A Two-stream Network with Spatial Long-range Modeling for Weakly-supervised Temporal Action Localization

This paper focuses on weakly supervised temporal action localization, a critical issue within the field of Artificial Intelligence (AI) in the context of the Internet of Things (IoT). The objective is to identify and locate action segments within untrimmed videos, which are solely trained using video-level action labels. Current visual perception and analysis techniques in the IoT face substantial challenges, including a significant amount of noise in videos, the complexity of backgrounds, and the absence of clear motion boundaries in lengthy video sequences. In this paper, we fully recognize that each frame space contains a wealth of information that contributes to classification and localization tasks. Therefore, we propose a method based on modeling features using spatial information within long video frames, aiming to more accurately locate action boundaries and achieve perception of complex data within IoT environments. Additionally, we employ traditional features within our model to alleviate noise issues typically encountered in lengthy videos. Traditional and deep features are processed separately, constituting a two-stream network within the entire model. We conducted comprehensive experiments on the widely used THUMOS14 dataset, demonstrating significant improvements compared to state-of-the-art methods. Furthermore, we conducted experiments on the ActivityNet v1.2 dataset, where traditional features were omitted. The experiments revealed that even without traditional features, our module and two-stream network strategy remained effective within IoT environments.