Zehao Liu

Zehao Liu

Auto-generated profile, based on publicly available information

Zehao Liu

School of Control Science and Engineering, Shandong University, Jinan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 April 2022 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
QLQiang Li
Qiang Li
Chunsheng LiuChunsheng Liu
Chunsheng Liu
Faliang ChangFaliang Chang
Faliang Chang
SLShuang Li
Shuang Li
HLHui Liu
Hui Liu
ZLZehao Liu
Zehao Liu
Driver attention prediction can solve the problem of ‘Where should the driver pay attention?’, Most previous methods are designed to predict regional attention with redundant regions. Furthermore, popular spatial-temporal feature extraction networks such as ConvLSTM and 3D-CNN are difficult to achieve real-time. To overcome these difficulties, we propose an Adaptive Short-temporal Induced Aware Fusion Network (ASIAF-Net) for region-level and object-level driver attention prediction. 1 In ASIAF-Net, we design an Attention Related Spatial Feature Encoder (AF-Encoder) and an Induced Aware Fusion Network (IAF-Net) as the main network; with an Association Analysis Cell (AAC), the AF-Encoder makes it possible to effectively capture the relationship information of different objects. Considering most vital visual cues from moving objects, we propose a Self-adaptive Short-temporal Feature Extraction Module (SSFE-Module) to obtain inter-frame motion features. In IAF-Net, a Multi-scale Driver Attention Region Prediction Branch is designed to predict the regional attention, and an Object Saliency Estimation Branch is proposed to fuse the perception results and the regional attention map to estimate the object-level attention. Experiments show that the proposed ASIAF-Net can predict driver’s attention on regions and objects more robustly and precisely than state-of-the-art methods on three datasets, and that it achieves real-time on our ADAS platform.

14 May 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
WWWenqian Wang
Wenqian Wang
Faliang ChangFaliang Chang
Faliang Chang
Chunsheng LiuChunsheng Liu
Chunsheng Liu
BWBin Wang
Bin Wang
ZLZehao Liu
Zehao Liu
Early action prediction aiming to recognize which classes the actions belong to before they are fully conveyed is a very challenging task, owing to the insufficient discrimination information caused by the domain gaps among different temporally observed domains. Most of the existing approaches focus on using fully observed temporal domains to “guide” the partially observed domains while ignoring the discrepancies between the harder low-observed temporal domains and the easier highly observed temporal domains. The recognition models tend to learn the easier samples from the highly observed temporal domains and may lead to significant performance drops on low-observed temporal domains. Therefore, in this article, we propose a novel temporally observed domain contrastive network, namely, TODO-Net, to explicitly mine the discrimination information from the hard actions samples from the low-observed temporal domains by mitigating the domain gaps among various temporally observed domains for 3-D early action prediction. More specifically, the proposed TODO-Net is able to mine the relationship between the low-observed sequences and all the highly observed sequences belonging to the same action category to boost the recognition performance of the hard samples with fewer observed frames. We also introduce a temporal domain conditioned supervised contrastive (TD-conditioned SupCon) learning scheme to empower our TODO-Net with the ability to minimize the gaps between the temporal domains within the same action categories, meanwhile pushing apart the temporal domains belonging to different action classes. We conduct extensive experiments on two public 3-D skeleton-based activity datasets, and the results show the efficacy of the proposed TODO-Net.

17 May 2024
Verified
Conference Paper
Open access
Chunsheng LiuChunsheng Liu
Chunsheng Liu
PHPenghui Hao
Penghui Hao
Faliang ChangFaliang Chang
Faliang Chang
JZJun Zhou
Jun Zhou
ZLZehao Liu
Zehao Liu
A Dual-Attention-Guided Time-Shifted Convolutional Traffic Event Video Classification Network (DAG-Net) is proposed to classify events in traffic videos, addressing the challenges posed by complex and changing traffic environments and varying relative camera positions. Dual Attention Based Feature Enhancement Module (DAE-Module) is designed to focus on the main objects, such as cars and pedestrians, thus addressing the challenges of diverse traffic backgrounds and rapidly changing environments. Additionally, we introduce the Weighted Time Shift Module (WTS-Module) to handle rapidly changing traffic video environments by improving the network's capability to capture temporal relationships between consecutive frames. We built a Traffic Event Video Classification and Recognition (TEVCR) dataset, and experiments on the TEVCR dataset demonstrated the good performance of this method.