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 ContentDOI
Visual Intelligence through Human Interaction
TL;DR: In this article, a crowdsourcing interface for paid data collection and evaluation for computer vision models is presented, and a method to increase volunteer contributions using automated social interventions is explored, which is grounded in psychophysics theory, and future opportunities for human-computer interaction to aid computer vision are discussed.
Journal ArticleDOI
Solvent-exfoliated Cu-TCPP nanosheets: electrochemistry and sensing application in simultaneous determination of 4-aminophenol and acetaminophen
TL;DR: In this article , a series of Cu-TCPP nanosheets (TCPP: Tetrakis(4-carboxyphenyl)porphyrin) were prepared through ultrasonic exfoliation of bulk Cu-CPP in different solvents, including ethanol absolute (EtOH), N,Ndimethylformamide (DMF), N-methyl-2-pyrrolidone (NMP), and ultrapure water (H2O).
Journal ArticleDOI
Finding “good” features for natural scene classification
TL;DR: References Fei-Fei, L., & Perona, P. (2005).
Proceedings Article
A Dual Representation Framework for Robot Learning with Human Guidance
Ruohan Zhang,Dhruva Bansal,Yilun Hao,Ayano Hiranaka,Jialu Gao,Chen Wang,Li Fei-Fei,Jiajun Wu +7 more
TL;DR: In this article , a dual representation framework for robot learning from human guidance is proposed, which includes one for learning a sensorimotor control policy, and the other, in the form of a symbolic scene graph, for encoding the task-relevant information that motivates human input.
Social Role Discovery in Human Events (Open Access)
TL;DR: This work proposes a Conditional Random Field to model the inter-role interactions, along with person specific social descriptors, and develops tractable variational inference to simultaneously infer model weights, as well as role assignment to all people in the videos.