Stéphane Massonnet
ABSTRACT
Lots of machine learning models with applications in Multimedia Search are released as Open Source Software. However, integrating these models into an application is not always an easy task due to the lack of a consistent interface to run, train or distribute models. With MoZuMa, we aim at reducing this effort by providing a model zoo for image similarity, text-to-image retrieval, face recognition, object similarity search, video key-frames detection and multilingual text search implemented in a generic interface with a modular architecture. The code is released as Open Source Software at https://github.com/mozuma/mozuma.
Supplemental Material
- Jia Deng,Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255.Google Scholar
Cross Ref
- Jiankang Deng, Jia Guo, Xue Niannan, and Stefanos Zafeiriou. 2019. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In CVPR.Google Scholar
- ONNX Runtime developers. 2021. ONNX Runtime. https://onnxruntime.ai/. Version: x.y.z.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778. https://doi.org/10.1109/CVPR.2016.90Google Scholar
- Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- Qiang Meng, Shichao Zhao, Zhida Huang, and Feng Zhou. 2021. MagFace: A Universal Representation for Face Recognition and Quality Assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 14225--14234.Google ScholarCross Ref
- Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. https://proceedings.mlr.press/v139/radford21a.htmlGoogle Scholar
- Nils Reimers and Iryna Gurevych. 2020. Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. https://arxiv.org/abs/2004.09813Google ScholarCross Ref
- K. Zhang, Z. Zhang, Z. Li, and Y. Qiao. 2016. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Processing Letters 23, 10 (Oct 2016), 1499--1503. https://doi.org/10.1109/LSP.2016.2603342Google ScholarCross Ref
- Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, LijuanWang, Yejin Choi, and Jianfeng Gao. 2021. VinVL: Revisiting Visual Representations in Vision-Language Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5579--5588.Google ScholarCross Ref
- Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million Image Database for Scene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2017).Google Scholar
Index Terms
- MoZuMa: A Model Zoo for Multimedia Applications
Recommendations
Licenses of Open Source Software and their Economic Values
SAINT-W '05: Proceedings of the 2005 Symposium on Applications and the Internet WorkshopsLicenses of open source software (OSS) are quiet various but can be categorised into three. That is GPL (GNU general Public License) like, LGPL (GNU Lesser general Public License) like, or MPL (Mozilla Public License) like. Although there are numbers of ...
Microsoft, Open Source and the software ecosystem: of predators and prey—the leopard can change its spots
Over the past few years, Microsoft has promoted a project called 'Shared Source Initiative', which allows certain customers (e.g., research institutions and independent software vendors) access to its source code on a restricted basis. As part of this ...
Open Source Drives Innovation
Engineers using free and open source software created many of today's most innovative products and solutions. FOSS also changed the way we develop software. IEEE Software's Open Source column first appeared in this magazine in July 2004. In this last ...
Comments