Trevor Darrell
E1017402
Trevor Darrell is a prominent computer vision and machine learning researcher and professor known for his work on deep learning, visual recognition, and autonomous systems.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Trevor Darrell canonical | 1 |
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
computer vision researcher
ⓘ
machine learning researcher ⓘ person ⓘ university professor ⓘ |
| citizenship |
United States of America
ⓘ
surface form:
United States
|
| fieldOfWork |
artificial intelligence
ⓘ
autonomous systems ⓘ computer vision ⓘ deep learning ⓘ machine learning ⓘ visual recognition ⓘ |
| gender | male ⓘ |
| hasAcademicPosition |
faculty member
ⓘ
professor ⓘ |
| influencedField |
autonomous driving research
ⓘ
deep learning for perception ⓘ modern computer vision ⓘ |
| knownFor |
autonomous driving perception systems
ⓘ
context-based visual recognition ⓘ deep learning for visual recognition ⓘ domain adaptation in computer vision ⓘ large-scale visual recognition datasets and benchmarks ⓘ multimodal learning for vision and language ⓘ object recognition in images and video ⓘ |
| notableContribution |
advances in domain adaptation for visual recognition
ⓘ
development of deep learning methods for image recognition ⓘ methods for context-aware object detection ⓘ research on perception for autonomous driving systems ⓘ work on integrating vision with natural language ⓘ |
| occupation |
computer scientist
ⓘ
professor ⓘ researcher ⓘ |
| researchInterest |
autonomous vehicles
ⓘ
deep neural networks ⓘ human-robot interaction ⓘ object detection ⓘ representation learning ⓘ robust perception in real-world environments ⓘ scene understanding ⓘ segmentation ⓘ transfer learning in vision ⓘ vision-language models ⓘ |
| worksOn |
autonomous systems perception
ⓘ
deep learning architectures for vision ⓘ interactive and embodied AI systems ⓘ large-scale visual recognition systems ⓘ learning from weakly labeled visual data ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.