Zobrazeno 1 - 10
of 134
pro vyhledávání: '"Gao, Zhanning"'
Autor:
Liu, Chang, Yu, Han, Li, Boyang, Shen, Zhiqi, Gao, Zhanning, Ren, Peiran, Xie, Xuansong, Cui, Lizhen, Miao, Chunyan
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks. Cleaning data manually is labour-intensive and time-consuming. Previous research mostly focuses on enhancing classification models agains
Externí odkaz:
http://arxiv.org/abs/2108.01431
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence, 41(12), 3086-3099 (2018)
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video frames. With
Externí odkaz:
http://arxiv.org/abs/2106.03283
Autor:
Liu, Chang, Yu, Han, Li, Boyang, Shen, Zhiqi, Gao, Zhanning, Ren, Peiran, Xie, Xuansong, Cui, Lizhen, Miao, Chunyan
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels i
Externí odkaz:
http://arxiv.org/abs/2103.16047
Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less reliable due to the misalignm
Externí odkaz:
http://arxiv.org/abs/2012.06134
Face restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology. However, real-world image prior are often hard to simulate with precise mathematical models, which
Externí odkaz:
http://arxiv.org/abs/2010.05508
Autor:
Yang, Lingbo, Wang, Pan, Zhang, Xinfeng, Wang, Shanshe, Gao, Zhanning, Ren, Peiran, Xie, Xuansong, Ma, Siwei, Gao, Wen
Publikováno v:
2020 IEEE International Conference on Multimedia and Expo (ICME 2020)
The ability to produce convincing textural details is essential for the fidelity of synthesized person images. However, existing methods typically follow a ``warping-based'' strategy that propagates appearance features through the same pathway used f
Externí odkaz:
http://arxiv.org/abs/2005.12486
Autor:
Yang, Lingbo, Wang, Pan, Liu, Chang, Gao, Zhanning, Ren, Peiran, Zhang, Xinfeng, Wang, Shanshe, Ma, Siwei, Hua, Xiansheng, Gao, Wen
Publikováno v:
in IEEE Transactions on Image Processing, vol. 30, pp. 2422-2435, 2021
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the visual realism of fine-grained appearance details is crucial for prod
Externí odkaz:
http://arxiv.org/abs/2005.12494
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from the query by an equal margin in
Externí odkaz:
http://arxiv.org/abs/1911.07528
Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on controlling the contributions of current and previous information. Howe
Externí odkaz:
http://arxiv.org/abs/1909.01939
Autor:
Liu, Chang, Dong, Yi, Yu, Han, Shen, Zhiqi, Gao, Zhanning, Wang, Pan, Zhang, Changgong, Ren, Peiran, Xie, Xuansong, Cui, Lizhen, Miao, Chunyan
Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based promotion campaigns infeasible. The first step of automatically produ
Externí odkaz:
http://arxiv.org/abs/1908.11588