54 citations · 76 across the 3 of their papers we have counts for
3 papers
Forecasting Action through Contact Representations from First Person Video
Eadom Dessalene, Chinmaya Devaraj, Michael Maynord +2
Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on antici…
Egocentric Object Manipulation Graphs
Eadom Dessalene, Michael Maynord, Chinmaya Devaraj +2
We introduce Egocentric Object Manipulation Graphs (Ego-OMG) - a novel representation for activity modeling and anticipation of near future actions integrating three components: 1)…
Following Instructions by Imagining and Reaching Visual Goals
John Kanu, Eadom Dessalene, Xiaomin Lin +2
While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learn…