论文标题
我们不需要成千上万个建议$ \ colon $单镜头演员在视频中检测
We don't Need Thousand Proposals$\colon$ Single Shot Actor-Action Detection in Videos
论文作者
论文摘要
我们提出了SSA2D，这是一个简单而有效的端到端深层网络，用于视频中的演员行动检测。现有方法采用基于区域范围（RPN）的自上而下方法，在该方法中，根据检测到的提案估算该动作，然后是后处理，例如非最大程度抑制。尽管在性能方面有效，但这些方法在可伸缩的视频场景中构成了可伸缩性的限制，对数千个建议的记忆要求很高。我们建议从不需要任何建议的不同角度来解决这个问题。 SSA2D是一个统一的网络，它在单次射击中执行像素级关节行动检测，其中每个检测到的参与者的每个像素都被分配一个动作标签。 SSA2D具有两个主要优点：1）它是一个完全卷积的网络，不需要任何建议和后处理，使其内存以及时间效率，2）由于其内存需求与现场中存在的参与者的数量无关，因此很容易扩展到密集的视频场景。我们评估了Actor-Action数据集（A2D）和视频对象关系（Vidor）数据集的提议方法，并在视频中证明了其在多个参与者中的有效性和动作检测。与先前的作品相比，在推断出可比（有时更好）的性能（有时更好）的性能和更少的网络参数期间，SSA2D的速度快11倍。
We propose SSA2D, a simple yet effective end-to-end deep network for actor-action detection in videos. The existing methods take a top-down approach based on region-proposals (RPN), where the action is estimated based on the detected proposals followed by post-processing such as non-maximal suppression. While effective in terms of performance, these methods pose limitations in scalability for dense video scenes with a high memory requirement for thousands of proposals. We propose to solve this problem from a different perspective where we don't need any proposals. SSA2D is a unified network, which performs pixel level joint actor-action detection in a single-shot, where every pixel of the detected actor is assigned an action label. SSA2D has two main advantages: 1) It is a fully convolutional network which does not require any proposals and post-processing making it memory as well as time efficient, 2) It is easily scalable to dense video scenes as its memory requirement is independent of the number of actors present in the scene. We evaluate the proposed method on the Actor-Action dataset (A2D) and Video Object Relation (VidOR) dataset, demonstrating its effectiveness in multiple actors and action detection in a video. SSA2D is 11x faster during inference with comparable (sometimes better) performance and fewer network parameters when compared with the prior works.
