TVHighlights：LLM 引导的无人工协同训练用于影视剧视频亮点检测
TVHighlights: LLM-Guided Human-Free Collaborative Training for Video Highlight Detection in Movies and TV Dramas
把 LLM 生成的片段级伪标签与轻量视频模型的置信度预测放进自提升闭环，配合噪声鲁棒学习，为长视频时序定位类任务提供了一套无需人工标注的协同训练范式，可直接迁移到视频摘要、精彩片段检索等时序定位问题。
原文依据 LLMs generate noisy clip-level pseudo-labels, which the lightweight model learns from under a noise-robust strategy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频亮点检测旨在识别长视频中最具吸引力的片段，支撑内容剪辑与推荐，对电影和电视剧尤为重要。然而，现有方法难以适配影视内容的叙事复杂性，而标注数据的稀缺与人工标注的高成本进一步阻碍了进展。为弥补这一空白，我们提出 TVHighlights，这是首个面向电影与电视剧视频亮点检测的大规模数据集，包含 1,721 个精心筛选的视频，覆盖多种类型。该数据集基于社区驱动的行为构建，无需人工标注即可提供真实且多样的标注。基于 TVHighlights，我们提出 LTV-HD：一个由大语言模型引导、无需人工参与的协同训练框架，用于影视内容的视频亮点检测。LTV-HD 分两个阶段运行：（1）利用视频级标签对轻量模型进行弱监督预训练；（2）通过大语言模型与轻量模型之间的协作进行迭代精炼。大语言模型生成带噪的片段级伪标签，轻量模型在噪声鲁棒策略下从中学习，其高置信度预测随后被反馈用于引导大语言模型通过自提升循环蒸馏出类型特定的亮点模式。实验表明，LTV-HD 在 TVHighlights 上取得最优性能，验证了其在真实、无标注场景中的有效性。
英文原文摘要 1504 字符
Video highlight detection aims to identify the most engaging segments in long-form videos, supporting content editing and recommendation, especially for movies and TV dramas. However, existing methods are ill-suited to cinematic content due to its narrative complexity, while the scarcity of annotated data and the high cost of manual labeling further hinder progress. To bridge this gap, we introduce **TVHighlights**, the first large-scale dataset tailored for video highlight detection in movies and TV dramas, with 1,721 carefully curated videos covering diverse genres. Built on community-driven behaviors, it provides realistic and diverse annotations without human labeling. Based on TVHighlights, we propose **LTV-HD**: a LLM-guided, human-free collaborative training framework for video highlight detection in cinematic content. LTV-HD operates in two stages: (1) weakly supervised pre-training of a lightweight model using video-level labels, followed by (2) iterative refinement through collaboration between large language models (LLMs) and the lightweight model. LLMs generate noisy clip-level pseudo-labels, which the lightweight model learns from under a noise-robust strategy, and its high-confidence predictions are then fed back to guide the LLM in distilling genre-specific highlight patterns through a self-improving loop. Experiments demonstrate that LTV-HD achieves state-of-the-art performance on TVHighlights, validating its effectiveness in real-world, annotation-free scenarios.