上海科技大学信息科学与技术研讨会（SSIST day1) 笔记

迈不过友情╰ 2022-05-21 07:46 149阅读 0赞

### 一、Deep representations，Adversial learning and Domain Adaptation for Some Computer Vision Problems ###

Presenters:Rama Chellappa University of Maryland  
**1.Deep representations:**  
Learning Deep Representations of Fine-Grained Visual Descriptions(CVPR2016)  
本文提出了一个模型，可以用来做什么呢？就是给你一句话，搜出满足这句话的图像。可参考： [https://blog.csdn.net/cv\_family\_z/article/details/52061403?locationNum=10][https_blog.csdn.net_cv_family_z_article_details_52061403_locationNum_10]  
**2.Adversial learning:**  
主要介绍了UMD face analytics system的训练、网络结构和结果，具体可参考：[https://www.umd.edu/][https_www.umd.edu]  
原文：Deep intermodal video analytics  
链接：[https://www.iarpa.gov/index.php/research-programs/diva][https_www.iarpa.gov_index.php_research-programs_diva]  
**3.Domain Adaptation：**  
可参考：[https://blog.csdn.net/matafela/article/details/77827217][https_blog.csdn.net_matafela_article_details_77827217]  
听报告的时候拍了几张照片，手抖，勉强看一下还是可以的  
![这里写图片描述][70]  
![这里写图片描述][70 1]  
![这里写图片描述][70 2]

### 二、Visual Domain Adaptation ###

Presenters:Dong Xu The University of Sydney  
**1.Domain Adversarial Neural Network(DANN):**  
原文：Domain-Adversarial Training of Neural Networks（JMLR 2016, ICML 2015）  
链接：[https://arxiv.org/abs/1505.07818][https_arxiv.org_abs_1505.07818]  
**2.Collaborative and Adversarial Network(CAN)，Incremental CAN(iCAN):**  
原文：Collaborative and Adversarial Network for Unsupervised Domain Adaptation（CVPR 2018）  
![这里写图片描述][70 3]

### 三、3D Visual Reconstruction of Non-Rigid Dynamic Scenes ###

Presenters: Hongdong Li Australian National University  
**1.Superpixel Soup Algorithm:Dense Complex Dynamic Scene Reconstruction from a monocular camera**  
原文：Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames（ICCV 2017）  
链接：[https://arxiv.org/abs/1708.04398][https_arxiv.org_abs_1708.04398]  
**2. SFRM: Structure from Recurrent Motion for 3D human pose recovery**  
原文：Structure from Recurrent Motion: From Rigidity to Recurrency（CVPR 2018）  
链接：[https://arxiv.org/abs/1804.06510][https_arxiv.org_abs_1804.06510]

### 四、Bridging Visual-Semantic Gap via Deep Multimodal Learning ###

Presenters: Liang Wang Chinese Academy of Sciences  
![这里写图片描述][70 4]  
![这里写图片描述][70 5]  
![这里写图片描述][70 6]  
![这里写图片描述][70 7]  
![这里写图片描述][70 8]  
![这里写图片描述][70 9]  
![这里写图片描述][70 10]  
![这里写图片描述][70 11]

### 五、Deep Learning in Medical Image Synthesis,Quantification, and Prediction ###

Presenters: Dinggang Shen United Imaging Intelligence  
![这里写图片描述][70 12]

### 六、Recent Development in Image Generation and Processing ###

Presenters: Jiaya Jia Tencent  
**1.Super-resolution**  
原文：Detail-revealing Deep Video Super-resolution（ICCV 2017)  
链接：[https://arxiv.org/abs/1704.02738][https_arxiv.org_abs_1704.02738]  
**2. Deblurring**  
Scale-recurrent Network for Deep Image Deblurring(CVPR 2018)  
**3.Image Generation**  
Semi-parametric Image Synthesis(CVPR 2018)

[https_blog.csdn.net_cv_family_z_article_details_52061403_locationNum_10]: https://blog.csdn.net/cv_family_z/article/details/52061403?locationNum=10
[https_www.umd.edu]: https://www.umd.edu/
[https_www.iarpa.gov_index.php_research-programs_diva]: https://www.iarpa.gov/index.php/research-programs/diva
[https_blog.csdn.net_matafela_article_details_77827217]: https://blog.csdn.net/matafela/article/details/77827217
[70]: /images/20220521/00ef9b1feefa47b3957e2e65e9cb2d16.png
[70 1]: /images/20220521/3efc2b62a0c0404c90ff2b3ca3bfa880.png
[70 2]: /images/20220521/2a7f9b5ab16746cc88fcbbf06c7378b2.png
[https_arxiv.org_abs_1505.07818]: https://arxiv.org/abs/1505.07818
[70 3]: /images/20220521/79d19e103fab49cdbf2acf20f1caca53.png
[https_arxiv.org_abs_1708.04398]: https://arxiv.org/abs/1708.04398
[https_arxiv.org_abs_1804.06510]: https://arxiv.org/abs/1804.06510
[70 4]: /images/20220521/ae3f018db7cc47f5a85cccc09c7d2a5d.png
[70 5]: /images/20220521/617662cc64114e1a9cd5cb0c963cfe0a.png
[70 6]: /images/20220521/6ac74842c3d84945aef0de1816a5083c.png
[70 7]: /images/20220521/b4299637206846e4b6e69572738851c3.png
[70 8]: /images/20220521/a1f44c27cfda430d9b98c19da7620c8d.png
[70 9]: /images/20220521/97894bf7c45f421f9a39d0160464d460.png
[70 10]: /images/20220521/7df1720cebda4745a796915410d1c83e.png
[70 11]: /images/20220521/09d15ca769d74265a2c18cd555bb2e04.png
[70 12]: /images/20220521/74f6819b762f4282ba5c15f3be813337.png
[https_arxiv.org_abs_1704.02738]: https://arxiv.org/abs/1704.02738