HiVid-Narrator：基于场景优先的ASR锚定压缩的分层视频叙事生成
HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression
AI总结：
HiVid-Narrator通过分阶段构建和SPA-Compressor压缩技术，在减少输入标记的同时生成高质量的电子商务视频叙事。
摘要：
生成结构化的叙述用于现实世界的电子商务视频需要模型能够感知细粒度的视觉细节并将它们组织成连贯的高层次故事——这种能力现有方法难以统一。我们引入了具有双粒度、时间相关的注释的电子商务分层视频描述（E-HVC）数据集：一个时间链式思维，用于锚定事件级观察，以及章节摘要，将它们组合成简洁、以故事为中心的摘要。而不是直接提示章节，我们采用分阶段的构建方法，首先通过精心挑选的ASR和帧级描述收集可靠的语言和视觉证据，然后通过时间链式思维对粗略注释进行细化，生成精确的章节边界和标题，从而产生事实支持、时间对齐的叙述。我们还观察到电子商务视频节奏快且信息密集，视觉标记主导输入序列。为了在减少输入标记的同时实现高效训练，我们提出了基于ASR语义提示的场景优先ASR锚定压缩器（SPA-Compressor），将多模态标记压缩成层次化的场景和事件表示。基于这些设计，我们的HiVid-Narrator框架在较少的输入标记下实现了优于现有方法的叙述质量。
英文摘要：
Generating structured narrations for real-world e-commerce videos requires models to perceive fine-grained visual details and organize them into coherent, high-level stories--capabilities that existing approaches struggle to unify. We introduce the E-commerce Hierarchical Video Captioning (E-HVC) dataset with dual-granularity, temporally grounded annotations: a Temporal Chain-of-Thought that anchors event-level observations and Chapter Summary that compose them into concise, story-centric summaries. Rather than directly prompting chapters, we adopt a staged construction that first gathers reliable linguistic and visual evidence via curated ASR and frame-level descriptions, then refines coarse annotations into precise chapter boundaries and titles conditioned on the Temporal Chain-of-Thought, yielding fact-grounded, time-aligned narratives. We also observe that e-commerce videos are fast-paced and information-dense, with visual tokens dominating the input sequence. To enable efficient training while reducing input tokens, we propose the Scene-Primed ASR-anchored Compressor (SPA-Compressor), which compresses multimodal tokens into hierarchical scene and event representations guided by ASR semantic cues. Built upon these designs, our HiVid-Narrator framework achieves superior narrative quality with fewer input tokens compared to existing methods.
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。
