A Comprehensive Study on Temporal Modeling for Online Action Detection

TL;DR

This paper provides a comprehensive analysis of various temporal modeling techniques for online action detection, evaluating their effectiveness and proposing hybrid methods that outperform current state-of-the-art systems.

Contribution

It systematically investigates four types of temporal modeling methods for OAD and introduces hybrid approaches that achieve superior performance.

Findings

Hybrid temporal models outperform existing methods on THUMOS-14 and TVSeries datasets.

Extensive evaluation reveals best practices for temporal modeling in OAD.

Many models are explored in OAD for the first time.

Abstract

Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules: a frame-level feature extractor which is usually based on pre-trained deep Convolutional Neural Networks (CNNs), a temporal modeling module, and an action classifier. Among them, the temporal modeling module is crucial which aggregates discriminative information from historical and current features. Though many temporal modeling methods have been developed for OAD and other topics, their effects are lack of investigation on OAD fairly. This paper aims to provide a comprehensive study on temporal modeling for OAD including four meta types of temporal modeling methods, \ie temporal pooling, temporal convolution, recurrent neural networks, and temporal attention, and uncover some good practices to produce a state-of-the-art OAD system. Many of them are explored in OAD for the first time, and extensively evaluated with various hyper parameters. Furthermore, based on our comprehensive study, we present several hybrid temporal modeling methods, which outperform the recent state-of-the-art methods with sizable margins on THUMOS-14 and TVSeries.