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
Posted Content
KETO: Learning Keypoint Representations for Tool Manipulation
TL;DR: The KETO framework is presented, a framework of learning keypoint representations of tool-based manipulation that consistently outperforms state-of-the-art methods in terms of task success rates.
Proceedings Article
Efficient Euclidean Projections onto the Intersection of Norm Balls
Adams Wei Yu,Hao Su,Li Fei-Fei +2 more
TL;DR: It is proved that the projection can be reduced to finding the root of an auxiliary function which is piecewise smooth and monotonic and hence, a bisection algorithm is sufficient to solve the problem.
Posted Content
Action Genome: Actions as Composition of Spatio-temporal Scene Graphs.
TL;DR: Action Genome as mentioned in this paper decomposes actions into spatio-temporal scene graphs to capture changes between objects and their pairwise relationships while an action occurs, and learns the temporal changes in visual relationships that result in an action.
Proceedings ArticleDOI
GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation
TL;DR: GaitForeMer as discussed by the authors uses human motion forecasting as an effective self-supervised pre-training task for the estimation of motor impairment severity, which is first pre-trained on public datasets to forecast gait movements and then applied to clinical data to predict MDS-UPDRS gait impairment severity.
Posted Content
Learning to Play with Intrinsically-Motivated Self-Aware Agents
TL;DR: In this paper, a neural network that implements curiosity-driven intrinsic motivation is used to train a self-model that allows the agent to track the error map of its own world-model, and then uses the self model to adversarially challenge the developing world model.