Visually Browsing Millions of Images Using Image Graphs
2017 International Conference on Multimedia Retrieval (ICMR '17)
TL;DR
We present a new method for visually browsing large sets of untagged images using high-quality features from convolutional neural network activations to build a hierarchical image graph. Our approach offers an efficient and user-friendly way to explore the image collection interactively.
Abstract
We present a new approach to visually browse very large sets of untagged images. High quality image features are generated using transformed activations of a convolutional neural network. These features are used to model image similarities, from which a hierarchical image graph is build. We show how such a graph can be constructed efficiently. In our experiments we found best user experience for navigating the graph is achieved by projecting sub-graphs onto a regular 2D image map. This allows users to explore the image collection like an interactive map.
BibTeX
If you use our work in your research, please cite our publication:
@inproceedings{10.1145/3078971.3079016,
author = {Barthel, Kai Uwe and Hezel, Nico and Jung, Klaus},
title = {Visually Browsing Millions of Images Using Image Graphs},
year = {2017},
isbn = {9781450347013},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3078971.3079016},
doi = {10.1145/3078971.3079016},
booktitle = {Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval},
pages = {475–479},
numpages = {5},
keywords = {visualization, navigation, image graph, exploration, convolutional neural networks, cbir, browsing},
location = {Bucharest, Romania},
series = {ICMR '17}
}