TadML: A fast temporal action detection with Mechanics-MLP

TL;DR

TadML introduces a fast, one-stage, anchor-free temporal action detection method using Mechanics-MLP that achieves high accuracy and significantly faster inference speeds on untrimmed videos without optical flow computation.

Contribution

The paper proposes a novel Mechanics-MLP architecture for real-time, one-stage temporal action detection using only RGB data, improving inference speed over existing methods.

Findings

Achieves 4.44 videos per second inference speed on THUMOS14

Maintains comparable accuracy with state-of-the-art models

Eliminates the need for optical flow computation

Abstract

Temporal Action Detection(TAD) is a crucial but challenging task in video understanding.It is aimed at detecting both the type and start-end frame for each action instance in a long, untrimmed video.Most current models adopt both RGB and Optical-Flow streams for the TAD task. Thus, original RGB frames must be converted manually into Optical-Flow frames with additional computation and time cost, which is an obstacle to achieve real-time processing. At present, many models adopt two-stage strategies, which would slow the inference speed down and complicatedly tuning on proposals generating.By comparison, we propose a one-stage anchor-free temporal localization method with RGB stream only, in which a novel Newtonian Mechanics-MLP architecture is established. It has comparable accuracy with all existing state-of-the-art models, while surpasses the inference speed of these methods by a large margin. The typical inference speed in this paper is astounding 4.44 video per second on THUMOS14. In applications, because there is no need to convert optical flow, the inference speed will be faster.It also proves that MLP has great potential in downstream tasks such as TAD. The source code is available at https://github.com/BonedDeng/TadML