发表机构
University of Science and Technology of China; Sun Yat-sen University（中国科学技术大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出面向结果的视频生成任务语义任务完成，构建SemComp-Data数据集与SemComp-Bench基准，发现代表性视频生成模型在兼顾结果实现与参考图像语义基础上仍具挑战。
AI 中文摘要
我们提出了语义任务完成视频生成，这是一种面向结果的视频生成任务。在该任务设定下，成功既需要实现预期结果，也需要具备语义基础。语义基础指的是参考图像与生成结果之间在与任务相关的高级语义层面的对应关系。评估聚焦于生成结果，既不需要呈现完整的中间任务步骤序列，也不需要与参考图像保持传统的外观一致性。为支持系统性评估，我们构建了覆盖六个领域的评估数据集SemComp-Data，每个实例包含一张参考图像、一条详细指令、一条简要指令以及一段以结果为中心的视频片段。一个可扩展的四阶段整理流程将原始视频转换为标准化的SemComp-Data实例。我们还提出了SemComp-Bench，这是一种使用视觉语言模型（VLM）回答结构化二元问题的评估协议，该基准分别报告结果实现的OA分数和生成可靠性的GR分数。对代表性视频生成模型的实验表明，在保持参考图像与任务相关语义基础的同时实现预期结果仍然具有挑战性。
英文摘要
We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the intended outcome and semantic grounding. Semantic grounding characterizes the correspondence between the reference image and the generated outcome in terms of high-level semantics relevant to the task. Evaluation focuses on the generated outcome and requires neither the presentation of a complete sequence of intermediate task steps nor conventional appearance consistency with the reference image. To support systematic evaluation, we construct SemComp-Data, an evaluation dataset covering six domains. Each instance comprises a reference image, a detailed instruction, a brief instruction, and an outcome-centric video clip. A scalable four-stage curation pipeline converts raw videos into standardized SemComp-Data instances. We further introduce SemComp-Bench, an evaluation protocol that uses a vision-language model (VLM) to answer structured binary questions. SemComp-Bench reports the OA Score and the GR Score for Outcome Achievement and Generation Reliability, respectively. Experiments on representative video generation models show that achieving intended outcomes while maintaining task-relevant semantic grounding in reference images remains challenging.
