De-An Huang

De-An Huang

Auto-generated profile, based on publicly available information

De-An Huang

Stanford University

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
MGMichelle Guo
Michelle Guo
AHAlbert Haque
Albert Haque
DHDe-An Huang
De-An Huang
SYSerena Yeung
Serena Yeung
LFLi Fei-Fei
Li Fei-Fei

17 September 2016
Verified
Book Chapter
Closed access
PDF file
DHDe-An Huang
De-An Huang
LFLi Fei-Fei
Li Fei-Fei
JNJuan Carlos Niebles
Juan Carlos Niebles

6 October 2018
Verified
Book Chapter
Closed access
PDF file
MGMichelle Guo
Michelle Guo
ECEdward Chou
Edward Chou
DHDe-An Huang
De-An Huang
SSShuran Song
Shuran Song
SYSerena Yeung
Serena Yeung
LFLi Fei-Fei
Li Fei-Fei

27 November 2020
Verified
Book Chapter
Closed access
PDF file
CCChien-Yi Chang
Chien-Yi Chang
DHDe-An Huang
De-An Huang
DXDanfei Xu
Danfei Xu
EMEhsan Adeli Mosabbeb
Ehsan Adeli Mosabbeb
LFLi Fei-Fei
Li Fei-Fei
JNJuan Carlos Niebles
Juan Carlos Niebles

7 October 2018
Verified
Book Chapter
Closed access
PDF file
BLBingbin Liu
Bingbin Liu
SYSerena Yeung
Serena Yeung
ECEdward Chou
Edward Chou
DHDe-An Huang
De-An Huang
LFLi Fei-Fei
Li Fei-Fei
JNJuan Carlos Niebles
Juan Carlos Niebles

21 February 2015 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
DHDe-An Huang
De-An Huang
AFAmir-Massoud Farahmand
Amir-Massoud Farahmand
KKKris Kitani
Kris Kitani
JBJames Bagnell
James Bagnell
Maximum entropy inverse optimal control (MaxEnt IOC) is an effective means of discovering the underlying cost function of demonstrated human activity and can be used to predict human behavior over low-dimensional state spaces (i.e., forecasting of 2D trajectories). To enable inference in very large state spaces, we introduce an approximate MaxEnt IOC procedure to address the fundamental computational bottleneck stemming from calculating the partition function via dynamic programming. Approximate MaxEnt IOC is based on two components: approximate dynamic programming and Monte Carlo sampling. We analyze this approximation approach and provide a finite-sample error upper bound on its excess loss. We validate the proposed method in the context of analyzing dual-agent interactions from video, where we use approximate MaxEnt IOC to simulate mental images of a single agents body pose sequence (a high-dimensional image space). We experiment with sequences image data taken from RGB and RGBD data and show that it is possible to learn cost functions that lead to accurate predictions in high-dimensional problems that were previously intractable.