Trevor Darrell
Biographic Data
| ID | 4973298 |
|---|---|
| NAME | Trevor Darrell |
| GIVEN NAMES | Trevor |
| FAMILY NAME | Darrell |
| SIGNATURE | DARRELL T |
| AFFILIATIONS | Massachusetts Institute of Technology |
| ORCID | 0000-0001-5453-8533 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 2 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2001 |
| LATEST PUBLICATION YEAR | 2015 |
| H-INDEX | 0 |
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolut…
Privacy in Context
Context-aware computing offers the promise of significant user gains-the ability for systems to adapt more readily to user needs, models, and goals. Dey, Abowd, and Salber (2001 [this special issue]) present a masterful step toward understanding context-aware applications. We examine Dey et al. in the light of privacy issues-that is, individuals' control over their personal data-to highlight some of the thorny issues in context-aware computing th…
No prominent works on this page.
Privacy in Context
Context-aware computing offers the promise of significant user gains-the ability for systems to adapt more readily to user needs, models, and goals. Dey, Abowd, and Salber (2001 [this special issue]) present a masterful step toward understanding context-aware applications. We examine Dey et al. in the light of privacy issues-that is, individuals' control over their personal data-to highlight some of the thorny issues in context-aware computing th…
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolut…
Computer Science (2 works) · Advanced Neural Network Applications (1 works) · Artificial Intelligence (1 works) · Computer security (1 works) · Context (archaeology (1 works) · Context-Aware Activity Recognition Systems (1 works) · Convolutional neural network (1 works) · Domain Adaptation and Few-Shot Learning (1 works) · Geography (1 works) · Inference (1 works)