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
The Sound of Motions
TL;DR: In this paper, an end-to-end learnable model called Deep Dense Trajectory (DDT) and a curriculum learning scheme was proposed for sound localization and separation.
Posted Content
Connecting Touch and Vision via Cross-Modal Prediction
TL;DR: This work investigates the cross-modal connection between vision and touch with a new conditional adversarial model that incorporates the scale and location information of the touch and demonstrates that the model can produce realistic visual images from tactile data and vice versa.
Proceedings ArticleDOI
Open Vocabulary Scene Parsing
TL;DR: In this article, a joint image pixel and word concept embeddings framework is proposed, where word concepts are connected by semantic relations and the trained joint embedding space is further explored to show its interpretability.
Proceedings ArticleDOI
Neural Turtle Graphics for Modeling City Road Layouts
Hang Chu,Daiqing Li,David Acuna,Amlan Kar,Maria Shugrina,Xinkai Wei,Ming-Yu Liu,Antonio Torralba,Sanja Fidler +8 more
TL;DR: NTG is a sequential generative model parameterized by a neural network that iteratively generates a new node and an edge connecting to an existing node conditioned on the current graph and achieves state-of-the-art performance on the SpaceNet dataset.
Journal ArticleDOI
Revealing hidden scenes by photon-efficient occlusion-based opportunistic active imaging.
Feihu Xu,Gal Shulkind,Christos Thrampoulidis,Jeffrey H. Shapiro,Antonio Torralba,Franco N. C. Wong,Gregory W. Wornell +6 more
TL;DR: This work employs a computational imaging technique that opportunistically exploits the presence of occluding objects, which obstruct probe-light propagation in the hidden scene, to undo the mixing and greatly improve scene recovery and represents an instance of a rich and promising new imaging modality.