Name
Abstract | ||
|---|---|---|
To go beyond the query-by-example paradigm in image retrieval, there is a need for semantic indexing of large image collections for intuitive text-based image search. Different models have been proposed to learn the dependencies between the visual content of an image set and the associated text captions, then allowing for the automatic creation of semantic indices for unannotated images. The task, however, remains unsolved. In this paper, we present three alternatives to learn a Probabilistic Latent Semantic Analysis model (PLSA) for annotated images, and evaluate their respective performance for automatic image indexing. Under the PLSA assumptions, an image is modeled as a mixture of latent aspects that generates both image features and text captions, and we investigate three ways to learn the mixture of aspects. We also propose a more discriminative image representation than the traditional Blob histogram, concatenating quantized local color information and quantized local texture descriptors. The first learning procedure of a PLSA model for annotated images is a standard EM algorithm, which implicitly assumes that the visual and the textual modalities can be treated equivalently. The other two models are based on an asymmetric PLSA learning, allowing to constrain the definition of the latent space on the visual or on the textual modality. We demonstrate that the textual modality is more appropriate to learn a semantically meaningful latent space, which translates into improved annotation performance. A comparison of our learning algorithms with respect to recent methods on a standard dataset is presented, and a detailed evaluation of the performance shows the validity of our framework. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/TPAMI.2007.1097 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
annotated image,image feature,automatic image indexing,unannotated image,image retrieval,discriminative image representation,modeling semantic aspects,large image collection,image set,intuitive text-based image search,textual modality,cross-media image indexing,expectation maximization,image features,indexation,image annotation,probability,image segmentation,indexing,probabilistic latent semantic analysis,query by example,em algorithm,expectation maximization algorithm,feature extraction | Computer science,Image retrieval,Search engine indexing,Image segmentation,Probabilistic latent semantic analysis,Artificial intelligence,Computer vision,Automatic image annotation,Information retrieval,Pattern recognition,Feature (computer vision),Feature extraction,Automatic indexing | Journal |
Volume | Issue | ISSN |
29 | 10 | 0162-8828 |
Citations | PageRank | References |
116 | 4.42 | 31 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Florent Monay | 1 | 593 | 31.43 |
| Daniel Gatica-Perez | 2 | 4182 | 276.74 |
| Gatica-Perez, D. | 3 | 116 | 4.42 |