Zhengwei Shen

Zhengwei Shen

Auto-generated profile, based on publicly available information

Zhengwei Shen

School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2024 in Alexandria Engineering Journal
Verified
Journal Article
Open access
ZSZhengwei Shen
Zhengwei Shen
FQFeiwei Qin
Feiwei Qin
RGRuiquan Ge
Ruiquan Ge
CWChangmiao Wang
Changmiao Wang
KZKai Zhang
Kai Zhang
JHJie Huang
Jie Huang

10 January 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
FQFeiwei Qin
Feiwei Qin
ZSZhengwei Shen
Zhengwei Shen
RGRuiquan Ge
Ruiquan Ge
KZKai Zhang
Kai Zhang
FLFei Lin
Fei Lin
CWChangmiao Wang
Changmiao Wang

18 March 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
ZSZhengwei Shen
Zhengwei Shen
RXRan Xu
Ran Xu
YZYongquan Zhang
Yongquan Zhang
FQFeiwei Qin
Feiwei Qin
RGRuiquan Ge
Ruiquan Ge
MTMasahiro Toyoura
Masahiro Toyoura
The advent of deep learning has provided solutions to many challenges posed by the Internet. However, efficient localization and recognition of vulgar segments within videos remain formidable tasks. This difficulty arises from the blurring of spatial features in vulgar actions, which can render them indistinguishable from general actions. Furthermore, issues of boundary ambiguity and over-segmentation complicate the segmentation of vulgar actions. To address these issues, we present the Boundary-Match U-shaped Temporal Convolutional Network (BMUTCN), a novel approach for the segmentation of vulgar actions. The BMUTCN employs a U-shaped architecture within an encoder–decoder temporal convolutional network to bolster feature recognition by leveraging the context of the video. Additionally, we introduce a boundary-match map that fuses action boundary inform ation with greater precision for frames that exhibit ambiguous boundaries. Moreover, we propose an adaptive internal block suppression technique, which substantially mitigates over-segmentation errors while preserving accuracy. Our methodology, tested across several public datasets as well as a bespoke vulgar dataset, has demonstrated state-of-the-art performance on the latter.