- Illumination and Specularity
- Deformation Invariant Matching. Also see for scale-cascaded matching
- Multiscale Local Features & Multiscale Global Features
- Hybrid Contexts: Eulerian & Lagrangian Shape-Contexts
- Randomized Representations — In the 2008 JAE paper, we perturb patch geometries to account for distributional shifts between the provided data and reality. The initial perturbation models are generalized to deformations learned from scale-cascaded alignment.
- Hierarchical Retrieval
- Boosted Retrieval
- Relevance Feedback and Crowd-soucring Relevance Feedback
- Learning to seek Sparse Human Input Representations for Retrieval