https://github.com/compvis/cliquecnn
Code for our paper "CliqueCNN: Deep Unsupervised Exemplar Learning" https://arxiv.org/abs/1608.08792
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.1%) to scientific vocabulary
Repository
Code for our paper "CliqueCNN: Deep Unsupervised Exemplar Learning" https://arxiv.org/abs/1608.08792
Basic Info
- Host: GitHub
- Owner: CompVis
- License: bsd-2-clause
- Language: CSS
- Default Branch: master
- Size: 640 KB
Statistics
- Stars: 2
- Watchers: 4
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
CliqueCNN: Deep Unsupervised Exemplar Learning (NIPS 2016)
Based on our NIPS 2016 Paper: "CliqueCNN: Deep Unsupervised Exemplar Learning" by Miguel A. Bautista* , Artsiom Sanakoyeu* , Ekaterina Sutter, Björn Ommer.
https://asanakoy.github.io/cliquecnn/
- The paper can be downloaded from https://arxiv.org/abs/1608.08792
- Labels that we gathered for Olympic Sports can be found in olympicsportsretrieval/data
- All our pretrained models for Olympic Sports dataset can be downloaded from here
- Caffe's deploy file: olympicsportsretrieval/models/deploy.prototxt
- Evaluation script for Olympic Sports: olympicsportsretrieval/calculaterocauc.py
- Baseline HOG-LDA similarity matrices for Olympic Sports: similaritieshoglda.tar.zip (11.5 Gb)
If you find this code or data useful for your research, please cite
@inproceedings{cliquecnn2016,
title={CliqueCNN: Deep Unsupervised Exemplar Learning},
author={Bautista, Miguel A and Sanakoyeu, Artsiom and Tikhoncheva, Ekaterina and Ommer, Bj{\"o}rn},
booktitle={Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS)},
pages={3846--3854},
year={2016}
}
Owner
- Name: CompVis - Computer Vision and Learning LMU Munich
- Login: CompVis
- Kind: organization
- Email: assist.mvl@lrz.uni-muenchen.de
- Location: Germany
- Website: https://ommer-lab.com/
- Repositories: 33
- Profile: https://github.com/CompVis
Computer Vision and Learning research group at Ludwig Maximilian University of Munich (formerly Computer Vision Group at Heidelberg University)