Going deeper into action recognition: A survey

Abstract

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply to almost all daily activities. Given the broad range of applications from video surveillance to human-computer interaction, scientific milestones in action recognition are achieved more rapidly, eventually leading to the demise of what used to be good in a short time. This motivated us to provide a comprehensive review of the notable steps taken towards recognizing human actions. To this end, we start our discussion with the pioneering methods that use handcrafted representations, and then, navigate into the realm of deep learning based approaches. We aim to remain objective throughout this survey, touching upon encouraging improvements as well as inevitable fallbacks, in the hope of raising fresh questions and motivating new research directions for the reader.

Vision-Based Fall Detection with Convolutional Neural Networks

“…This is a standard practice in the deep learning literature [42], as the network learns generic features for image recognition; for example, it can distinguish corners, textures, basic geometric elements, and so on. Even though the target is to process optical flow images rather than RGB images, Wang et al [8] argue that the generic appearance features learned from Imagenet provide a solid initialization for the network in order to learn more optical flow oriented features.…”

Calorific Expenditure Estimation Using Deep Convolutional Network Features

“…Deep neural networks have also significantly improved action recognition compared to traditional techniques [13].The knowledge about the type of action is strongly correlated with calorie expenditure [5]. While great progress has been made on human action recognition [4] there are still many challenges left to address the range and complexity of human motions and actions in practical, real-world applications, such as in a healthcare scenario within the home environment.…”

Learning an Invariant Hilbert Space for Domain Adaptation

“…Thanks to deep learning, we are witnessing rapid growth in classification accuracy of the imaging techniques if substantial amount of labeled data is provided (Krizhevsky et al, 2012;Simonyan and Zisserman, 2014;He et al, 2016;Herath et al, 2017). However, harnessing the attained knowledge into a new application with limited labeled data (or even without having labels) is far beyond clear (Koniusz et al, 2017;Long et al, 2016;Ganin and Lempitsky, 2015;Tzeng et al, 2014;Chen et al, 2015).…”