This paper presents a semi-supervised approach to extracting and analyzing combat phases in judo tournaments using live-streamed footage. The objective is to automate the annotation and summarization of live streamed judo matches. We train models that extract relevant entities and classify combat phases from fixed-perspective judo recordings. We employ semi-supervised methods to address limited labeled data in the domain. We build a model of combat phases via transfer learning from a fine-tuned object detector to classify the presence, activity, and standing state of the match. We evaluate our approach on a dataset of 19 thirty-second judo clips, achieving an F1 score on a $20\%$ test hold-out of 0.66, 0.78, and 0.87 for the three classes, respectively. Our results show initial promise for automating more complex information retrieval tasks using rigorous methods with limited labeled data.

翻译：本文提出了一种半监督方法，利用直播录像提取并分析柔道赛事中的对抗阶段。其目标在于实现柔道比赛直播的自动化标注与摘要生成。我们训练了从固定视角柔道录像中提取相关实体并对抗阶段进行分类的模型。针对该领域标注数据有限的问题，我们采用了半监督方法。我们通过从微调后的目标检测器进行迁移学习，构建了一个对抗阶段模型，用于分类比赛中运动员的存在状态、活动状态与站立状态。我们在一个包含19段三十秒柔道视频片段的数据集上评估了该方法，在20%的测试集上，三个类别的F1分数分别达到了0.66、0.78和0.87。我们的结果表明，利用严谨的方法在有限标注数据下，自动化执行更复杂的信息检索任务具有初步的可行性。