Discovering states and transformations in image collections
Open Access
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1383-1391
- https://doi.org/10.1109/cvpr.2015.7298744
Abstract
Objects in visual scenes come in a rich variety of transformed states. A few classes of transformation have been heavily studied in computer vision: mostly simple, parametric changes in color and geometry. However, transformations in the physical world occur in many more flavors, and they come with semantic meaning: e.g., bending, folding, aging, etc. The transformations an object can undergo tell us about its physical and functional properties. In this paper, we introduce a dataset of objects, scenes, and materials, each of which is found in a variety of transformed states. Given a novel collection of images, we show how to explain the collection in terms of the states and transformations it depicts. Our system works by generalizing across object classes: states and transformations learned on one set of objects are used to interpret the image collection for an entirely new object class.This publication has 18 references indexed in Scilit:
- Reconstructing Storyline Graphs for Image Recommendation from Web Community PhotosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Style-Aware Mid-level Representation for Discovering Visual Connections in Space and TimePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- NEIL: Extracting Visual Knowledge from Web DataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Adding Unlabeled Samples to Categories by Learned AttributesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- SUN database: Large-scale scene recognition from abbey to zooPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Infinite Images: Creating and Exploring a Large Photorealistic Virtual SpaceProceedings of the IEEE, 2010
- Describing objects by their attributesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and ContextInternational Journal of Computer Vision, 2007
- Separating Style and Content with Bilinear ModelsNeural Computation, 2000
- Multidimensional Morphable Models: A Framework for Representing and Matching Object ClassesInternational Journal of Computer Vision, 1998