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 Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
TL;DR: In this article, the authors propose to learn a particle-based simulator for complex control tasks, such as manipulating fluids and deformable foam, with experiments both in simulation and in the real world.
Book ChapterDOI
Deep Feedback Inverse Problem Solver
Wei-Chiu Ma,Wei-Chiu Ma,Shenlong Wang,Shenlong Wang,Jiayuan Gu,Jiayuan Gu,Sivabalan Manivasagam,Sivabalan Manivasagam,Antonio Torralba,Raquel Urtasun,Raquel Urtasun +10 more
TL;DR: An efficient, effective, and generic approach towards solving inverse problems by leveraging the feedback signal provided by the forward process and learning an iterative update model that can produce accurate estimations that are coherent to the input observation.
Proceedings ArticleDOI
Disentangling visual and written concepts in CLIP
TL;DR: This work investigates the entanglement of the representation of word images and natural images in its image encoder and devise a procedure for identifying representation subspaces that selectively isolate or eliminate spelling capabilities of CLIP.
Book ChapterDOI
Using Computer Vision to Study the Effects of BMI on Online Popularity and Weight-Based Homophily
TL;DR: A state-of-the-art computer vision system is used to predict a person’s body-mass index (BMI) from their social media profile picture and the type of analyses this approach enables using data from two culturally diverse settings – the US and Qatar are demonstrated.
Proceedings ArticleDOI
Learning Program Representations for Food Images and Cooking Recipes
Dimitrios P. Papadopoulos,Enrique Mora,Nadiia Chepurko,Kuan-Wei Huang,Ferda Ofli,Antonio Torralba +5 more
TL;DR: This paper builds a model that is trained to learn a joint embedding between recipes and food images via self-supervision and jointly generate a program from this embedding as a sequence and crowdsource programs for cooking recipes show that projecting the image-recipe embeddings into programs leads to better cross-modal retrieval results.