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
Proceedings ArticleDOI
Efficient extraction of human motion volumes by tracking
TL;DR: An automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearance-based approaches and provides temporally coherent human regions.
Posted Content
Unsupervised Learning of Long-Term Motion Dynamics for Videos
TL;DR: In this article, an unsupervised representation learning approach that compactly encodes the motion dependencies in videos is presented, given a pair of images from a video clip, the framework learns to predict the long-term 3D motions.
Journal ArticleDOI
Pinpointing the peripheral bias in neural scene-processing networks during natural viewing.
TL;DR: Functional MRI results show a fine-scale relationship between eccentricity biases and functional correlation during natural perception, giving new insight into the structure of the scene-perception network.
Journal ArticleDOI
Online Developmental Science to Foster Innovation, Access, and Impact.
Mark Sheskin,Kimberly Scott,Candice M. Mills,Elika Bergelson,Elizabeth Bonawitz,Elizabeth S. Spelke,Li Fei-Fei,Frank C. Keil,Hyowon Gweon,Joshua B. Tenenbaum,Julian Jara-Ettinger,Karen E. Adolph,Marjorie Rhodes,Michael C. Frank,Samuel A. Mehr,Laura Schulz +15 more
TL;DR: It is proposed that developmental cognitive science should invest in an online CRADLE, a Collaboration for Reproducible and Distributed Large-Scale Experiments that crowdsources data from families participating on the internet.
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation.
TL;DR: CAVIN Planner is presented, a model-based method that hierarchically generates plans by sampling from latent spaces that decouple the prediction of high-level effects from the generation of low-level motions through cascaded variational inference to facilitate planning over long time horizons.