Zobrazeno 1 - 10
of 1 784
pro vyhledávání: '"Zhao Chunhui"'
Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes against domain shift problem (DSP) where data of unseen classes may be misclassified as seen classes. However, existing GZSL is still limited to seen domains. In the
Externí odkaz:
http://arxiv.org/abs/2403.14362
Zero-shot fault diagnosis (ZSFD) is capable of identifying unseen faults via predicting fault attributes labeled by human experts. We first recognize the demand of ZSFD to deal with continuous changes in industrial processes, i.e., the model's abilit
Externí odkaz:
http://arxiv.org/abs/2403.13845
Simultaneous Localization and Mapping (SLAM) plays an important role in robot autonomy. Reliability and efficiency are the two most valued features for applying SLAM in robot applications. In this paper, we consider achieving a reliable LiDAR-based S
Externí odkaz:
http://arxiv.org/abs/2310.04162
Autor:
Zhang, Songchun, Zhao, Chunhui
Weakly supervised temporal action localization (WSTAL) aims to localize actions in untrimmed videos using video-level labels. Despite recent advances, existing approaches mainly follow a localization-by-classification pipeline, generally processing e
Externí odkaz:
http://arxiv.org/abs/2308.12609
Fault diagnosis is a critical aspect of industrial safety, and supervised industrial fault diagnosis has been extensively researched. However, obtaining fault samples of all categories for model training can be challenging due to cost and safety conc
Externí odkaz:
http://arxiv.org/abs/2306.02359
Autor:
Abdelmeguid, Mohamed, Zhao, Chunhui, Yalcinkaya, Esref, Gazetas, George, Elbanna, Ahmed, Rosakis, Ares
Publikováno v:
Commun Earth Environ 4, 456 (2023)
The 2023 M7.8 Kahramanmara\c{s}/Pazarcik earthquake was larger and more destructive than what had been expected. Here we analyzed near-field seismic records and developed a dynamic rupture model that reconciles different currently conflicting inversi
Externí odkaz:
http://arxiv.org/abs/2305.01825
Embedding-aware generative model (EAGM) addresses the data insufficiency problem for zero-shot learning (ZSL) by constructing a generator between semantic and visual feature spaces. Thanks to the predefined benchmark and protocols, the number of prop
Externí odkaz:
http://arxiv.org/abs/2302.04060
Autor:
Zhang, Songchun, Zhao, Chunhui
Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dy
Externí odkaz:
http://arxiv.org/abs/2301.05871
Publikováno v:
In Aquacultural Engineering November 2024 107
Autor:
Hong, Xiaodong, Chen, Wanke, Liao, Zuwei, Fan, Xiaoqiang, Sun, Jingyuan, Yang, Yao, Zhao, Chunhui, Wang, Jingdai, Yang, Yongrong
Publikováno v:
In Chinese Journal of Chemical Engineering November 2024 75:110-120