论文标题
通过层次强化学习弱监督的视频摘要
Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning
论文作者
论文摘要
基于强化学习的常规视频摘要方法存在一个问题，即只有在整个摘要生成后才能收到奖励。这种奖励很稀疏，它使加强学习难以融合。另一个问题是标记每个框架都是乏味和昂贵的，这通常禁止构建大型数据集。为了解决这些问题，我们提出了一个弱监督的分层增强学习框架，该框架将整个任务分解为多个子任务以提高汇总质量。该框架由经理网络和一个工作网络组成。对于每个子任务，经理都需要通过任务级二进制标签来设置子目标，该标签所需的标签比常规方法要少得多。在该子目标的指南中，工人根据全球奖励和创新定义的子奖励来预测策略梯度在子任务中视频帧的重要性得分，以克服稀疏的问题。两个基准数据集的实验表明，我们的建议取得了最佳性能，甚至比监督方法更好。
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework consists of a manager network and a worker network. For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches. With the guide of the subgoal, the worker predicts the importance scores for video frames in the subtask by policy gradient according to both global reward and innovative defined sub-rewards to overcome the sparse problem. Experiments on two benchmark datasets show that our proposal has achieved the best performance, even better than supervised approaches.
