Zobrazeno 1 - 10
of 144
pro vyhledávání: '"Zhu Aichun"'
Publikováno v:
Gong-kuang zidonghua, Vol 44, Iss 11, Pp 32-36 (2018)
In view of problems that human—centered video monitoring mode had limited duration, multiple scenes were difficult to monitor at the same time, and results of manual monitoring were not processed in time, target detection method of underground pers
Externí odkaz:
https://doaj.org/article/9e4083a50206455db33ebd475eeb25a9
Publikováno v:
IEEE Access, Vol 6, Pp 21710-21718 (2018)
Compressed sensing is a novel information collection theory. Compared with the Nyquist sampling theorem, compressed sensing can obtain all the information of a signal with very few samples. The deterministic construction of the measurement matrix is
Externí odkaz:
https://doaj.org/article/36f4eff860994aa5a5d7f202b042d370
Phenotype-based screening has attracted much attention for identifying cell-active compounds. Transcriptional and proteomic profiles of cell population or single cells are informative phenotypic measures of cellular responses to perturbations. In thi
Externí odkaz:
http://arxiv.org/abs/2311.10315
Most existing methods for text-based person retrieval focus on text-to-image person retrieval. Nevertheless, due to the lack of dynamic information provided by isolated frames, the performance is hampered when the person is obscured in isolated frame
Externí odkaz:
http://arxiv.org/abs/2307.07184
Given a natural language description, text-based person retrieval aims to identify images of a target person from a large-scale person image database. Existing methods generally face a \textbf{color over-reliance problem}, which means that the models
Externí odkaz:
http://arxiv.org/abs/2209.05773
The core problem of text-based person retrieval is how to bridge the heterogeneous gap between multi-modal data. Many previous approaches contrive to learning a latent common manifold mapping paradigm following a \textbf{cross-modal distribution cons
Externí odkaz:
http://arxiv.org/abs/2209.06209
Autor:
Kan, Ge, Lü, Jinhu, Wang, Tian, Zhang, Baochang, Zhu, Aichun, Huang, Lei, Guo, Guodong, Snoussi, Hichem
Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two in
Externí odkaz:
http://arxiv.org/abs/2203.14702
Publikováno v:
In Signal Processing: Image Communication July 2024 125
Autor:
Zhu, Aichun, Wang, Zijie, Li, Yifeng, Wan, Xili, Jin, Jing, Wang, Tian, Hu, Fangqiang, Hua, Gang
Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality. Nevertheless, due to the complexity of
Externí odkaz:
http://arxiv.org/abs/2109.05534
Publikováno v:
In Image and Vision Computing February 2024 142