20 citations · 41 across the 20 of their papers we have counts for
4 papers · 1 filter
FIction: 4D Future Interaction Prediction from Video
Kumar Ashutosh, Georgios Pavlakos, Kristen Grauman
Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-cap…
ExpertAF: Expert Actionable Feedback from Video
Kumar Ashutosh, Tushar Nagarajan, Georgios Pavlakos +2
Feedback is essential for learning a new skill or improving one's current skill-level. However, current methods for skill-assessment from video only provide scores or compare demon…
SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
Changan Chen, Kumar Ashutosh, Rohit Girdhar +2
We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Whereas existing methods rely on curated data with known audio-…
Detours for Navigating Instructional Videos
Kumar Ashutosh, Zihui Xue, Tushar Nagarajan +1
We introduce the video detours problem for navigating instructional videos. Given a source video and a natural language query asking to alter the how-to video's current path of exe…