Zobrazeno 1 - 10
of 304
pro vyhledávání: '"Shah, Nisarg A."'
We study letter grading schemes, which are routinely employed for evaluating student performance. Typically, a numerical score obtained via one or more evaluations is converted into a letter grade (e.g., A+, B-, etc.) by associating a disjoint interv
Externí odkaz:
http://arxiv.org/abs/2406.15405
Automated surgical step recognition is an important task that can significantly improve patient safety and decision-making during surgeries. Existing state-of-the-art methods for surgical step recognition either rely on separate, multi-stage modeling
Externí odkaz:
http://arxiv.org/abs/2307.11081
We study the problem of designing voting rules that take as input the ordinal preferences of $n$ agents over a set of $m$ alternatives and output a single alternative, aiming to optimize the overall happiness of the agents. The input to the voting ru
Externí odkaz:
http://arxiv.org/abs/2305.19453
Autor:
Banerjee, Siddhartha, Gkatzelis, Vasilis, Hossain, Safwan, Jin, Billy, Micha, Evi, Shah, Nisarg
We design online algorithms for the fair allocation of public goods to a set of $N$ agents over a sequence of $T$ rounds and focus on improving their performance using predictions. In the basic model, a public good arrives in each round, the algorith
Externí odkaz:
http://arxiv.org/abs/2209.15305
In this paper we present a novel self-supervised method to anticipate the depth estimate for a future, unobserved real-world urban scene. This work is the first to explore self-supervised learning for estimation of monocular depth of future unobserve
Externí odkaz:
http://arxiv.org/abs/2207.00506
A voting rule decides on a probability distribution over a set of m alternatives, based on rankings of those alternatives provided by agents. We assume that agents have cardinal utility functions over the alternatives, but voting rules have access to
Externí odkaz:
http://arxiv.org/abs/2205.15760
Autor:
Shah, Nisarg A., Bharaj, Gaurav
We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation. Our method is device agnostic, and can optimize an autoencoder for a given C
Externí odkaz:
http://arxiv.org/abs/2203.10363
In the classical version of online bipartite matching, there is a given set of offline vertices (aka agents) and another set of vertices (aka items) that arrive online. When each item arrives, its incident edges -- the agents who like the item -- are
Externí odkaz:
http://arxiv.org/abs/2203.03751
Development of perceptual image quality assessment (IQA) metrics has been of significant interest to computer vision community. The aim of these metrics is to model quality of an image as perceived by humans. Recent works in Full-reference IQA resear
Externí odkaz:
http://arxiv.org/abs/2203.00845
Autor:
Fang, Huihui, Li, Fei, Fu, Huazhu, Sun, Xu, Cao, Xingxing, Lin, Fengbin, Son, Jaemin, Kim, Sunho, Quellec, Gwenole, Matta, Sarah, Shankaranarayana, Sharath M, Chen, Yi-Ting, Wang, Chuen-heng, Shah, Nisarg A., Lee, Chia-Yen, Hsu, Chih-Chung, Xie, Hai, Lei, Baiying, Baid, Ujjwal, Innani, Shubham, Dang, Kang, Shi, Wenxiu, Kamble, Ravi, Singhal, Nitin, Wang, Ching-Wei, Lo, Shih-Chang, Orlando, José Ignacio, Bogunović, Hrvoje, Zhang, Xiulan, Xu, Yanwu, group, iChallenge-AMD study
Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photogra
Externí odkaz:
http://arxiv.org/abs/2202.07983