no code implementations • 9 Apr 2024 • Mukul Khanna, Ram Ramrakhya, Gunjan Chhablani, Sriram Yenamandra, Theophile Gervet, Matthew Chang, Zsolt Kira, Devendra Singh Chaplot, Dhruv Batra, Roozbeh Mottaghi
The Embodied AI community has made significant strides in visual navigation tasks, exploring targets from 3D coordinates, objects, language descriptions, and images.
no code implementations • 27 Feb 2024 • XiaoYu Zhang, Matthew Chang, Pranav Kumar, Saurabh Gupta
The Dataset Aggregation, or DAgger approach to this problem simply collects more data to cover these failure states.
no code implementations • 11 Dec 2023 • Aditya Prakash, Ruisen Tu, Matthew Chang, Saurabh Gupta
We present WildHands, a method for 3D hand pose estimation in egocentric images in the wild.
no code implementations • 4 May 2023 • Aditya Prakash, Matthew Chang, Matthew Jin, Saurabh Gupta
Prior works for reconstructing hand-held objects from a single image rely on direct 3D shape supervision which is challenging to gather in real world at scale.
no code implementations • 9 Feb 2023 • Matthew Chang, Saurabh Gupta
In this paper, we analyze the behavior of existing techniques and design new solutions for the problem of one-shot visual imitation.
no code implementations • ICLR 2022 • Matthew Chang, Arjun Gupta, Saurabh Gupta
We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions.
1 code implementation • NeurIPS 2020 • Matthew Chang, Arjun Gupta, Saurabh Gupta
Semantic cues and statistical regularities in real-world environment layouts can improve efficiency for navigation in novel environments.