从内容到受众：一种多模态注释框架用于广播电视分析
From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics
AI总结：
本文提出了一种多模态注释框架，用于广播电视内容分析，通过构建特定领域的基准测试，评估不同管道架构在广播新闻中的表现，展示了框架在受众分析中的应用价值。
摘要：
自动语义注释广播电视内容面临独特挑战，结合了结构化的音频视频组成、领域特定的编辑模式和严格的运营约束。尽管多模态大语言模型（MLLMs）在通用视频理解方面表现强大，但其在广播特定设置中在管道架构和输入配置上的相对有效性仍缺乏实证研究。本文系统评估了应用于意大利广播新闻的多模态注释管道。我们构建了一个在四个语义维度上标注的领域特定基准测试，包括视觉环境分类、主题分类、敏感内容检测和命名实体识别。在九种前沿模型上评估了两种不同的管道架构，包括Gemini 3.0 Pro、LLaMA 4 Maverick、Qwen-VL变体和Gemma 3，在逐步增强的输入策略下结合了视觉信号、自动语音识别、说话人分割和元数据。实验结果表明，视频输入带来的收益在模型上高度依赖：大模型有效利用时间连续性，而小模型在扩展多模态上下文下表现出性能下降，可能由于令牌过载。除了基准测试外，所选管道被部署在14个完整的广播节目上，分钟级注释与意大利媒体公司提供的标准化观众测量数据相结合。这种整合使在主题层面的观众敏感度和世代间参与差异的关联分析成为可能，展示了所提出框架在基于内容的观众分析中的操作可行性。
英文摘要：
Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, domain-specific editorial patterns, and strict operational constraints. While multimodal large language models (MLLMs) have demonstrated strong general-purpose video understanding capabilities, their comparative effectiveness across pipeline architectures and input configurations in broadcast-specific settings remains empirically undercharacterized. This paper presents a systematic evaluation of multimodal annotation pipelines applied to broadcast television news in the Italian setting. We construct a domain-specific benchmark of clips labeled across four semantic dimensions: visual environment classification, topic classification, sensitive content detection, and named entity recognition. Two different pipeline architectures are evaluated across nine frontier models, including Gemini 3.0 Pro, LLaMA 4 Maverick, Qwen-VL variants, and Gemma 3, under progressively enriched input strategies combining visual signals, automatic speech recognition, speaker diarization, and metadata. Experimental results demonstrate that gains from video input are strongly model-dependent: larger models effectively leverage temporal continuity, while smaller models show performance degradation under extended multimodal context, likely due to token overload. Beyond benchmarking, the selected pipeline is deployed on 14 full broadcast episodes, with minute-level annotations integrated with normalized audience measurement data provided by an Italian media company. This integration enables correlational analysis of topic-level audience sensitivity and generational engagement divergence, demonstrating the operational viability of the proposed framework for content-based audience analytics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
