StreamSoccer：用于流式足球解说的事件驱动记忆
StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary
- Migu Video Technology Co., Ltd.（咪咕视讯科技有限公司）
- South China University of Technology（华南理工大学）
- East China Normal University（华东师范大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出StreamSoccer，一种用于流式足球解说的事件驱动系统，通过建模事件生命周期实现多时间范围解说，在数据集评估中取得优异性能且计算开销可控。
AI中文摘要：
流式视频理解要求模型在视频输入时进行因果状态更新，并在有限计算和内存条件下将不断增长的历史组织成可演化、持久化和可检索的语义单元。这一挑战在实时足球解说中尤为突出，系统必须仅利用每次输出前的可用信息，描述已完成事件、总结近期比赛、回忆早期事件或弃权（不执行）。我们提出StreamSoccer，这是一个以事件记忆为中间表示的事件驱动系统。固定预算的活跃内存整合输入流；已完成的事件状态被本地保留并合并为可检索的历史记录。统一生成器利用当前、近期和历史上下文生成三种解说模式，而规则辅助调度器选择其中一种模式或弃权（不执行）。与基于帧、视觉令牌或缓存组织的流式视频-语言模型，以及基于预定义片段或输出时间戳的足球解说方法不同，StreamSoccer明确对事件生命周期进行建模。我们构建了三轨流式足球解说数据集和分层评估协议。在通用参考锚点处，StreamSoccer在当前事件、近期窗口和历史记忆解说任务上分别获得CIDEr分数38.62、23.96和17.39，在当前事件和历史记忆轨道排名第一，近期窗口轨道排名第二。受控消融实验显示，本地已完成事件可提升所有轨道性能，完整系统在三个轨道上均表现最佳。在58场比赛的174次原始视频运行中，每分钟实时因子（RTF）的第95百分位范围为0.10至0.22，且不随比赛历史持续增长。这些结果表明，事件记忆支持跨时间范围的流式足球解说，同时控制长历史计算开销。
英文摘要：
Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. This challenge is pronounced in live soccer commentary, where a system must describe completed events, summarize recent play, recall earlier events, or remain silent using only information available before each utterance. We present StreamSoccer, an event-driven system that uses event memory as its intermediate representation. A fixed-budget active memory integrates the stream; completed event states are retained locally and consolidated into retrievable historical records. A unified generator uses current, recent, and historical context to produce three commentary modes, while a rule-assisted scheduler selects a mode or silence. Unlike streaming video-language models organized around frames, visual tokens, or caches, and soccer-commentary methods based on predefined clips or output timestamps, StreamSoccer explicitly models event lifecycles. We construct a three-track streaming soccer commentary dataset and a layered evaluation protocol. At common reference anchors, StreamSoccer obtains CIDEr scores of 38.62, 23.96, and 17.39 for current-event, recent-window, and historical-memory commentary, ranking first on the current-event and historical-memory tracks and second on recent-window. Controlled ablations show that local completed events improve all tracks and that the full system performs best on all three. Across 174 raw-video runs on 58 matches, per-minute RTF p95 ranges from 0.10 to 0.22 without sustained growth with match history. These results indicate that event memory supports streaming soccer commentary across temporal scopes while controlling long-history computation.
