In this paper, we present a novel Single Shot multi-Span Detector for
temporal activity detection in long, untrimmed videos using a simple end-to-end
fully three-dimensional convolutional (Conv3D) network. Our architecture, named
S3D, encodes the entire video stream and discretizes the output space of
temporal activity spans into a set of default spans over different temporal
locations and scales. At prediction time, S3D predicts scores for the presence
of activity categories in each default span and produces temporal adjustments
relative to the span location to predict the precise activity duration. Unlike
many state-of-the-art systems that require a separate proposal and
classification stage, our S3D is intrinsically simple and dedicatedly designed
for single-shot, end-to-end temporal activity detection. When evaluating on
THUMOS'14 detection benchmark, S3D achieves state-of-the-art performance and is
very efficient and can operate at 1271 FPS.

本文提出了一种名为 S3D 的新颖的单镜头多跨度检测器，利用简单的端到端完全三维卷积 (Conv3D) 网络，在长的、未修剪的视频中进行时间活动检测。在 THUMOS'14 检测基准测试中，S3D 实现了最先进的性能，并且非常有效，能以 1271 FPS 的速度运行。