Large-Scale Image Mining with Flickr Groups
| Autor: | Ioannis Kanellos, Adrian Popescu, Nicolas Ballas, Phong D. Vo, Hervé Le Borgne, Alexandru Lucian Ginsca |
|---|---|
| Přispěvatelé: | Département informatique (INFO), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université de Montréal (UdeM), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)) |
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
Information retrieval
Computer science Semantic feature Flickr Groups [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Semantic image retrieval Convolutional neural network Pipeline (software) Resource (project management) Semantic representations Scalability Benchmark (computing) Content-based image retrieval (CBIR) Noise (video) Image retrieval |
| Zdroj: | Proceedings MMM 2015 : 21st International Conference on MultiMedia Modeling International Conference on Multimedia Modeling International Conference on Multimedia Modeling, Jan 2015, Sydney, NSW, Australia. pp.318-334, ⟨10.1007/978-3-319-14445-0_28⟩ MultiMedia Modeling ISBN: 9783319144443 MMM (1) |
| DOI: | 10.1007/978-3-319-14445-0_28⟩ |
| Popis: | International audience; The availability of large annotated visual resources, such as ImageNet, recently led to important advances in image mining tasks. However, the manual annotation of such resources is cumbersome. Exploiting Web datasets as a substitute or complement is an interesting but challenging alternative. The main problems to solve are the choice of the initial dataset and the noisy character of Web text-image associations. This article presents an approach which first leverages Flickr groups to automatically build a comprehensive visual resource and then exploits it for image retrieval. Flickr groups are an interesting candidate dataset because they cover a wide range of user interests. To reduce initial noise, we introduce innovative and scalable image reranking methods. Then, we learn individual visual models for 38,500 groups using a low-level image representation. We exploit off-the-shelf linear models to ensure scalability of the learning and prediction steps. Finally, Semfeat image descriptions are obtained by concatenating prediction scores of individual models and by retaining only the most salient responses. To provide a comparison with a manually created resource, a similar pipeline is applied to ImageNet. Experimental validation is conducted on the ImageCLEF Wikipedia Retrieval 2010 benchmark, showing competitive results that demonstrate the validity of our approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|