Hi there, I'm Arushi Rai!

I am a PhD student at the University of Pittsburgh since Fall 2021, where I am advised by Dr. Adriana Kovashka. My research is at the intersection of computer vision and language. I am currently working on video understanding and weakly-supervised object detection from noisy captions.

Publications

VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection. Arushi Rai and Adriana Kovashka. To appear at The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), March 2024. [pdf]

Improving language-supervised object detection with linguistic structure analysis. Arushi Rai and Adriana Kovashka. Workshop on Open-Domain Reasoning Under Multi-Modal Settings (O-DRUM), held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023. [pdf]