{"ID":2880481,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.13470","arxiv_id":"2508.13470","title":"STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models","abstract":"Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding. This paper introduces STER-VLM, a computationally efficient framework that enhances VLM performance through (1) caption decomposition to tackle spatial and temporal information separately, (2) temporal frame selection with best-view filtering for sufficient temporal information, and (3) reference-driven understanding for capturing fine-grained motion and dynamic context and (4) curated visual/textual prompt techniques. Experimental results on the WTS \\cite{kong2024wts} and BDD \\cite{BDD} datasets demonstrate substantial gains in semantic richness and traffic scene interpretation. Our framework is validated through a decent test score of 55.655 in the AI City Challenge 2025 Track 2, showing its effectiveness in advancing resource-efficient and accurate traffic analysis for real-world applications.","short_abstract":"Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding. This paper introduces STER-VLM, a computationally efficient framework that enha...","url_abs":"https://arxiv.org/abs/2508.13470","url_pdf":"https://arxiv.org/pdf/2508.13470v1","authors":"[\"Tinh-Anh Nguyen-Nhu\",\"Triet Dao Hoang Minh\",\"Dat To-Thanh\",\"Phuc Le-Gia\",\"Tuan Vo-Lan\",\"Tien-Huy Nguyen\"]","published":"2025-08-19T03:03:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}