Human action recognition using attention based LSTM network with dilated CNN features

K Muhammad, A Ullah, AS Imran, M Sajjad… - Future Generation …, 2021 - Elsevier
Human action recognition in videos is an active area of research in computer vision and
pattern recognition. Nowadays, artificial intelligence (AI) based systems are needed for …

Deep image-to-video adaptation and fusion networks for action recognition

Y Liu, Z Lu, J Li, T Yang, C Yao - IEEE Transactions on Image …, 2019 - ieeexplore.ieee.org
Existing deep learning methods for action recognition in videos require a large number of
labeled videos for training, which is labor-intensive and time-consuming. For the same …

A Deep Bidirectional LSTM Model Enhanced by Transfer-Learning-Based Feature Extraction for Dynamic Human Activity Recognition

N Hassan, ASM Miah, J Shin - Applied Sciences, 2024 - mdpi.com
Dynamic human activity recognition (HAR) is a domain of study that is currently receiving
considerable attention within the fields of computer vision and pattern recognition. The …

A Swarm Intelligence Assisted IoT-Based Activity Recognition System for Basketball Rookies

Y Zhou, R Wang, Y Wang, S Sun… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recent years have witnessed many applications of wearable sensor technology and
machine learning on smart sports training, eg, basketball. For rookie players, the …

Behavior recognition based on the improved density clustering and context-guided Bi-LSTM model

T Zhou, A Tao, L Sun, B Qu, Y Wang… - Multimedia Tools and …, 2023 - Springer
Context information is vital to research video human behavior recognition. Under the LSTM
together with CNN of the framework, a novel action recognition method, which extracts …

Self-updatable database system based on human motion assessment framework

K Lee, Y Park, J Huh, J Kang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Recently, human motion-centric videos have been attracting attention in the field of
computer vision. Observing and detecting human motion in intelligent surveillance camera …

A context-aware capsule network for multi-label classification

S Ramasinghe, CD Athuraliya… - Proceedings of the …, 2018 - openaccess.thecvf.com
Abstract Recently proposed Capsule Network is a brain inspired architecture that brings a
new paradigm to deep learning by modelling input domain variations through vector based …

Understanding Long Videos in One Multimodal Language Model Pass

K Ranasinghe, X Li, K Kahatapitiya… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs), known to contain a strong awareness of world knowledge,
have allowed recent approaches to achieve excellent performance on Long-Video …

Task activity recognition and workspace extraction for nursing care assistance in intelligent space

K Sakotani, S Kato, M Niitsuma… - 2020 IEEE/SICE …, 2020 - ieeexplore.ieee.org
With the rapid increase in the elderly population, there is a shortage of caregivers in Japan.
Consequently, the workload per caregiver has increased, which is now a major social issue …

Pose identification for task recognition in care work

S Kato, M Niitsuma, T Tanaka - 2021 IEEE/SICE International …, 2021 - ieeexplore.ieee.org
In Japan, the number of caregivers is not increasing with the same rate as the aging of the
population, resulting in an increased workload per caregiver, which has become a social …