Asformer: Transformer for action segmentation

F Yi, H Wen, T Jiang - arXiv preprint arXiv:2110.08568, 2021 - arxiv.org
Algorithms for the action segmentation task typically use temporal models to predict what
action is occurring at each frame for a minute-long daily activity. Recent studies have shown …

Human action recognition and prediction: A survey

Y Kong, Y Fu - International Journal of Computer Vision, 2022 - Springer
Derived from rapid advances in computer vision and machine learning, video analysis tasks
have been moving from inferring the present state to predicting the future state. Vision-based …

A comprehensive survey of rgb-based and skeleton-based human action recognition

C Wang, J Yan - IEEE Access, 2023 - ieeexplore.ieee.org
With the advancement of computer vision, human action recognition (HAR) has shown its
broad research worth and application prospects in a wide range of fields such as intelligent …

Structural-rnn: Deep learning on spatio-temporal graphs

A Jain, AR Zamir, S Savarese… - Proceedings of the ieee …, 2016 - openaccess.thecvf.com
Abstract Deep Recurrent Neural Network architectures, though remarkably capable at
modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while …

Every moment counts: Dense detailed labeling of actions in complex videos

S Yeung, O Russakovsky, N Jin, M Andriluka… - International Journal of …, 2018 - Springer
Every moment counts in action recognition. A comprehensive understanding of human
activity in video requires labeling every frame according to the actions occurring, placing …

Toward human activity recognition: a survey

G Saleem, UI Bajwa, RH Raza - Neural Computing and Applications, 2023 - Springer
Human activity recognition (HAR) is a complex and multifaceted problem. The research
community has reported numerous approaches to perform HAR. Along with HAR …

Anticipating human activities using object affordances for reactive robotic response

HS Koppula, A Saxena - IEEE transactions on pattern analysis …, 2015 - ieeexplore.ieee.org
An important aspect of human perception is anticipation, which we use extensively in our
day-to-day activities when interacting with other humans as well as with our surroundings …

Overview of lifelogging: current challenges and advances

A Ksibi, ASD Alluhaidan, A Salhi, SA El-Rahman - IEEE Access, 2021 - ieeexplore.ieee.org
Lifelogging is the process of digital tracking of person's daily experiences for a variety of
purposes. In recent years, lifelogging has become an increasingly popular area of research …

Learning human activities and object affordances from rgb-d videos

HS Koppula, R Gupta… - The International journal …, 2013 - journals.sagepub.com
Understanding human activities and object affordances are two very important skills,
especially for personal robots which operate in human environments. In this work, we …

Segmental spatiotemporal cnns for fine-grained action segmentation

C Lea, A Reiter, R Vidal, GD Hager - … 11-14, 2016, Proceedings, Part III 14, 2016 - Springer
Joint segmentation and classification of fine-grained actions is important for applications of
human-robot interaction, video surveillance, and human skill evaluation. However, despite …