2021 |
| Poursaeed, Omid; Jiang, Tianxing; Yang, Harry; Belongie, Serge; Lim, Ser-Nam Robustness and Generalization via Generative Adversarial Training International Conference on Computer Vision (ICCV), Virtual, 2021. (Links | BibTeX) @conference{Poursaeed2021,
title = {Robustness and Generalization via Generative Adversarial Training},
author = {Omid Poursaeed and Tianxing Jiang and Harry Yang and Serge Belongie and Ser-Nam Lim},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2021/08/02380.pdf},
year = {2021},
date = {2021-10-11},
booktitle = {International Conference on Computer Vision (ICCV)},
address = {Virtual},
keywords = {}
}
|
2020 |
| Poursaeed, Omid; Jiang, Tianxing; Qiao, Quintessa; Xu, Nayun; Kim, Vladimir Self-supervised Learning of Point Clouds via Orientation Estimation International Conference on 3D Vision (3DV), 2020. (Links | BibTeX) @article{poursaeed2020self,
title = {Self-supervised Learning of Point Clouds via Orientation Estimation},
author = {Omid Poursaeed and Tianxing Jiang and Quintessa Qiao and Nayun Xu and Vladimir Kim},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2020/10/Self_supervised_Point_Clouds.pdf},
year = {2020},
date = {2020-10-02},
journal = {International Conference on 3D Vision (3DV)},
keywords = {}
}
|
| Poursaeed, Omid; Fisher, Matthew; Aigerman, Noam; Kim, Vladimir Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling European Conference on Computer Vision (ECCV) , 2020. (Links | BibTeX) @conference{Poursaeed2020,
title = {Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling},
author = {Omid Poursaeed and Matthew Fisher and Noam Aigerman and Vladimir Kim},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2020/07/HybridNet-1.pdf},
year = {2020},
date = {2020-07-04},
booktitle = {European Conference on Computer Vision (ECCV) },
journal = {European Conference on Computer Vision (ECCV)},
keywords = {}
}
|
| Poursaeed, Omid; Kim, Vladimir; Shechtman, Eli; Saito, Jun; Belongie, Serge Neural Puppet: Generative Layered Cartoon Characters Winter Conference on Applications of Computer Vision (WACV), 2020. (Links | BibTeX) @conference{poursaeed2019neural,
title = {Neural Puppet: Generative Layered Cartoon Characters},
author = {Omid Poursaeed and Vladimir Kim and Eli Shechtman and Jun Saito and Serge Belongie },
url = {https://vision.cornell.edu/se3/wp-content/uploads/2019/12/Neural_Puppet-1.pdf},
year = {2020},
date = {2020-03-02},
booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
keywords = {}
}
|
2019 |
| Bagdasaryan, Eugene; Poursaeed, Omid; Shmatikov, Vitaly Differential Privacy has Disparate Impact on Model Accuracy Neural Information Processing Systems (NeurIPS), 2019. (Links | BibTeX) @conference{bagdasaryan2019differential,
title = {Differential Privacy has Disparate Impact on Model Accuracy},
author = {Eugene Bagdasaryan and Omid Poursaeed and Vitaly Shmatikov},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2019/12/differential-privacy-1.pdf},
year = {2019},
date = {2019-11-21},
booktitle = {Neural Information Processing Systems (NeurIPS)},
keywords = {}
}
|
2018 |
| Poursaeed, Omid; Yang, Guandao; Prakash, Aditya; Jiang, Hanqing; Fang, Qiuren; Hariharan, Bharath; Belongie, Serge Deep Fundamental Matrix Estimation without Correspondences European Conference on Computer Vision Workshops, Munich, Germany, 2018. (Links | BibTeX) @conference{Poursaeed2018deep,
title = {Deep Fundamental Matrix Estimation without Correspondences},
author = {Omid Poursaeed and Guandao Yang and Aditya Prakash and Hanqing Jiang and Qiuren Fang and Bharath Hariharan and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2018/09/Deep-fundamental-matrix-estimation-camera-ready-2.pdf},
year = {2018},
date = {2018-09-30},
booktitle = {European Conference on Computer Vision Workshops},
address = {Munich, Germany},
keywords = {}
}
|
| Poursaeed, Omid; Katsman, Isay; Gao, Bicheng; Belongie, Serge Generative Adversarial Perturbations Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, 2018. (Links | BibTeX) @conference{Poursaeed2018,
title = {Generative Adversarial Perturbations},
author = {Omid Poursaeed and Isay Katsman and Bicheng Gao and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2018/03/2387.pdf, https://vision.cornell.edu/se3/wp-content/uploads/2018/03/2387-supp.pdf},
year = {2018},
date = {2018-06-18},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
address = {Salt Lake City, UT},
keywords = {}
}
|
| Poursaeed, Omid; Matera, Tomas; Belongie, Serge Vision-based Real Estate Price Estimation Machine Vision and Applications, 2018. (Abstract | Links | BibTeX) @article{poursaeed2017vision,
title = {Vision-based Real Estate Price Estimation},
author = {Omid Poursaeed and Tomas Matera and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2021/05/Vision_based_Real_Estate_Price_Estimation.pdf},
year = {2018},
date = {2018-03-20},
journal = {Machine Vision and Applications},
abstract = {Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates.},
keywords = {}
}
Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates.
|
2017 |
| Huang, Xun; Li, Yixuan; Poursaeed, Omid; Hopcroft, John; Belongie, Serge Stacked Generative Adversarial Networks Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017. (Links | BibTeX) @conference{huang2017sgan,
title = {Stacked Generative Adversarial Networks},
author = {Xun Huang and Yixuan Li and Omid Poursaeed and John Hopcroft and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2017/04/1612.04357-2.pdf},
year = {2017},
date = {2017-07-21},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
journal = {CVPR},
address = {Honolulu, HI},
keywords = {}
}
|