Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.
Automatic image annotation via label transfer in the semantic space / Uricchio, Tiberio; Ballan, Lamberto; Seidenari, Lorenzo; Del Bimbo, Alberto. - In: PATTERN RECOGNITION. - ISSN 0031-3203. - ELETTRONICO. - 71:(2017), pp. 144-157. [10.1016/j.patcog.2017.05.019]
Automatic image annotation via label transfer in the semantic space
Uricchio, Tiberio;Ballan, Lamberto;Seidenari, Lorenzo;Del Bimbo, Alberto
2017
Abstract
Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.File | Dimensione | Formato | |
---|---|---|---|
1-s2.0-S0031320317302066-main.pdf
Accesso chiuso
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Tutti i diritti riservati
Dimensione
2.24 MB
Formato
Adobe PDF
|
2.24 MB | Adobe PDF | Richiedi una copia |
1605.04770.pdf
accesso aperto
Tipologia:
Preprint (Submitted version)
Licenza:
Open Access
Dimensione
4.6 MB
Formato
Adobe PDF
|
4.6 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.