Behavior Recognition via Sparse Spatio-Temporal Features
A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while pr...
Publications
2 shownUnderstanding Convolution for Semantic Segmentation
Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we ...
Frequent Co-Authors
Researcher Info
- h-index
- 2
- Publications
- 2
- Citations
- 4,378
- Institution
- University of California, San Diego
External Links
Identifiers
- ORCID
- 0000-0001-7538-1715
Impact Metrics
h-index
2
h-index: Number of publications with at least h citations each.