diplomska-text/literatura.bib

@article{wang2023wamf,
  title={WAMF-FPI: A Weight-Adaptive Multi-Feature Fusion Network for UAV Localization},
  author={Wang, Guirong and Chen, Jiahao and Dai, Ming and Zheng, Enhui},
  journal={Remote Sensing},
  volume={15},
  number={4},
  pages={910},
  year={2023},
  publisher={MDPI}
}

@article{bianchi2021uav,
  title={UAV Localization Using Autoencoded Satellite Images},
  author={Bianchi, Mollie and Barfoot, Timothy D.},
  journal={arXiv preprint arXiv:2102.05692},
  year={2021},
  url={http://arxiv.org/abs/2102.05692v1}
}

@article{zhu2022transgeo,
  title={TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization},
  author={Zhu, Sijie and Shah, Mubarak and Chen, Chen},
  journal={arXiv preprint arXiv:2204.00097},
  year={2022},
  url={http://arxiv.org/abs/2204.00097v1}
}

@article{bahdanau2015neural,
  title={Neural Machine Translation by Jointly Learning to Align and Translate},
  author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1409.0473},
  year={2015}
}

@article{dai2022finding,
  title={Finding Point with Image: An End-to-End Benchmark for Vision-based UAV Localization},
  author={Dai, Ming and Chen, Jiahao and Lu, Yusheng and Hao, Wenlong and Zheng, Enhui},
  journal={arXiv preprint arXiv:2208.06561},
  year={2022}
}

@article{vaswani2017attention,
  title={Attention is all you need},
  author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
  journal={Advances in neural information processing systems},
  volume={30},
  year={2017}
}

@inproceedings{liu2021swin,
  title={Swin transformer: Hierarchical vision transformer using shifted windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={10012--10022},
  year={2021}
}

@article{chu2021twins,
  title={Twins: Revisiting the design of spatial attention in vision transformers},
  author={Chu, Xiangxiang and Tian, Zhi and Wang, Yuqing and Zhang, Bo and Ren, Haibing and Wei, Xiaolin and Xia, Huaxia and Shen, Chunhua},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={9355--9366},
  year={2021}
}

@article{chu2021conditional,
  title={Conditional positional encodings for vision transformers},
  author={Chu, Xiangxiang and Tian, Zhi and Zhang, Bo and Wang, Xinlong and Wei, Xiaolin and Xia, Huaxia and Shen, Chunhua},
  journal={arXiv preprint arXiv:2102.10882},
  year={2021}
}

@article{vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={arXiv preprint arXiv:2010.11929},
  year={2020}
}

@article{wang2021pyramid,
  title={Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions},
  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
  journal={arXiv preprint arXiv:2102.12122},
  year={2021}
}

@article{targ2016resnet,
  title={Resnet in resnet: Generalizing residual architectures},
  author={Targ, Sasha and Almeida, Diogo and Lyman, Kevin},
  journal={arXiv preprint arXiv:1603.08029},
  year={2016}
}

% slike
@misc{analyticsvidhya2022rnn,
  author = {Analytics Vidhya},
  title = {A Brief Overview of Recurrent Neural Networks (RNN)},
  year = {2022},
  url = {https://www.analyticsvidhya.com/blog/2022/03/a-brief-overview-of-recurrent-neural-networks-rnn/},
  note = {Dostopano: 30.8.2022}
}

@misc{wikipedia_teacher_forcing_2023,
    title = {Teacher forcing},
    howpublished = {\url{https://en.wikipedia.org/wiki/Teacher_forcing}},
    publisher = {Wikipedia, The Free Encyclopedia},
    year = {2023}, 
    note = {Dostopano: 30.8.2023}
}

@misc{google_earth_studio,
  author = {Google},
  title = {Google Earth Studio},
  year = {2021}, 
  note = {Dostopano: 30.8.2023},
  url = {https://www.google.com/earth/studio/}
}

@misc{mapbox_api,
  author = {Mapbox},
  title = {Mapbox API Dokumentacija},
  year = {2021}, 
  note = {Dostopano: 30.8.2023},
  url = {https://www.mapbox.com/api-documentation/}
}

