A New Baseline for Image Annotation

A New Baseline for Image Annotation

Cached

Download Links

by Ameesh Makadia , Vladimir Pavlovic , Sanjiv Kumar

Citations:

BibTeX

@MISC{Makadia_anew,
    author = {Ameesh Makadia and Vladimir Pavlovic and Sanjiv Kumar},
    title = {A New Baseline for Image Annotation},
    year = {}
}

Bookmark

OpenURL

Abstract

Abstract. Automatically assigning keywords to images is of great interest as it allows one to index, retrieve, and understand large collections of image data. Many techniques have been proposed for image annotation in the last decade that give reasonable performance on standard datasets. However, most of these works fail to compare their methods with simple baseline techniques to justify the need for complex models and subsequent training. In this work, we introduce a new baseline technique for image annotation that treats annotation as a retrieval problem. The proposed technique utilizes low-level image features and a simple combination of basic distances to find nearest neighbors of a given image. The keywords are then assigned using a greedy label transfer mechanism. The proposed baseline outperforms the current state-of-the-art methods on two standard and one large Web dataset. We believe that such a baseline measure will provide a strong platform to compare and better understand future annotation techniques. 1

Citations

1824	Normalized cuts and image segmentation - Shi, Malik - 2000
1369	Latent Dirichlet allocation - Blei, Andrew, et al.
999	Regression shrinkage and selection via the lasso - Tibshirani - 2006
333	Labeling Images with a Computer Game - Ahn, Dabbish - 2004
327	Object recognition as machine translation :learning a lexicon for a fixed image vocabulary - Duygulu, Barnard, et al. - 2002
275	Similarity search in high dimensions via hashing - Gionis, Indyk, et al. - 1999
240	Modeling annotated data - Blei, Jordan - 2003
238	Automatic image annotation and retrieval using cross-media relevance models - Jeon, Lavrenko, et al. - 2003
171	Automatic linguistic indexing of pictures by a statistical modeling approach - Li, Wang
157	Image Retrieval: Ideas, Influences, and Trends of the New Age - Datta, Joshi, et al.
128	Multiple bernoulli relevance models for image and video annotation - Feng, Manmatha, et al. - 2004
127	A model for learning the semantics of pictures - Lavrenko, Manmatha, et al. - 2003
113	Image-to-word transformation based on dividing and vector quantizing images with words - Mori, Takahashi, et al. - 1999
80	Learning the discriminative powerinvariance trade-off - Varma, Ray - 2007
74	Supervised learning of semantic classes for image annotation and retrieval - Carneiro, Chan, et al. - 1998
60	On image auto-annotation with latent space models - Monay, Gatica-Perez - 2003
50	Learning globally-consistent local distance functions for shape-based image retrieval and classification - Frome, Singer, et al.
48	Automated image annotation using global features and robust nonparametric density estimation - Yavlinsky, Schofield, et al. - 2005
42	Formulating semantic image annotation as a supervised learning problem - Carneiro, Vasconcelos - 2005
25	Effective automatic image annotation via a coherent language model and active learning - Jin, Chai, et al. - 2004
22	M.: Word sense disambiguation with pictures - Barnard, Johnson - 2005
19	An inference network approach to image retrieval - Metzler, Manmatha - 2004
15	A database centric view of semantic image annotation and retrieval - Carneiro, Vasconcelos
13	C.J.: Mind the gap: another look at the problem of the semantic gap in image retrieval - Hare, Lewis, et al.
11	Region-based image annotation using asymmetrical support vector machinebased multiple-instance learning - Yang, Dong, et al. - 2006
5	Incorporating concept ontology to enable probabilistic concept reasoning for multi-level image annotation - Gao, Fan - 2006
4	Automatic image annotation and retrieval using subspace clustering algorithm," presented at the - Wang - 2004
2	2002), “Object recognition as machine translation: learning a lexicon for a fixed image vocabulary - Duygulu, Barnard
2	2003, ‘Automatic linguistic indexing of pictures by a statistical modeling approach - Li, Wang
1	Sandomb: 2006, ‘Mind the Gap: Another look at the problem of the semantic gap in image retrieval’. Multimedia Content, Analysis, Management and Retrieval - Hare, Lewisa, et al.