CCChengxue Cai

Chengxue Cai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chengxue Cai has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Graph Convolutional Network for Action Recognition in Occluded Skeleton Data

    by Sicheng Jin, Kai Hu, Shuai Shen, Yongkai Cai, Chengxue Cai

    Skeleton-based human action recognition has achieved significant progress, but local occlusions and missing joints in complex environments (e.g., occlusion and low-light conditions) still degrade recognition accuracy and stability. Existing GCN-based methods aggregate features uniformly across joints and lack mechanisms to suppress unreliable observations or recover structural semantics under large-area occlusion. To address this, we propose a Robust Occlusion-Compensated Graph Convolutional Network (ROC-GCN) with two complementary components: an adaptive dropout module that suppresses spatiotemporal noise via attention-guided Bernoulli sampling with dynamic spatial–temporal fusion, and an Occlusion Compensation Graph Convolution Module that compensates occluded features through Local–Global Body-Prior-Guided Attention together with feature-guided and multi-hop aggregation. To enable systematic evaluation, we further construct two complementary occlusion benchmarks on NTU RGB+D 60/120 covering spatial-random and spatiotemporal-continuous occlusion, and additionally validate the model on a real-world missing-joint subset. On standard NTU60/120 X-Sub, ROC-GCN improves Top-1 accuracy by +0.41% and +0.48% over the baseline, with the Top-1 standard deviation reduced from 0.61 → 0.17 and 0.47 → 0.10. On the occlusion benchmarks, Top-1 accuracy further improves by +0.98% and +0.73%, and consistent gains are also observed on the real-world missing-joint validation, confirming improved robustness and training stability.

  • Open Access

    Overview of temporal action detection based on deep learning

    by Kai Hu, Chaowen Shen, Tianyan Wang, Keer Xu, Qingfeng Xia, Min Xia, Chengxue Cai

    Temporal Action Detection (TAD) aims to accurately capture each action interval in an untrimmed video and to understand human actions. This paper comprehensively surveys the state-of-the-art techniques and models used for TAD task. Firstly, it conducts comprehensive research on this field through Citespace and comprehensively introduce relevant dataset. Secondly, it summarizes three types of methods, i.e., anchor-based, boundary-based, and query-based, from the design method level. Thirdly, it summarizes three types of supervised learning methods from the level of learning methods, i.e., fully supervised, weakly supervised, and unsupervised. Finally, this paper explores the current problems, and proposes prospects in TAD task.


  • Open Access

    Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton

    by Kai Hu, Chaowen Shen, Tianyan Wang, Shuai Shen, Chengxue Cai, Huaming Huang, Min Xia

    In action recognition, obtaining skeleton data from human poses is valuable. This process can help eliminate negative effects of environmental noise, including changes in background and lighting conditions. Although GCN can learn unique action features, it fails to fully utilize the prior knowledge of human body structure and the coordination relations between limbs. To address these issues, this paper proposes a Multi-level Topological Channel Attention Network algorithm: Firstly, the Multi-level Topology and Channel Attention Module incorporates prior knowledge of human body structure using a coarse-to-fine approach, effectively extracting action features. Secondly, the Coordination Module utilizes contralateral and ipsilateral coordinated movements in human kinematics. Lastly, the Multi-scale Global Spatio-temporal Attention Module captures spatiotemporal features of different granularities and incorporates a causal convolution block and masked temporal attention to prevent non-causal relationships. This method achieved accuracy rates of 91.9% (Xsub), 96.3% (Xview), 88.5% (Xsub), and 90.3% (Xset) on NTU-RGB+D 60 and NTU-RGB+D 120, respectively.