Automatic image annotation and retrieval using cross-media relevance models Export

@inproceedings{Jeon2003image-anno, abstract = {Libraries have traditionally used manual image annotation for indexing and then later retrieving their image collections. However, manual image annotation is an expensive and labor intensive procedure and hence there has been great interest in coming up with automatic ways to retrieve images based on content. Here, we propose an automatic approach to annotating and retrieving images based on a training set of images. We assume that regions in an image can be described using a small vocabulary of blobs. Blobs are generated from image features using clustering. Given a training set of images with annotations, we show that probabilistic models allow us to predict the probability of generating a word given the blobs in an image. This may be used to automatically annotate and retrieve images given a word as a query. We show that relevance models allow us to derive these probabilities in a natural way. Experiments show that the annotation performance of this cross-media relevance model is almost six times as good (in terms of mean precision) than a model based on word-blob co-occurrence model and twice as good as a state of the art model derived from machine translation. Our approach shows the usefulness of using formal information retrieval models for the task of image annotation and retrieval.}, address = {New York, NY, USA}, author = {Jeon, J. and Lavrenko, V. and Manmatha, R.}, booktitle = {SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval}, citeulike-article-id = {1258162}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=860459}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/860435.860459}, doi = {10.1145/860435.860459}, isbn = {1-58113-646-3}, keywords = {annotation, cross, image, media, model, relevance, retrieval}, location = {Toronto, Canada}, pages = {119--126}, posted-at = {2009-08-13 04:12:13}, priority = {2}, publisher = {ACM}, title = {Automatic image annotation and retrieval using cross-media relevance models}, url = {http://dx.doi.org/10.1145/860435.860459}, year = {2003} }

TY - CONF ID - Jeon2003image-anno L3 - citeulike-article-id:1258162 N2 - Libraries have traditionally used manual image annotation for indexing and then later retrieving their image collections. However, manual image annotation is an expensive and labor intensive procedure and hence there has been great interest in coming up with automatic ways to retrieve images based on content. Here, we propose an automatic approach to annotating and retrieving images based on a training set of images. We assume that regions in an image can be described using a small vocabulary of blobs. Blobs are generated from image features using clustering. Given a training set of images with annotations, we show that probabilistic models allow us to predict the probability of generating a word given the blobs in an image. This may be used to automatically annotate and retrieve images given a word as a query. We show that relevance models allow us to derive these probabilities in a natural way. Experiments show that the annotation performance of this cross-media relevance model is almost six times as good (in terms of mean precision) than a model based on word-blob co-occurrence model and twice as good as a state of the art model derived from machine translation. Our approach shows the usefulness of using formal information retrieval models for the task of image annotation and retrieval. CY - Toronto, Canada SN - 1-58113-646-3 AD - New York, NY, USA EP - 126 TI - Automatic image annotation and retrieval using cross-media relevance models PB - ACM T2 - SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval SP - 119 KW - annotation KW - cross KW - image KW - media KW - model KW - relevance KW - retrieval AU - Jeon, J AU - Lavrenko, V AU - Manmatha, R PY - 2003/// UR - http://dx.doi.org/10.1145/860435.860459 ER -