L
Li Fei-Fei
Researcher at Stanford University
Publications - 515
Citations - 199224
Li Fei-Fei is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 120, co-authored 420 publications receiving 145574 citations. Previous affiliations of Li Fei-Fei include Google & California Institute of Technology.
Papers
More filters
Journal ArticleDOI
Quantifying Parkinson's disease motor severity under uncertainty using MDS-UPDRS videos.
Mandy Lu,Qingyu Zhao,Kathleen L. Poston,Edith V. Sullivan,Adolf Pfefferbaum,Marian Shahid,Maya Katz,Leila Montaser Kouhsari,Kevin A. Schulman,Arnold Milstein,Juan Carlos Niebles,Victor W. Henderson,Li Fei-Fei,Kilian M. Pohl,Ehsan Adeli +14 more
TL;DR: In this article, an ordinal focal neural network is used to estimate the MDS-UPDRS scores from input videos, to leverage the ordinal nature of ratings and combat class imbalance.
Posted Content
Towards Viewpoint Invariant 3D Human Pose Estimation
TL;DR: A viewpoint invariant model for 3D human pose estimation from a single depth image that leverages a convolutional and recurrent network architecture with a top-down error feedback mechanism to self-correct previous pose estimates in an end-to-end manner.
Posted Content
A Study of Face Obfuscation in ImageNet
TL;DR: In this paper, the authors explore the effects of face obfuscation on the popular ImageNet challenge visual recognition benchmark and demonstrate that face blurring has minimal impact on the accuracy of recognition models.
Posted Content
End-to-end Learning of Action Detection from Frame Glimpses in Videos
TL;DR: A fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions and uses REINFORCE to learn the agent's decision policy.
Journal ArticleDOI
Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
TL;DR: In this paper, a set of metaphors along the dimensions of warmth and competence was used to test the effect of metaphor choices on users' experience of conversational AI agents, and they found that metaphors that signal low competence lead to better evaluations of the agent than metaphor that signal high competence.