Building discriminative CNN image representations for object retrieval using the replicator equation.
Shanmin PangJihua ZhuJiaxing WangVicente OrdonezJianru XuePublished in: Pattern Recognit. (2018)
Keyphrases
- object retrieval
- image representation
- visual words
- bag of words
- spatial pyramid
- image classification
- multiscale
- bag of visual words
- image retrieval
- object recognition
- retrieval accuracy
- image database
- image features
- visual vocabulary
- feature space
- text retrieval
- scene classification
- text mining
- action recognition
- sparse representation
- keypoints
- human detection
- feature extraction