DADa An

Da An

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

Da An has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multimodal Data Fusion-based Graph Neural Networks for Ship Trajectory Prediction

    by Jianbin Liu, Shang Zhao, Da An, Hongyuan Ding, Jianfeng Wang, Xiaohui Huang

    Global trade depends heavily on maritime transport, as ships carry more than [ ] of all international goods. The Automatic Identification System (AIS) is crucial for safe and efficient maritime navigation, providing real-time ship movement data. However, precise prediction of ship behavior is difficult because of complex environmental factors, human decisions and ship interactions. This paper introduces a novel method that uses multimodal data fusion with GNNs for improved trajectory prediction. Our model leverages AIS data in conjunction with oceanographic and meteorological data to create a ship interaction graph depicting spatial correlations. This graph-based methodology facilitates the modeling of ship dynamics, which are impacted by environmental variables and navigational regulations, by explicitly representing complex interdependencies. This proposed method yields a significant improvement in prediction accuracy, with consequential advantages for collision avoidance systems, route optimization strategies and maritime surveillance operations. Experimental findings reveal that our model achieves a higher level of accuracy than established time-series techniques in predicting ship behavior, thus setting a new benchmark.


  • Open Access

    Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding

    by Minghui Wu, Chenxu Zhao, Anyang Su, Donglin Di, Tianyu Fu, Da An, Min He, Ya Gao, Meng Ma, Kun Yan, et al.

    Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Video Subjective Multi-modal Evaluation dataset, namely Video-SME. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on Video-SME and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/mininglamp-MLLM/HMLLM