Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Huang, Sangxia"'
We address the challenges in estimating 3D human poses from multiple views under occlusion and with limited overlapping views. We approach multi-view, single-person 3D human pose reconstruction as a regression problem and propose a novel encoder-deco
Externí odkaz:
http://arxiv.org/abs/2312.17106
In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation strategy inc
Externí odkaz:
http://arxiv.org/abs/2202.02232
Autor:
Kurakin, Alexey, Goodfellow, Ian, Bengio, Samy, Dong, Yinpeng, Liao, Fangzhou, Liang, Ming, Pang, Tianyu, Zhu, Jun, Hu, Xiaolin, Xie, Cihang, Wang, Jianyu, Zhang, Zhishuai, Ren, Zhou, Yuille, Alan, Huang, Sangxia, Zhao, Yao, Zhao, Yuzhe, Han, Zhonglin, Long, Junjiajia, Berdibekov, Yerkebulan, Akiba, Takuya, Tokui, Seiya, Abe, Motoki
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop ne
Externí odkaz:
http://arxiv.org/abs/1804.00097
We study $k$-means clustering in a semi-supervised setting. Given an oracle that returns whether two given points belong to the same cluster in a fixed optimal clustering, we investigate the following question: how many oracle queries are sufficient
Externí odkaz:
http://arxiv.org/abs/1803.00926
Autor:
Huang, Sangxia
A Probabilistically Checkable Proof (PCP) of a mathematical statement is a proof written in a special manner that allows for efficient probabilistic verification. The celebrated PCP Theorem states that for every family of statements in NP, there is a
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-168576
Initially developed for the min-knapsack problem, the knapsack cover inequalities are used in the current best relaxations for numerous combinatorial optimization problems of covering type. In spite of their widespread use, these inequalities yield l
Externí odkaz:
http://arxiv.org/abs/1609.03737
Autor:
Huang, Sangxia
We show that it is quasi-NP-hard to color 2-colorable 8-uniform hypergraphs with $2^{(\log N)^{1/10-o(1)}}$ colors, where $N$ is the number of vertices. There has been much focus on hardness of hypergraph coloring recently. Guruswami, H{\aa}stad, Har
Externí odkaz:
http://arxiv.org/abs/1504.03923
Autor:
Huang, Sangxia
We prove that for sufficiently large K, it is NP-hard to color K-colorable graphs with less than 2^{K^{1/3}} colors. This improves the previous result of K versus K^{O(log K)} in Khot [14].
Externí odkaz:
http://arxiv.org/abs/1301.5216
We explore the intricate interdependent relationship among counting problems, considered from three frameworks for such problems: Holant Problems, counting CSP and weighted H-colorings. We consider these problems for general complex valued functions
Externí odkaz:
http://arxiv.org/abs/1004.0803
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.