Advances in Human Action Recognition: A Survey

Cheng, Guangchun; Wan, Yiwen; Saudagar, Abdullah N.; Namuduri, Kamesh; Buckles, Bill P.

doi:10.48550/arxiv.1501.05964

Cited by 21 publications

(25 citation statements)

References 73 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the literature often uses the terms action and activity synonymously [28,36,121], we prefer to use action in this article for a few reasons. First, action is the dominant term across the field, and we would need significant reason to divert from that.…”

Section: Action Understandingmentioning

confidence: 99%

Video Action Understanding

Hutchinson,

Gadepally

2020

Preprint

View full text Add to dashboard Cite

Many believe that the successes of deep learning on image understanding problems can be replicated in the realm of video understanding. However, the span of video action problems and the set of proposed deep learning solutions is arguably wider and more diverse than those of their 2D image siblings. Finding, identifying, and predicting actions are a few of the most salient tasks in video action understanding. This tutorial clarifies a taxonomy of video action problems, highlights datasets and metrics used to baseline each problem, describes common data preparation methods, and presents the building blocks of state-of-the-art deep learning model architectures.

show abstract

Section: Action Understandingmentioning

confidence: 99%

Video Action Understanding

Hutchinson,

Gadepally

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Critical to this success are datasets of diverse videos released to facilitate this research [50,5,32,53,64,27,7,1,41,51,28,17,16,11,18,40]. Most modern datasets are intended for discriminating between human activities to perform action classification and localization [46,69,2,10,26,26,4,76]. In our paper, we instead focus on analyzing goal-directed human action [59], and propose a dataset that allows for learning about failed goals and the transition from intentional to unintentional action.…”

Section: Related Workmentioning

confidence: 99%

Oops! Predicting Unintentional Action in Video

Epstein¹,

Chen²,

Vondrick³

2019

Preprint

View full text Add to dashboard Cite

Intentional versus Unintentional: Did this person intend for this action to happen, or was it an accident? In this paper, we introduce a large in-the-wild video dataset of unintentional action. Our dataset, which we have collected by downloading "fail" videos from the web, contains over twenty thousand clips, and they span a diverse number of activities and scenes. Using this dataset, we study a variety of visual clues for learning to predict intentionality in video.

show abstract

“…Action recognition from RGB videos is a long-standing problem. A detailed survey can be found in [4]. Recent approaches have shown great progress in this field, which can be generally divided into two categories.…”

Section: Action Recognitionmentioning

confidence: 99%

Unsupervised Learning of View-invariant Action Representations

Li,

Wong,

Zhao

et al. 2018

Preprint

View full text Add to dashboard Cite

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an expensive and time-consuming process. In this work, we propose an unsupervised learning framework, which exploits unlabeled data to learn video representations. Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view. By learning to extrapolate cross-view motions, the representation can capture view-invariant motion dynamics which is discriminative for the action. In addition, we propose a view-adversarial training method to enhance learning of view-invariant features. We demonstrate the effectiveness of the learned representations for action recognition on multiple datasets.

show abstract

Advances in Human Action Recognition: A Survey

Cited by 21 publications

References 73 publications

Video Action Understanding

Video Action Understanding

Oops! Predicting Unintentional Action in Video

Unsupervised Learning of View-invariant Action Representations

Contact Info

Product

Resources

About