{"ID":2885745,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04353","arxiv_id":"2508.04353","title":"LUST: A Multi-Modal Framework with Hierarchical LLM-based Scoring for Learned Thematic Significance Tracking in Multimedia Content","abstract":"This paper introduces the Learned User Significance Tracker (LUST), a framework designed to analyze video content and quantify the thematic relevance of its segments in relation to a user-provided textual description of significance. LUST leverages a multi-modal analytical pipeline, integrating visual cues from video frames with textual information extracted via Automatic Speech Recognition (ASR) from the audio track. The core innovation lies in a hierarchical, two-stage relevance scoring mechanism employing Large Language Models (LLMs). An initial \"direct relevance\" score, $S_{d,i}$, assesses individual segments based on immediate visual and auditory content against the theme. This is followed by a \"contextual relevance\" score, $S_{c,i}$, that refines the assessment by incorporating the temporal progression of preceding thematic scores, allowing the model to understand evolving narratives. The LUST framework aims to provide a nuanced, temporally-aware measure of user-defined significance, outputting an annotated video with visualized relevance scores and comprehensive analytical logs.","short_abstract":"This paper introduces the Learned User Significance Tracker (LUST), a framework designed to analyze video content and quantify the thematic relevance of its segments in relation to a user-provided textual description of significance. LUST leverages a multi-modal analytical pipeline, integrating visual cues from video f...","url_abs":"https://arxiv.org/abs/2508.04353","url_pdf":"https://arxiv.org/pdf/2508.04353v1","authors":"[\"Anderson de Lima Luiz\"]","published":"2025-08-06T11:48:51Z","proceeding":"cs.MM","tasks":"[\"cs.MM\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}