XLXinxin Liu

Xinxin Liu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


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


Latest Publications

  • Learning From Selective Attention for Pedestrian Collision Risk Assessment

    by Hui Gao, Benfei Wang, Zhixin Huang, Xinxin Liu, Chao Gou

    Accurate risk assessment is essential for ensuring the safety and efficiency of decision-making processes in autonomous driving systems. Existing studies have primarily focused on modeling traffic environments to capture spatial and interactive relationships among road users. However, achieving human-like scene comprehension remains a formidable challenge. Inspired by human visual cognition mechanisms, this work introduces a novel scanpath-enhanced risk assessment model designed to capture key elements effectively in driving scenarios. The proposed model integrates simulated driver attention distributions and visual behavior patterns, represented through scanpath imagery, to improve critical feature extraction and risk evaluation. Additionally, a specialized node update strategy is presented, specifically aimed at optimizing the ego-car node within heterogeneous traffic contexts. By incorporating simulated attention mechanisms, interactive reasoning, and human drivers’ prior knowledge, the model achieves a more accurate understanding of, and prediction of, the behavioral intentions and interaction dynamics of traffic participants. Extensive experiments on IESG, Non-IESG, and the 1043-Carla datasets demonstrate the superiority of the proposed model compared to existing methods.


  • Edge Feature-Enhanced Network for Collision Risk Assessment Using Traffic Scene Graphs

    by Xinxin Liu, Yuchen Zhou, Yongqi Ye, Chao Gou

    A traffic scene graph effectively models relationships among traffic entities and holds significant importance in enhancing the high-level scene-understanding capabilities of autonomous driving systems. Graph-learning-based methods are widely employed to model structural traffic scene graphs. However, for the collision risk assessment task, the majority of current state-of-the-art graph-learning models overlook essential visual appearance features and do not effectively incorporate the intrinsic graph edge features. In this article, we build a novel edge feature-enhanced collision risk assessment framework that can fully exploit edge features representing the relationships among traffic entities. Specifically, we introduce a node feature-enhanced module to fuse the visual appearance features and implement dynamic traffic scene graph extraction. Next, we design a novel hierarchical node feature update strategy that leverages cross-attention to sufficiently integrate the edge features. Moreover, the temporal transformer encoder is employed to capture the temporal dynamics in driving scenario video. Extensive experiments on the real-world IESG dataset and simulated 1043-carla-sg demonstrate the proposed approach’s superiority, achieving state-of-the-art performance in accuracy (Acc), area under the curve (AUC), and F1-score metrics.


  • HKTSG: A Hierarchical Knowledge-guided Traffic Scene Graph Representation Learning Framework for Intelligent Vehicles

    by Yuchen Zhou, Xinxin Liu, Zipeng Guo, Ming Cai, Chao Gou

    Autonomous driving, propelled by data-driven approaches, has made significant advancements. However, challenges remain, particularly in achieving human-like cognitive capabilities within complex traffic scenarios and addressing limitations in model reliability and interpretability. To address these challenges, we draw inspiration from neuroscience and propose the Hierarchical Knowledge-Guided Traffic Scene Graph Representation Learning Framework, denoted as HKTSG. This framework integrates a human-like hierarchical cognition process into a data-driven learning paradigm, leveraging both domain-general and domain-specific knowledge. It systematically learns the visual features of global environments, spatial relations, dynamic interactions among all traffic instances, as well as the distinctive behavioral patterns and intrinsic associations of pedestrians and vehicles. HKTSG facilitates mutual learning across multiple levels and instances, fostering a comprehensive understanding of complex traffic scenarios. Extensive experiments demonstrate the effectiveness and versatility of our framework, consistently achieving state-of-the-art performance across diverse datasets and tasks, including IESG and Non-IESG for the pedestrian collision prediction task, and 571-Honda and 1043-Carla for the subjective risk assessment task.


  • Learning From Interaction-Enhanced Scene Graph for Pedestrian Collision Risk Assessment

    by Xinxin Liu, Yuchen Zhou, Chao Gou

    Collision risk assessment aims to provide a sub-jective cognitive comprehension of the risk level in driving scenarios, which is critical for the safety of autonomous driving systems. Pedestrian crossing scenarios contain intricate human-vehicle interactions. Hence, it is important to capture the rich relations between traffic entities and to assess the collision risk promptly to ensure safety. Existing studies focus on modeling the spatial relationships between the ego-vehicle and other vehicles in typical traffic scenarios, while ignoring the complex interactions between pedestrians and the ego-vehicle in critical driving scenarios. To address this issue, we propose a novel approach that involves constructing traffic scene graphs with enhanced vehicle-pedestrian interactions, along with introducing an innovative deep model built upon Transformer and GCN for pedestrian collision risk assessment. Specifically, to facilitate spatio-temporal modeling of traffic scene graph sequence, we propose a novel unified framework that integrates Multi-Relation Graph Convolution Network (MR-GCN) and Temporal Trans-former Encoder. In addition, two variants of traffic scene graph datasets termed as Interaction-Enhanced Scene Graph (IESG) and None-Interaction-Enhanced Scene Graph (Non-IESG) are created for the purpose of assessing pedestrian collision risk, utilizing the CAP-DATA and JAAD respectively. Experiments are conducted on our newly created traffic scene graph datasets of pedestrian crossing scenes. The results on the IESG dataset show that our model outperforms the baseline model with higher accuracy (94% vs. 84%), higher AUC (98% vs. 89%), and higher F1-score (93% vs. 84%). IESG and Non-IESG datasets are available at https://github.com/Pedestrian-Crossing-Collision-Risk-Assessment-Datasets .