Skip to content

Commit

Permalink
Updated README with citations
Browse files Browse the repository at this point in the history
  • Loading branch information
svebk committed Jan 21, 2020
1 parent 40b0e15 commit 074adcf
Showing 1 changed file with 56 additions and 8 deletions.
64 changes: 56 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,8 @@ Author: [Svebor Karaman](mailto:[email protected])

This repository implements the image and face search tools developed
by the [DVMM lab](http:https://www.ee.columbia.edu/ln/dvmm/) of Columbia University for the
[MEMEX project](https://www.darpa.mil/program/memex) by Dr. Svebor Karaman, Dr. Tao Chen and Prof. Shih-Fu Chang.
[MEMEX project](https://www.darpa.mil/program/memex) by
Dr. Svebor Karaman, Dr. Tao Chen and Prof. Shih-Fu Chang.

## Overview

Expand All @@ -17,17 +18,21 @@ Two feature extraction models are included:
* A full image recognition model is based on the DeepSentibank feature representation
that was trained targeting the Adjective-Noun Pairs (ANP) of the
[Visual Sentiment Ontology](http:https://www.ee.columbia.edu/ln/dvmm/vso/download/sentibank.html).
* A face detection and recognition model, that are the publicly available models from the [DLib](http:https://blog.dlib.net/)
library, see the blog post [DLib face recognition](http:https://blog.dlib.net/2017/02/high-quality-face-recognition-with-deep.html)
* A face detection and recognition model, that are the publicly available models from the
[DLib](http:https://blog.dlib.net/)
library, see the blog post
[DLib face recognition](http:https://blog.dlib.net/2017/02/high-quality-face-recognition-with-deep.html)
for more information about the models.

However, the package `cufacesearch` has been written in a modular way and using
another image feature extraction model, face detection or recognition model should be fairly easy.
The package `cufacesearch` is fully documented, you can build the documentation following the
instructions in the [docs](cufacesearch/docs) folder.

NB: For now, the python package is still named `cufacesearch` even if it contains both
image and face search capability. The package will be renamed soon.
image and face search capability. The package could be renamed soon.

[//]: # (Add a figure overview)
[//]: # (Add a figure overview, from the website?)

## Installation

Expand All @@ -50,9 +55,52 @@ You can check the [README.md](./www/README.md) file in `www` folder for details
You can also open your browser at `http:https://localhost/[endpoint]/view_similar_byURL?data=[an_image_URL]`
to visualize some results.

## License

Apache License Version 2.0, see [LICENSE](LICENSE).
## License and citations

This software is release under the Apache License Version 2.0, see [LICENSE](LICENSE).
This repository contains a modified version of the
[python lopq package](https://github.com/yahoo/lopq/tree/master/python) in [lopq](lopq) also
released under an Apache License Version 2.0.

If you use this software in a product please mention in any communication
(website, presentation, etc...) regarding the image search capabilities of your product
that it relies on this repository with a sentence like:


> The image search capabilities of this product rely on the open-sourced "ColumbiaImageSearch"
> tool developed by Dr. Svebor Karaman, Dr. Tao Chen and Prof. Shih-Fu Chang at the
> [DVMM lab](http:https://www.ee.columbia.edu/ln/dvmm/) of Columbia University and available
> at https://github.com/ColumbiaDVMM/ColumbiaImageSearch.
If you use this repository in a research paper, you can cite it as:

```
@misc{KaramanCIS2015,
author = {Svebor Karaman and Tao Chen and Shih{-}Fu Chang},
title = {Columbia Image Search},
year = {2015},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/ColumbiaDVMM/ColumbiaImageSearch}}
}
```

If you use the DeepSentibank feature extraction, please cite the following paper:

```
@article{ChenDSB14,
author = {Tao Chen and
Damian Borth and
Trevor Darrell and
Shih{-}Fu Chang},
title = {DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional
Neural Networks},
journal = {CoRR},
volume = {abs/1410.8586},
year = {2014},
url = {http:https://arxiv.org/abs/1410.8586}
}
```

## Contact

Expand Down

0 comments on commit 074adcf

Please sign in to comment.