Towards total scene understanding: Classification, annotation and segmentation in an automatic framework Export

@inproceedings{citeulike:6045657, abstract = {Given an image, we propose a hierarchical generative model that classifies the overall scene, recognizes and segments each object component, as well as annotates the image with a list of tags. To our knowledge, this is the first model that performs all three tasks in one coherent framework. For instance, a scene of a dasiapolo gamepsila consists of several visual objects such as dasiahumanpsila, dasiahorsepsila, dasiagrasspsila, etc. In addition, it can be further annotated with a list of more abstract (e.g. dasiaduskpsila) or visually less salient (e.g. dasiasaddlepsila) tags. Our generative model jointly explains images through a visual model and a textual model. Visually relevant objects are represented by regions and patches, while visually irrelevant textual annotations are influenced directly by the overall scene class. We propose a fully automatic learning framework that is able to learn robust scene models from noisy Web data such as images and user tags from Flickr.com. We demonstrate the effectiveness of our framework by automatically classifying, annotating and segmenting images from eight classes depicting sport scenes. In all three tasks, our model significantly outperforms state-of-the-art algorithms.}, author = {Li, Li-Jia and Socher, R. and Fei-Fei, Li}, citeulike-article-id = {6045657}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/CVPRW.2009.5206718}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5206718}, day = {25}, doi = {10.1109/CVPRW.2009.5206718}, journal = {Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on}, keywords = {cbir, mitchell-group}, month = {June}, pages = {2036--2043}, posted-at = {2009-10-31 00:19:08}, priority = {2}, title = {Towards total scene understanding: Classification, annotation and segmentation in an automatic framework}, url = {http://dx.doi.org/10.1109/CVPRW.2009.5206718}, year = {2009} }

TY - CONF ID - citeulike:6045657 L3 - citeulike-article-id:6045657 N2 - Given an image, we propose a hierarchical generative model that classifies the overall scene, recognizes and segments each object component, as well as annotates the image with a list of tags. To our knowledge, this is the first model that performs all three tasks in one coherent framework. For instance, a scene of a dasiapolo gamepsila consists of several visual objects such as dasiahumanpsila, dasiahorsepsila, dasiagrasspsila, etc. In addition, it can be further annotated with a list of more abstract (e.g. dasiaduskpsila) or visually less salient (e.g. dasiasaddlepsila) tags. Our generative model jointly explains images through a visual model and a textual model. Visually relevant objects are represented by regions and patches, while visually irrelevant textual annotations are influenced directly by the overall scene class. We propose a fully automatic learning framework that is able to learn robust scene models from noisy Web data such as images and user tags from Flickr.com. We demonstrate the effectiveness of our framework by automatically classifying, annotating and segmenting images from eight classes depicting sport scenes. In all three tasks, our model significantly outperforms state-of-the-art algorithms. JF - Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on EP - 2043 TI - Towards total scene understanding: Classification, annotation and segmentation in an automatic framework SP - 2036 KW - cbir KW - mitchell-group AU - Li, Li-Jia AU - Socher, R AU - Fei-Fei, Li PY - 2009/06/25/ UR - http://dx.doi.org/10.1109/CVPRW.2009.5206718 ER -