Titlebook: Computer Vision -- ACCV 2012; 11th Asian Conferenc Kyoung Mu Lee,Yasuyuki Matsushita,Zhanyi Hu Conference proceedings 2013 Springer-Verlag

简洁

雄辩

Focus-Words

sclera

Charade

CANON

The Development of Gas Turbine Materialsrate that combining features with multiple levels of spatial locality performs better than using just a single level. Our model performs better than all previous single-feature methods when tested on the Caltech 101 and 256 object recognition datasets.

敲诈

拔出

Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transferng, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance.

configuration

Cross-Database Transfer Learning via Learnable and Discriminant Error-Correcting Output Codese lack of training data in the target domain. Our approach is evaluated on several benchmark datasets, and leads to about 40% relative improvement in accuracy when only one training sample is available.

屈尊

The Pooled NBNN Kernel: Beyond Image-to-Class and Image-to-Imageo combine them in a multi kernel framework. We refer to our method as the .. This new scheme leads to significant improvement over the standard image-to-image and image-to-class baselines, with only a small increase in computational cost.