Tomas Matera
Publications
2018 | |
Poursaeed, Omid; Matera, Tomas; Belongie, Serge Vision-based Real Estate Price Estimation Machine Vision and Applications, 2018. @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. |
|
2016 | |
Veit, Andreas; Matera, Tomas; Neumann, Lukas; Matas, Jiri; Belongie, Serge COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images arXiv preprint arXiv:1601.07140, 2016. @conference{veit2016cocotext, title = {COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images}, author = {Andreas Veit and Tomas Matera and Lukas Neumann and Jiri Matas and Serge Belongie}, url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/01/1601.07140v1.pdf}, year = {2016}, date = {2016-01-26}, booktitle = {arXiv preprint arXiv:1601.07140}, keywords = {} } |
|
2014 | |
Matera, Tomas; Jakes, Jan; Cheng, Munan; Belongie, Serge A User Friendly Crowdsourcing Task Manager Workshop on Computer Vision and Human Computation, Columbus, OH, 2014. @inproceedings{504, title = {A User Friendly Crowdsourcing Task Manager}, author = {Tomas Matera and Jan Jakes and Munan Cheng and Serge Belongie}, url = {/se3/wp-content/uploads/2014/09/materauser2014.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Workshop on Computer Vision and Human Computation}, address = {Columbus, OH}, keywords = {} } |