@inproceedings{cinbis:hal-00873134,
AUTHOR = {Cinbis, Ramazan Gokberk and Verbeek, Jakob and Schmid, Cordelia},
TITLE = {{Segmentation Driven Object Detection with Fisher Vectors}},
BOOKTITLE = {{ICCV 2013 - IEEE International Conference on Computer Vision}},
YEAR = {2013},
MONTH = Dec,
PUBLISHER = {IEEE},
KEYWORDS = {object detection, fisher vectors},
ADDRESS = {Sydney, Australia},
URL = {http://hal.inria.fr/hal-00873134}
}
The paper is available here.
It is applied by default on the Pascal VOC detection challenge.
The code works on data from the Pascal dataset, re-packaged here: maskfishdet_1.1_data.tgz.
You will need a powerful Linux machine with a lot of RAM and disk space, and a Matlab license.
| Input image |
|
|
|
|
|
|
|---|---|---|---|---|---|---|
| A segment from UVA |
|
|
|
|
|
|
| Our mask |
|
|
|
|
|
|
| application of mask |
|
|
|
|
|
|