Temporal action detection (TAD) is extensively studied in the video understanding community by generally following the object detection pipeline in images. However, complex designs are not uncommon in TAD, such as two-stream feature extraction, multi-stage training, complex temporal modeling, and global context fusion. In this paper, we do not aim to introduce any novel technique for TAD. Instead, we study a simple, straightforward, yet must-known baseline given the current status of complex design and low detection efficiency in TAD. In our simple baseline (termed BasicTAD), we decompose the TAD pipeline into several essential components: data sampling, backbone design, neck construction, and detection head. We extensively investigate the existing techniques in each component for this baseline, and more importantly, perform end-to-end training over the entire pipeline thanks to the simplicity of design. As a result, this simple BasicTAD yields an astounding and real-time RGB-Only baseline very close to the state-of-the-art methods with two-stream inputs. In addition, we further improve the BasicTAD by preserving more temporal and spatial information in network representation (termed as PlusTAD). Empirical results demonstrate that our PlusTAD is very efficient and significantly outperforms the previous methods on the datasets of THUMOS14 and FineAction. Meanwhile, we also perform in-depth visualization and error analysis on our proposed method and try to provide more insights on the TAD problem. Our approach can serve as a strong baseline for future TAD research. The code and model will be released at https://github.com/MCG-NJU/BasicTAD.

翻译：在视频理解界广泛研究时间行动探测(TAD),通常根据图像中的物体探测管道,在视频理解界广泛研究时间行动探测(TAD),然而,在TAD中,复杂的设计并不罕见,例如两流特征提取、多阶段培训、复杂的时间模型和全球背景融合。在本文中,我们不打算为TAD引入任何新的技术。相反,我们研究一个简单、直截了当、但必须知道的基线,因为TAD的复杂设计和检测效率目前处于低位状态。在我们简单的基线(MD)中,我们将TAD管道分解成几个基本组成部分:数据取样、骨干设计、颈部构造和检测头。我们广泛调查了这一基线每个组成部分中的现有技术,更重要的是,由于设计简单,我们不打算引入任何新的技术。结果,这个简单的基础TAD将产生一个惊人和实时的 RGB-OOn 基线,非常接近最新版本的方法,同时提供双流投入。此外,我们进一步改进了基础TAD,通过在网络中保存更坚固的时空和空间的基线信息,我们将来的TAAD分析结果。