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 Compose Visual Relations.
TL;DR: In this article, the authors propose to represent each relation as an unnormalized density (an energy-based model), enabling them to compose separate relations in a factorized manner, which allows the model to both generate and edit scenes that have multiple sets of relations more faithfully.
Journal ArticleDOI
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models
TL;DR: In this article , an unsupervised approach is presented to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images.
Patent
Pose estimation using radio frequency signals
Dina Katabi,Antonio Torralba,Hang Zhao,Mingmin Zhao,Tianhong Li,Abualsheikh Mohammad,Yonglong Tian +6 more
TL;DR: In this article, a method for pose recognition includes storing parameters for configuration of an automated pose recognition system for detection of a pose of a subject represented in a radio frequency input signal.
Book ChapterDOI
A latent variable ranking model for content-based retrieval
TL;DR: This work proposes a latent variable ranking model that induces both the latent classes and the weights of the linear combination for each class from ranking triplets and has a clear computational advantages since it does not need to be retrained for each test query.
Journal ArticleDOI
Energy consumption analytical modeling of NB-IoT devices for diverse IoT applications
TL;DR: In this paper , a comprehensive power consumption model for battery lifetime estimation in narrowband IoT (NB-IoT) is presented, which is based on the user equipment (UE) state diagram and considers the extended discontinuous reception (eDRX) and power saving mode (PSM) mechanisms.