Xueyu Kang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xueyu Kang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Changzhi Wang
School of Computer Science, Shandong Xiehe University, Jinan 250109, China
1 shared publication - Hailing Feng
School of Computer Science, Shandong Xiehe University, Jinan 250109, China
1 shared publication - Houlin Wang
School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan 250399, China
1 shared publication - Qi Zhang
School of Computer Science, Shandong Xiehe University, Jinan 250109, China
1 shared publication - Xinyu Yang
School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
1 shared publication - Zhiquan Feng
School of Computer Science, Shandong Xiehe University, Jinan 250109, China
1 shared publication
Latest Publications
- Open Access
- 27 October 2026
- Published by MDPI AG in Biomimetics
- Vol. 11 (11) , 778
Hybrid Causal Action Reasoning for Temporal Action Detection
Human action understanding aims to detect action instances and classify them in videos. Existing methods capture contextual dependencies through temporal feature aggregation or attention-based interactions. However, these methods primarily rely on visual features to establish relationships, making them susceptible to interference from background content or irrelevant action frames. To address this limitation, we propose Hybrid Causal Action Reasoning (HCAR), a framework for modeling causal correlations between action proposals. Specifically, we design a Hybrid Causality-Aware Attention (HCAA) to refine the semantic representations of proposal classes. To further characterize relations between adjacent proposals, an ordered relation branch evaluates the refined representations in temporal order, while a hyperbolic branch measures hierarchical semantic relatedness between action categories in the Poincaré ball. The outputs of these branches are combined to obtain causal correlation scores, which are subsequently used to refine action proposals. Extensive experiments on THUMOS14 and ActivityNet-1.3 demonstrate the effectiveness of our HCAR.
- 27 October 2026
- Published by MDPI AG in Biomimetics
- Vol. 11 (11) , 778
Open AccessHybrid Causal Action Reasoning for Temporal Action Detection
Human action understanding aims to detect action instances and classify them in videos. Existing methods capture contextual dependencies through temporal feature aggregation or attention-based interactions. However, these methods primarily rely on visual features to establish relationships, making them susceptible to interference from background content or irrelevant action frames. To address this limitation, we propose Hybrid Causal Action Reasoning (HCAR), a framework for modeling causal correlations between action proposals. Specifically, we design a Hybrid Causality-Aware Attention (HCAA) to refine the semantic representations of proposal classes. To further characterize relations between adjacent proposals, an ordered relation branch evaluates the refined representations in temporal order, while a hyperbolic branch measures hierarchical semantic relatedness between action categories in the Poincaré ball. The outputs of these branches are combined to obtain causal correlation scores, which are subsequently used to refine action proposals. Extensive experiments on THUMOS14 and ActivityNet-1.3 demonstrate the effectiveness of our HCAR.