Info hash | 0f9ac75f2d9e2ce2ef7b800aa23882915f4e31fa |
Last mirror activity | 2:37 ago |
Size | 3.43MB (3,425,218 bytes) |
Added | 2014-10-08 21:03:47 |
Views | 2331 |
Hits | 12485 |
ID | 2895 |
Type | multi |
Downloaded | 225 time(s) |
Uploaded by | joecohen |
Folder | original |
Num files | 1406 files [See full list] |
Mirrors | 8 complete, 0 downloading = 8 mirror(s) total [Log in to see full list] |
original (1406 files)
watch-20.gif | 1.89kB |
watch-19.gif | 1.88kB |
watch-18.gif | 1.87kB |
watch-17.gif | 1.66kB |
watch-16.gif | 1.67kB |
watch-15.gif | 1.68kB |
watch-14.gif | 1.83kB |
watch-13.gif | 1.86kB |
watch-12.gif | 1.81kB |
watch-11.gif | 1.84kB |
watch-10.gif | 1.83kB |
watch-9.gif | 1.72kB |
watch-8.gif | 1.93kB |
watch-7.gif | 1.84kB |
watch-6.gif | 1.77kB |
watch-5.gif | 1.80kB |
watch-4.gif | 1.76kB |
watch-3.gif | 1.70kB |
watch-2.gif | 2.72kB |
watch-1.gif | 1.84kB |
turtle-20.gif | 1.71kB |
turtle-19.gif | 1.33kB |
turtle-18.gif | 1.01kB |
turtle-17.gif | 1.36kB |
turtle-16.gif | 0.92kB |
turtle-15.gif | 3.02kB |
turtle-14.gif | 2.37kB |
turtle-13.gif | 3.07kB |
turtle-12.gif | 1.49kB |
turtle-11.gif | 1.51kB |
turtle-10.gif | 1.10kB |
turtle-9.gif | 1.25kB |
turtle-8.gif | 2.85kB |
turtle-7.gif | 2.36kB |
turtle-6.gif | 1.32kB |
turtle-5.gif | 2.46kB |
turtle-4.gif | 1.94kB |
turtle-3.gif | 2.56kB |
turtle-2.gif | 1.87kB |
turtle-1.gif | 2.04kB |
truck-20.gif | 1.59kB |
truck-19.gif | 1.59kB |
truck-18.gif | 1.58kB |
truck-17.gif | 1.59kB |
truck-16.gif | 1.58kB |
truck-15.gif | 1.58kB |
truck-14.gif | 1.57kB |
truck-13.gif | 1.57kB |
truck-12.gif | 1.55kB |
Type: Dataset
Tags:
Bibtex:
Tags:
Bibtex:
@article{, title = {MPEG-7 Core Experiment CE-Shape-1}, journal = {}, author = {Richard Ralph}, year = {1999}, url = {http://www.dabi.temple.edu/~shape/MPEG7/dataset.html}, license = {}, abstract = {Here are the first shapes from each class in the MPEG-7 Core Experiment CE-Shape-1 Test Set. MPEG-7 Core Experiment CE-Shape-1 [?] is a popular database for shape matching evaluation consisting of 70 shape categories, where each category is represented by 20 different images with high intra-class variability. The shapes are defined by a binary mask outlining the objects. The evaluation protocol for this retrieval task is the bullseye rating, in which each image is used as reference and compared to all of the other images. The mean percentage of correct images in the top 40 matches (the 40 images with the lowest shape similarity values) is taken as bullseye rating. The Latecki group maintains an overview of recent results here: http://knight.cis.temple.edu/ shape/MPEG7/results.html. Download MPEG-7 Core Experiment CE-Shape-1 http://www.cis.temple.edu/ latecki/TestData/mpeg7shapeB.tar.gz Note: It raises interesting questions how to define the shape of an object, as there are very similar objects (apples and device9) in two categories, however the octopus category has much larger intra-class variances and is still the same category. } }