Rui Xu

Rui Xu

Auto-generated profile, based on publicly available information

Rui Xu

Nanjing University of Science and Techonology, Nanjing, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
RXRui Xu
Rui Xu
LHLe Hui
Le Hui
YHYuehui Han
Yuehui Han
JQJianjun Qian
Jianjun Qian
JXJin Xie
Jin Xie

26 October 2023
Verified
Conference Paper
Open access
RXRui Xu
Rui Xu
LHLe Hui
Le Hui
YHYuehui Han
Yuehui Han
JQJianjun Qian
Jianjun Qian
JXJin Xie
Jin Xie

1 January 2017
Verified
Conference Paper
Open access
PDF file
HHHye Rin Hwang
Hye Rin Hwang
BKBerm Soo Kim
Berm Soo Kim
RXRui Xu
Rui Xu
ILIn Soo Lee
In Soo Lee

5 August 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LTLongyang Tang
Longyang Tang
BZBo Zhang
Bo Zhang
HLHui Lv
Hui Lv
RXRui Xu
Rui Xu
XTXudong Tian
Xudong Tian
YCYi Chen
Yi Chen
Temporal Action Detection (TAD) aims to identify action boundaries and their corresponding categories in untrimmed videos, playing a crucial role in long-video understanding. Prior works often struggle to balance the trade-off between capturing long-range dependencies and ensuring computational efficiency. Recently, the state space model Mamba has exhibited impressive capabilities and efficiency in long-term sequence modeling. However, current methods based on Mamba generally lack a unified framework to simultaneously address the redundancy of long-duration actions and the boundary sensitivity of short-duration actions—limitations that largely stem from Mamba’s reliance on limited state representations and its unidirectional modeling. To tackle the aforementioned challenges, we propose DilatedTAD, a novel TAD framework with an expanded receptive field. DilatedTAD leverages the Inter-Parallel DIM component (InterDIM) to integrate multi-scale temporal information, enabling a better trade-off between short-duration and long-duration action detection. InterDIM is built upon our proposed Dilated Mamba (DIM), where multiple DIM branches with different dilation rates are designed to focus on actions of varying durations. Specifically, DIM introduces a novel use of dilation to skip redundant temporal information, thereby enhancing the model’s focus on crucial boundary features. Additionally, a bidirectional modeling design is adopted in DIM to compensate for the lack of future temporal context in the original Mamba architecture. Extensive experiments show that DilatedTAD outperforms state-of-the-art methods on multiple datasets, achieving mAPs of 74.9% (THUMOS14), 42.90% (ActivityNet 1.3), 45.0% (HACS), and 26.3% and 24.3% (EPIC-Kitchens 100). Our code will be publicly available.