Trevor Darrell
MIT Media Lab
5 papers in the Anchorcite directory, published between 1997 and 2016, cited 100,724 times in total.
ORCID profileResearch topics
- Advanced Neural Network Applications · 4 papers
- Domain Adaptation and Few-Shot Learning · 3 papers
- Advanced Image and Video Retrieval Techniques · 2 papers
- Multimodal Machine Learning Applications · 1 paper
- Medical Image Segmentation Techniques · 1 paper
- Generative Adversarial Networks and Image Synthesis · 1 paper
Frequent co-authors
- Jonathan Long · 3 papers
- Evan Shelhamer · 3 papers
- Ross Girshick · 2 papers
- Jeff Donahue · 2 papers
- Jitendra Malik · 1 paper
- Yangqing Jia · 1 paper
- Sergey Karayev · 1 paper
- Sergio Guadarrama · 1 paper
Papers
- Fully convolutional networks for semantic segmentation2015 · 37,731 citations
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…
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014 · 32,278 citations
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose…
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 15,272 citations
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, improve on the previous best result in semantic segmentation. Our key insight is to build "fully convolutional" networks that…
- Caffe2014 · 11,223 citations
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose…
- Pfinder: real-time tracking of the human bodyIEEE Transactions on Pattern Analysis and Machine Intelligence · 1997 · 4,220 citations
Pfinder is a real-time system for tracking people and interpreting their behavior. It runs at 10 Hz on a standard SGI Indy computer, and has performed reliably on thousands of people in many different physical locations. The system uses a…
Metadata from OpenAlex (CC0).