apsvvfb的专栏

Zero-example event search using multimodel pseudo relevance feedbackEasy samples first:self-paced reranking for zero-example multimedia searchBeyond gaussian pyramid: multi-skip feature stacking for ac

CVPR2015: Show and Tell: A Neural Image Caption Generator to use a CNN as an image “encoder”, by first pre-training it for an image classification task and using the last hidden layer as an input

Object Proposals: 1.Grouping super-pixels 2.Sliding windowsFaster R-CNN 2 modules: a deep fully convolutional network that proposes regions Fast R-CNN detector that uses the proposed regions // t