@misc{pytorch,
  author = {PyTorch},
  title = {PyTorch: Odprtokodni knjižnica za strojno učenje},
  year = {2021}, 
  note = {Dostopano: 30.8.2023},
  url = {https://pytorch.org/}
}

@misc{python,
  author = {Python},
  title = {Python: Programski jezik},
  year = {2021}, 
  note = {Dostopano: 5.9.2023},
  url = {https://www.python.org/}
}

@article{semantic_crossview,
  title={Semantic cross-view matching},
  author={F. Castaldo, A. Zamir and others},
  journal={2015 IEEE International Conference on Computer Vision Workshop (ICCVW)},
  year={2015},
  doi={https://doi.org/10.1109/iccvw.2015.137}
}


@article{crossview_image,
  title={Cross-view image geolocalization},
  author={T.-Y. Lin, S. Belongie, and J. Hays},
  journal={2013 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2013},
  doi={https://doi.org/10.1109/cvpr.2013.120}
}

@article{global_vehicle,
  title={A framework for global vehicle localization using stereo images and satellite and road maps},
  author={T. Senlet and A. Elgammal},
  journal={2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)},
  year={2011},
  doi={https://doi.org/10.1109/iccvw.2011.6130498}
}

@article{geo_localization,
  title={Geo-localization of street views with aerial image databases},
  author={M. Bansal, H. S. Sawhney and others},
  journal={Proceedings of the 19th ACM international conference on Multimedia - MM '11},
  year={2011},
  doi={https://doi.org/10.1145/2072298.2071954}
}

@article{location_dependence,
  title={On the location dependence of convolutional neural network features},
  author={S. Workman and N. Jacobs},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2015},
  doi={https://doi.org/10.1109/cvprw.2015.7301385}
}

@article{wide_area,
  title={Wide-area image geolocalization with aerial reference imagery},
  author={S. Workman, R. Souvenir, and N. Jacobs},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  doi={https://doi.org/10.1109/cvpr.2005.202}
}

@article{deep_representations,
  title={Learning deep representations for ground-to-aerial geolocalization},
  author={T.-Y. Lin, Y. Cui and others},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  doi={https://doi.org/10.1109/cvpr.2015.7299135}
}

@article{cvm_net,
  title={CVM-net: Cross-view matching network for image-based ground-to-aerial geo-localization},
  author={S. Hu, M. Feng and others},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  doi={https://doi.org/10.1109/cvpr.2018.00758}
}

@article{optimal_transport,
  title={Optimal feature transport for cross-view image geo-localization},
  author={Y. Shi, X. Yu and others},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2020},
  volume={34},
  number={07},
  pages={11 990–11 997},
  doi={https://doi.org/10.1609/aaai.v34i07.6875}
}

@article{cvusa,
  title={Predicting Ground-Level Scene Layout from Aerial Imagery},
  author={Liu, Liu and Li, Hongdong},
  journal={arXiv preprint arXiv:1612.02709},
  year={2016},
  url={http://arxiv.org/abs/1612.02709v1}
}

@article{university1652,
  title={University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization},
  author={Zheng, Zhedong and Ruan, Tao and Wei, Yunchao and Yang, Yi and Yang, Tao Mei},
  journal={arXiv preprint arXiv:2002.12186},
  year={2020},
  url={http://arxiv.org/abs/2002.12186v1}
}

@article{cvact,
  title={Lending Orientation to Neural Networks for Cross-view Geo-localization},
  author={Liu, Liu and Li, Hongdong},
  journal={arXiv preprint arXiv:1903.12351},
  year={2019},
  url={http://arxiv.org/abs/1903.12351v1}
}

@article{dey2017signet,
  title={SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification},
  author={Dey, Sounak and Dutta, Anjan and Toledo, J. Ignacio and Ghosh, Suman K. and Llados, Josep and Pal, Umapada},
  journal={arXiv preprint arXiv:1707.02131},
  year={2017},
  url={http://arxiv.org/abs/1707.02131v2}
}

@article{touvron2020training,
  title={Training data-efficient image transformers \& distillation through attention},
  author={Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jégou, Hervé},
  journal={arXiv preprint arXiv:2012.12877},
  year={2020},
  url={http://arxiv.org/abs/2012.12877v2}
}