Results 41 to 50 of about 5,777,447 (338)
On the Benefits of 3D Pose and Tracking for Human Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2023 In this work we study the benefits of using tracking and 3D poses for action recognition. To achieve this, we take the Lagrangian view on analysing actions over a trajectory of human motion rather than at a fixed point in space.
Jathushan Rajasegaran +4 more
semanticscholar +1 more source
Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling [PDF]
Computer Vision and Pattern Recognition, 2023 This paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition; skeleton detection and tracking errors, poor variety of the targeted actions, as well as person-wise and framewise action recognition. A
Ryo Hachiuma, Fumiaki Sato, Taiki Sekii
semanticscholar +1 more source
Sensors, 2018 Recognition of human actions form videos has been an active area of research because it has applications in various domains. The results of work in this field are used in video surveillance, automatic video labeling and human-computer interaction, among ...
Shahela Saif +2 more
doaj +1 more source
Brand recognition action in mobile shopping [PDF]
E3S Web of Conferences, 2023 Depending on the development in technology, consumer expectations are also changing. Depending on the changing demands and needs, both the consumers and the virtual environment quickly go to meet these situations.
Basal Murat, Gayretlı Sule
doaj +1 more source
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2022 In action recognition, although the combination of spatiotemporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required.
Dasom Ahn +3 more
semanticscholar +1 more source
Video Summarization Using Deep Action Recognition Features and Robust Principal Component Analysis [PDF]
Journal of Systemics, Cybernetics and Informatics, 2020 In an instance where desired pre-defined actions, behaviors, or other categories are known a priori, various video classification and recognition models can be trained to discover those classifications and their location within the video.
Daniel M. Claborne +3 more
doaj
Follower: A Novel Self-Deployable Action Recognition Framework
Sensors, 2021 Deep learning technology has improved the performance of vision-based action recognition algorithms, but such methods require a large number of labeled training datasets, resulting in weak universality.
Xu Yang +5 more
doaj +1 more source
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
Computer Vision and Pattern Recognition, 2018 In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance.
Lei Shi +3 more
semanticscholar +1 more source
TEA: Temporal Excitation and Aggregation for Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2020 Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion excitation (ME) module ...
Yan Li +5 more
semanticscholar +1 more source
Tensor Representations for Action Recognition [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships between visual features for the task of action recognition.
Piotr Koniusz, Lei Wang, Anoop Cherian
openaire +3 more sources