Zobrazeno 1 - 10
of 13 090
pro vyhledávání: '"Xiao, Jian"'
Autor:
Wu, Ruituo, Chen, Yang, Xiao, Jian, Li, Bing, Fan, Jicong, Dufaux, Frédéric, Zhu, Ce, Liu, Yipeng
Cooperation between temporal convolutional networks (TCN) and graph convolutional networks (GCN) as a processing module has shown promising results in skeleton-based video anomaly detection (SVAD). However, to maintain a lightweight model with low co
Externí odkaz:
http://arxiv.org/abs/2406.02976
Autor:
Xiao, Jian-Ci
Luo, Rao and Xiong [Topol. Appl. 322 (2022), 108271] conjectured that if a planar self-similar iterated function system with the open set condition does not involve rotations or reflections, then every connected component of the attractor is locally
Externí odkaz:
http://arxiv.org/abs/2403.19999
Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation has created a bottleneck for model generalization. To minimize annotat
Externí odkaz:
http://arxiv.org/abs/2403.14350
A near-field wideband beamforming scheme is investigated for reconfigurable intelligent surface (RIS) assisted multiple-input multiple-output (MIMO) systems, in which a deep learning-based end-to-end (E2E) optimization framework is proposed to maximi
Externí odkaz:
http://arxiv.org/abs/2401.11141
Autor:
Xiao, Jian-Ci
Let $K\subset\mathbb{R}^d$ be a self-similar set generated by an iterated function system $\{\varphi_i\}_{i=1}^m$ satisfying the strong separation condition and let $f$ be a contracting similitude with $f(K)\subset K$. We show that $f(K)$ is relative
Externí odkaz:
http://arxiv.org/abs/2310.12043
Due to the large volume of recording, the complete spontaneity, and the flexible pick-up and drop-off locations, taxi data portrays a realistic and detailed picture of urban space use to a certain extent. The spatial arrangement of pick-up and drop-o
Externí odkaz:
http://arxiv.org/abs/2310.11806
Previous approaches to detecting human anomalies in videos have typically relied on implicit modeling by directly applying the model to video or skeleton data, potentially resulting in inaccurate modeling of motion information. In this paper, we cond
Externí odkaz:
http://arxiv.org/abs/2309.15662
Video anomaly detection is a complex task, and the principle of "divide and conquer" is often regarded as an effective approach to tackling intricate issues. It's noteworthy that recent methods in video anomaly detection have revealed the application
Externí odkaz:
http://arxiv.org/abs/2309.14622
Intra-urban origin-destination (OD) network communities evolve throughout the day, indicating changing groups of closely connected regions. Under this variation, groups of regions with high consistency of community affiliation characterize the tempor
Externí odkaz:
http://arxiv.org/abs/2309.12691
Autor:
Hu, Jiajun, Xiao, Jian
We study the numerical characterization of two dimensional hard Lefschetz classes given by the complete intersections of nef classes. In Shenfeld and van Handel's breakthrough work on the characterization of the extremals of the Alexandrov-Fenchel in
Externí odkaz:
http://arxiv.org/abs/2309.05008