Ishani Chakraborty — accepted AI-conference papers

2023

HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World

Xin Wang, Taein Kwon, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist +6

ICCV 2023poster

Building an interactive AI assistant that can perceive, reason, and collaborate with humans in the real world has been a long-standing pursuit in the AI community. This work is part of a broader research effort to develop intelligent agents that can interactively guide humans through performing task…

Cited by 55 PDF ↗code ↗Scholar ↗

2019

Priming Deep Pedestrian Detection with Geometric Context

Ishani Chakraborty, Gang Hua

ICRA 2019poster

We investigate the role of geometric context in deep neural networks to establish better pedestrian detectors that are more robust to occlusions. Notwithstanding their demonstrated successes, deep object detectors under-perform in crowded scenes with high intra-category occlusions. One brute-force s…

Cited by 0 Source ↗Scholar ↗