam Swetha, Yogesh Rawat
An end-to-end model for consistency based semi-supervised model for action detection in videos is developed as an extension of consistency based semi-supervised object detection method.

Spam Filtering Using Visual Features

Sirnam Swetha, Sharvani Chandu, Sneha Kummetha
To filter the spam emails using Visual features and text, and then classify the emails as spam/ham. Combining Visual features with text improves the classification performance.

Fashion search and Apparel Retrieval

Sirnam Swetha, CV Jawahar
A Cloth retrieval system: application for enhanced image search from a database of images taken from Myntra.