Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Kang, Zhiqi"'
Existing continual learning literature relies heavily on a strong assumption that tasks arrive with a balanced data stream, which is often unrealistic in real-world applications. In this work, we explore task-imbalanced continual learning (TICL) scen
Externí odkaz:
http://arxiv.org/abs/2404.14721
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised le
Externí odkaz:
http://arxiv.org/abs/2212.05102
Publikováno v:
International Journal of Computer Vision 131 (5), 1122-1140, 2023
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preserves non-rigid facial deformations in order to boost the performance of
Externí odkaz:
http://arxiv.org/abs/2204.02810
Autor:
Kang, Zhiqi, Sadeghi, Mostafa, Horaud, Radu, Alameda-Pineda, Xavier, Donley, Jacob, Kumar, Anurag
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE). Although being a common conversational feature, head movements have been ignored by past and recent studies: they challenge today's learning-based methods
Externí odkaz:
http://arxiv.org/abs/2202.00538
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a robust face alignment method that enables pixel-to-pixel warping. The method simultaneously estimates the ri
Externí odkaz:
http://arxiv.org/abs/2010.13676
Autor:
Kang, Zhiqi1 (AUTHOR), Sadeghi, Mostafa2 (AUTHOR), Horaud, Radu1 (AUTHOR) radu.horaud@inria.fr, Alameda-Pineda, Xavier1 (AUTHOR)
Publikováno v:
International Journal of Computer Vision. May2023, Vol. 131 Issue 5, p1122-1140. 19p.
Autor:
Kang, Zhiqi1,2, Spitzer, Bernhard1,2 spitzer@mpib-berlin.mpg.de
Publikováno v:
Scientific Reports. 3/5/2021, Vol. 11 Issue 1, p1-12. 12p.
Autor:
Zhang, Han, Peng, Yilang
Publikováno v:
Sociological Methods & Research; Aug2024, Vol. 53 Issue 3, p1534-1587, 54p
Autor:
Zou, YaFeng, Feng, WenHui
Publikováno v:
Soft Computing - A Fusion of Foundations, Methodologies & Applications; Jul2023, Vol. 27 Issue 14, p10107-10119, 13p
Publikováno v:
JAMA Dermatology; Oct2020, Vol. 156 Issue 10, p1057-1065, 9p