Psvt: End-to-end multi-person 3d pose and shape estimation with progressive video transformers

Z Qiu, Q Yang, J Wang, H Feng, J Han… - Proceedings of the …, 2023 - openaccess.thecvf.com
Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE)
typically adopt a two-stage strategy, which first detects human instances in each frame and …

A review of abnormal behavior detection in activities of daily living

NC Tay, T Connie, TS Ong, ABJ Teoh, PS Teh - IEEE Access, 2023 - ieeexplore.ieee.org
Abnormal behavior detection (ABD) systems are built to automatically identify and recognize
abnormal behavior from various input data types, such as sensor-based and vision-based …

Learning to estimate robust 3d human mesh from in-the-wild crowded scenes

H Choi, G Moon, JK Park… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
We consider the problem of recovering a single person's 3D human mesh from in-the-wild
crowded scenes. While much progress has been in 3D human mesh estimation, existing …

A survey on human activity recognition and classification

A Gupta, K Gupta, K Gupta… - … on communication and …, 2020 - ieeexplore.ieee.org
Activity Recognition and Classification is one of the most significant issues in the computer
vision field. Identifying and recognizing actions or activities that are performed by a person is …

Skeletal video anomaly detection using deep learning: Survey, challenges, and future directions

PK Mishra, A Mihailidis, SS Khan - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The existing methods for video anomaly detection mostly utilize videos containing
identifiable facial and appearance-based features. The use of videos with identifiable faces …

A survey on human activity recognition using sensors and deep learning methods

K Banjarey, SP Sahu… - 2021 5th international …, 2021 - ieeexplore.ieee.org
One of the most difficult challenges in the field of computer vision is human activity
recognition (HAR). The main purpose of intelligent video system is to determine the actions …

Occluded Part-aware Graph Convolutional Networks for Skeleton-based Action Recognition

MH Kim, MJ Kim, SB Yoo - 2024 IEEE International Conference …, 2024 - ieeexplore.ieee.org
Recognizing human action is one of the most critical factors in the visual perception of
robots. Specifically, skeletonbased action recognition has been actively researched to …

Various approaches of human activity recognition: a review

AK Sharma, S Tomar, K Gupta - 2021 5th International …, 2021 - ieeexplore.ieee.org
In the past few decades, recognizing the activities of an individual is remaining as the most
challenging task in the computer science domain. Human activity recognition (HAR) is the …

Ibaggedfcnet: An ensemble framework for anomaly detection in surveillance videos

Y Zahid, MA Tahir, NM Durrani, A Bouridane - IEEE Access, 2020 - ieeexplore.ieee.org
The prevalent use of surveillance cameras in public places and advancements in computer
vision warrant most sought-after research in the domain of anomalous activity detection …

Modeling transformer architecture with attention layer for human activity recognition

G Pareek, S Nigam, R Singh - Neural Computing and Applications, 2024 - Springer
Human activity recognition (HAR) is necessary in numerous fields, involving medicine,
sports, and security. Traditional HAR methods often rely on complex feature extraction from …