Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time

Yong Jae Lee, Alexei A. Efros, Martial Hebert; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 1857-1864

Abstract


We present a weakly-supervised visual data mining approach that discovers connections between recurring midlevel visual elements in historic (temporal) and geographic (spatial) image collections, and attempts to capture the underlying visual style. In contrast to existing discovery methods that mine for patterns that remain visually consistent throughout the dataset, our goal is to discover visual elements whose appearance changes due to change in time or location; i.e., exhibit consistent stylistic variations across the label space (date or geo-location). To discover these elements, we first identify groups of patches that are stylesensitive. We then incrementally build correspondences to find the same element across the entire dataset. Finally, we train style-aware regressors that model each element's range of stylistic differences. We apply our approach to date and geo-location prediction and show substantial improvement over several baselines that do not model visual style. We also demonstrate the method's effectiveness on the related task of fine-grained classification.

Related Material


[pdf]
[bibtex]
@InProceedings{Lee_2013_ICCV,
author = {Lee, Yong Jae and Efros, Alexei A. and Hebert, Martial},
title = {Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}