A
Antonio Torralba
Researcher at Massachusetts Institute of Technology
Publications - 437
Citations - 105763
Antonio Torralba is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 119, co-authored 388 publications receiving 84607 citations. Previous affiliations of Antonio Torralba include Vassar College & Nvidia.
Papers
More filters
Posted Content
Learning to Simulate Dynamic Environments with GameGAN
TL;DR: GameGAN is introduced, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training and is able to disentangle static and dynamic components within an image making the behavior of the model more interpretable, and relevant for downstream tasks that require explicit reasoning over dynamic elements.
Journal ArticleDOI
Guest Editorial: Big Data
Alyosha Efros,Antonio Torralba +1 more
TL;DR: Computer vision has a split personality; within the same field, and largely guided by the same set of fundamental algorithms, it combines two problems that are utterly disparate in their aims and philosophy—here the authors will call them “Vision as Measurement” and “ Vision as Understanding”.
Journal Article
What are the shapes of response time distributions in visual search
TL;DR: This paper presents the raw RT distributions and fit several psychologically motivated functions (ex-Gaussian, ex-Wald, Gamma, and Weibull) to the data, and analyzes and interpret parameter trends from these four functions within the context of theories of visual search.
Proceedings Article
From retinal circuits to motion processing: a neuromorphic approach to velocity estimation.
Antonio Torralba,Jeanny Hérault +1 more
Proceedings ArticleDOI
Composing Ensembles of Pre-trained Models via Iterative Consensus
TL;DR: Results show that the proposed framework for composing ensembles of different pre-trained models can be used as a general purpose framework for a wide range of zero-shot multimodal tasks, such as image generation, video question answering, mathematical reasoning, and robotic manipulation.