@inproceedings{825,
  author = {Thang-Long Nguyen-Ho and Minh-Khoi Pham and Tien-Phat Nguyen and Hai-Dang Nguyen and Minh Do and Tam Nguyen and Minh-Triet Tran},
  title = {Text Query based Traffic Video Event Retrieval with Global-Local Fusion Embedding},
  abstract = {Retrieving event videos based on textual description is a promising research topic in the fast-growing data field. Since traffic data increases every day, there is an essential need of an intelligent traffic system to speed up the traffic event search. We propose a multi-module system that outputs accurate results. Our solution considers neighboring entities related to the mentioned object to represent an event by rule-based, which can represent an event by the relationship of multiple objects. We also propose to add a modified model from last year's Alibaba model with an explainable architecture. As the traffic data is vehicle-centric, we apply two language and image modules to analyze the input data and obtain the global properties of the context and the internal attributes of the vehicle. We introduce a one-on-one dual training strategy for each representation vector to optimize the interior features for the query. Finally, a refinement module gathers previous results to enhance the final retrieval result. We benchmarked our approach on the data of the AI City Challenge 2022 and obtained the competitive results at an MMR of 0.3611. We were ranked in the top 4 on 50\% of the test set and in the top 5 on the full set.},
  year = {2022},
  journal = {CVPR 2022 Workshop},
  chapter = {3133},
  pages = {8},
  month = {06},
  url = {https://par.nsf.gov/biblio/10428272},
  doi = {10.1109/CVPRW56347.2022.00353},
}