J
Jonathon Shlens
Researcher at Google
Publications - 116
Citations - 88633
Jonathon Shlens is an academic researcher from Google. The author has contributed to research in topics: Object detection & Artificial neural network. The author has an hindex of 53, co-authored 116 publications receiving 63492 citations. Previous affiliations of Jonathon Shlens include Salk Institute for Biological Studies.
Papers
More filters
Proceedings ArticleDOI
A dataset and architecture for visual reasoning with a working memory
TL;DR: In this paper, the authors developed an artificial, configurable visual question and answer dataset (COG) to parallel experiments in humans and animals, inspired by a rich tradition of visual reasoning and memory in cognitive psychology and neuroscience.
Posted Content
Scene Transformer: A unified architecture for predicting multiple agent trajectories
Jiquan Ngiam,Benjamin Caine,Vijay K. Vasudevan,Zhengdong Zhang,Hao-Tien Lewis Chiang,Jeffrey Ling,Rebecca Roelofs,Alex Bewley,Chenxi Liu,Ashish Venugopal,David J. Weiss,Ben Sapp,Zhifeng Chen,Jonathon Shlens +13 more
TL;DR: In this article, a model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents is proposed, inspired by recent language modeling approaches, enabling one to invoke a single model to predict agent behavior in many ways, such as potentially conditioned on the goal or full future trajectory of the autonomous vehicle or the behaviour of other agents.
Posted ContentDOI
Individual variability of neural computations in the primate retina
Nishal P. Shah,Nora Brackbill,Samarakoon R,Colleen Rhoades,Alexandra Kling,Alexander Sher,Alan Litke,Yoram Singer,Jonathon Shlens,E. J. Chichilnisky +9 more
TL;DR: In this article, the authors probed neural code variation using ~100 neural population recordings from major ganglion cell types in the macaque retina, combined with an interpretable computational representation of individual variability using machine learning.
Patent
Label consistency for image analysis
TL;DR: In this article, an option may have an option score associated with an associated relation score, and a relation score may be calculated for a first option and a second option corresponding to a second object in an image.
Posted Content
A Learned Representation for Scalable Vector Graphics
TL;DR: In this paper, the drawing process of fonts is modeled by building sequential generative models of vector graphics, which have the benefit of providing a scale-invariant representation for imagery whose latent representation may be systematically manipulated and exploited to perform style propagation.