Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the quality, quantity, and diversity of \textit{annotated} training data and do not often generalize to out-of-domain samples. In this work, we tackle the problem of active action localization where the goal is to localize an action while controlling the geometric and physical parameters of an active camera to keep the action in the field of view without training data. We formulate an energy-based mechanism that combines predictive learning and reactive control to perform active action localization without rewards, which can be sparse or non-existent in real-world environments. We perform extensive experiments in both simulated and real-world environments on two tasks - active object tracking and active action localization. We demonstrate that the proposed approach can generalize to different tasks and environments in a streaming fashion, without explicit rewards or training. We show that the proposed approach outperforms unsupervised baselines and obtains competitive performance compared to those trained with reinforcement learning.
翻译:行动本地化等视觉事件感知任务主要侧重于静态观察者监管的学习设置,即相机是静态的,无法受算法控制。它们往往受到培训数据的质量、数量和多样性的限制,而且通常不向外推广。在这项工作中,我们处理积极行动本地化问题,目标是在控制活跃相机的几何和物理参数的同时将行动本地化,以便在没有培训数据的情况下保持观察领域的行动。我们制定了一种以能源为基础的机制,将预测性学习和反应性控制结合起来,在没有回报的情况下开展积极的行动本地化,这在现实世界环境中可能很少或根本不存在。我们在模拟和现实世界环境中就两项任务进行了广泛的实验——主动物体跟踪和积极行动本地化。我们证明,拟议的方法可以以流传方式将不同的任务和环境概括为一种通用,而没有明确的奖励或培训。我们表明,拟议的方法超越了不受监督的基线,并取得了与受过强化学习培训的人相比具有竞争性的绩效。