Scholarlink

<p>Existing movie scene segmentation methods struggle with long-range temporal dependencies, attention degradation, and rigid multimodal fusion, often ignoring the inherent hierarchical structure of movies. To address these limitations, this paper proposes a Hierarchical Attentive Transformer (HATrans). First, to capture multi-granularity semantic consistency and discriminative scene boundaries, we adopt a shot-to-segment hierarchical encoding pipeline that explicitly models structural priors. Second, to mitigate attention degradation when processing extremely long shot sequences, we introduce a hierarchical masked attention mechanism combined with a temporal position-aware bias, which restricts irrelevant connections and enhances structural sensitivity. Third, to overcome the inflexibility of conventional multimodal integration, we propose a label-guided attention fusion module that leverages semantic category priors to dynamically weight visual, audio, and subtitle features based on varying semantic contexts. Experimental results on MovieNet-42&#xa0;K suggest that HATrans achieves competitive performance, outperforming several baselines including CMTS.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hierarchical attentive transformer with label guided fusion for multimodal movie scene segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月21日

查看全文
  • Weiwei Zhao,
  • Jing Wang

摘要

Existing movie scene segmentation methods struggle with long-range temporal dependencies, attention degradation, and rigid multimodal fusion, often ignoring the inherent hierarchical structure of movies. To address these limitations, this paper proposes a Hierarchical Attentive Transformer (HATrans). First, to capture multi-granularity semantic consistency and discriminative scene boundaries, we adopt a shot-to-segment hierarchical encoding pipeline that explicitly models structural priors. Second, to mitigate attention degradation when processing extremely long shot sequences, we introduce a hierarchical masked attention mechanism combined with a temporal position-aware bias, which restricts irrelevant connections and enhances structural sensitivity. Third, to overcome the inflexibility of conventional multimodal integration, we propose a label-guided attention fusion module that leverages semantic category priors to dynamically weight visual, audio, and subtitle features based on varying semantic contexts. Experimental results on MovieNet-42 K suggest that HATrans achieves competitive performance, outperforming several baselines including CMTS.