Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Cai, Bill"'
Autor:
Lee, Seungyeop, Peterson, Knut, Arezoomandan, Solmaz, Cai, Bill, Li, Peihan, Zhou, Lifeng, Han, David
A major obstacle to the development of effective monocular depth estimation algorithms is the difficulty in obtaining high-quality depth data that corresponds to collected RGB images. Collecting this data is time-consuming and costly, and even data c
Externí odkaz:
http://arxiv.org/abs/2405.01113
Dictionary example sentences play an important role in illustrating word definitions and usage, but manually creating quality sentences is challenging. Prior works have demonstrated that language models can be trained to generate example sentences. H
Externí odkaz:
http://arxiv.org/abs/2404.06224
We investigate the problem of energy-constrained planning for a cooperative system of an Unmanned Ground Vehicles (UGV) and an Unmanned Aerial Vehicle (UAV). In scenarios where the UGV serves as a mobile base to ferry the UAV and as a charging statio
Externí odkaz:
http://arxiv.org/abs/2310.07729
In this paper, we propose Domain Agnostic Meta Score-based Learning (DAMSL), a novel, versatile and highly effective solution that delivers significant out-performance over state-of-the-art methods for cross-domain few-shot learning. We identify key
Externí odkaz:
http://arxiv.org/abs/2106.03041
While many deep learning methods have seen significant success in tackling the problem of domain adaptation and few-shot learning separately, far fewer methods are able to jointly tackle both problems in Cross-Domain Few-Shot Learning (CD-FSL). This
Externí odkaz:
http://arxiv.org/abs/2012.01784
Autor:
Cai, Bill Yang.
Thesis: S.M., Massachusetts Institute of Technology, Computation for Design and Optimization Program, 2018
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 73-77).
A modern city generates a large volume
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 73-77).
A modern city generates a large volume
Externí odkaz:
https://hdl.handle.net/1721.1/122317
Urban canopy cover is important to mitigate the impact of climate change. Yet, existing quantification of urban greenery is either manual and not scalable, or use traditional computer vision methods that are inaccurate. We train deep convolutional ne
Externí odkaz:
http://arxiv.org/abs/1912.02109
Parking spaces are costly to build, parking payments are difficult to enforce, and drivers waste an excessive amount of time searching for empty lots. Accurate quantification would inform developers and municipalities in space allocation and design,
Externí odkaz:
http://arxiv.org/abs/1902.07401
Autor:
Wang, Zhoutong, Liang, Qianhui, Duarte, Fabio, Zhang, Fan, Charron, Louis, Johnsen, Lenna, Cai, Bill, Ratti, Carlo
Legibility is the extent to which a space can be easily recognized. Evaluating legibility is particularly desirable in indoor spaces, since it has a large impact on human behavior and the efficiency of space utilization. However, indoor space legibil
Externí odkaz:
http://arxiv.org/abs/1901.10553
This paper applies state-of-the-art techniques in deep learning and computer vision to measure visual similarities between architectural designs by different architects. Using a dataset consisting of web scraped images and an original collection of i
Externí odkaz:
http://arxiv.org/abs/1812.01714