TY - JOUR
T1 - Towards A Richer 2D Understanding of Hands at Scale
AU - Cheng, Tianyi
AU - Shan, Dandan
AU - Sultan, Ayda
AU - Higgins, Richard E.L.
AU - Fouhey, David F.
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - As humans, we learn a lot about how to interact with the world by observing others interacting with their hands. To help AI systems obtain a better understanding of hand interactions, we introduce a new model that produces a rich understanding of hand interaction. Our system produces a richer output than past systems at a larger scale. Our outputs include boxes and segments for hands, in-contact objects, and second objects touched by tools as well as contact and grasp type. Supporting this method are annotations of 257K images, 401K hands, 288K objects, and 19K second objects spanning four datasets. We show that our method provides rich information and performs and generalizes well.
AB - As humans, we learn a lot about how to interact with the world by observing others interacting with their hands. To help AI systems obtain a better understanding of hand interactions, we introduce a new model that produces a rich understanding of hand interaction. Our system produces a richer output than past systems at a larger scale. Our outputs include boxes and segments for hands, in-contact objects, and second objects touched by tools as well as contact and grasp type. Supporting this method are annotations of 257K images, 401K hands, 288K objects, and 19K second objects spanning four datasets. We show that our method provides rich information and performs and generalizes well.
UR - http://www.scopus.com/inward/record.url?scp=85189186924&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85189186924&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85189186924
SN - 1049-5258
VL - 36
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
Y2 - 10 December 2023 through 16 December 2023
ER -