LAUSR

Triplet attention multiple spacetime-semantic graph convolutional network for skeleton-based action recognition

Sign Up to like & get
recommendations!
1 Published in 2022 at "Applied Intelligence"

DOI: 10.1007/s10489-021-02370-x

Abstract: Skeleton-based action recognition has recently attracted widespread attention in the field of computer vision. Previous studies on skeleton-based action recognition are susceptible to interferences from redundant video frames in judging complex actions but ignore the… read more here.

Keywords: action recognition; spacetime semantic; attention; skeleton based ... See more keywords

ConvNets-based action recognition from skeleton motion maps

Sign Up to like & get
recommendations!
0 Published in 2019 at "Multimedia Tools and Applications"

DOI: 10.1007/s11042-019-08261-1

Abstract: With the advance of deep learning, deep learning based action recognition is an important research topic in computer vision. The skeleton sequence is often encoded into an image to better use Convolutional Neural Networks (ConvNets)… read more here.

Keywords: action recognition; skeleton motion; based action; action ... See more keywords

Slavery from Space: Demonstrating the role for satellite remote sensing to inform evidence-based action related to UN SDG number 8

Sign Up to like & get
recommendations!
1 Published in 2018 at "Isprs Journal of Photogrammetry and Remote Sensing"

DOI: 10.1016/j.isprsjprs.2018.02.012

Abstract: The most recent Global Slavery Index estimates that there are 40.3 million people enslaved globally. The UN’s Agenda 2030 for Sustainable Development Goal number 8, section 8.7 specifically refers to the issue of forced labour:… read more here.

Keywords: remote sensing; number; slavery; evidence based ... See more keywords

Convolutional relation network for skeleton-based action recognition

Sign Up to like & get
recommendations!
0 Published in 2019 at "Neurocomputing"

DOI: 10.1016/j.neucom.2019.08.043

Abstract: Abstract In the skeleton-based action recognition, mining information from the joints and limbs of human skeletons plays a key role. Previous studies treated the skeleton data as vectors and could not explicitly capture the joint… read more here.

Keywords: action recognition; skeleton based; network; skeleton ... See more keywords

Submentalizing Cannot Explain Belief-Based Action Anticipation in Apes

Sign Up to like & get
recommendations!
0 Published in 2017 at "Trends in Cognitive Sciences"

DOI: 10.1016/j.tics.2017.06.011

Abstract: We presented apes with a nonsocial control of our previously published study [11] using identical methods except that, following [6] (Figure I), stimuli were animated versions in which the human actor was swapped out for… read more here.

Keywords: action anticipation; belief based; submentalizing explain; anticipation apes ... See more keywords

An efficient self-attention network for skeleton-based action recognition

Sign Up to like & get
recommendations!
1 Published in 2022 at "Scientific Reports"

DOI: 10.1038/s41598-022-08157-5

Abstract: There has been significant progress in skeleton-based action recognition. Human skeleton can be naturally structured into graph, so graph convolution networks have become the most popular method in this task. Most of these state-of-the-art methods… read more here.

Keywords: action recognition; skeleton based; based action; skeleton ... See more keywords

Fully Attentional Network for Skeleton-Based Action Recognition

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE Access"

DOI: 10.1109/access.2023.3247840

Abstract: With the extraordinary ability by representing human body structure as a spatial graph, graph convolution networks (GCNs) have progressed much in skeleton-based action recognition. However, these methods usually use a predefined graph to represent human… read more here.

Keywords: action recognition; graph; action; based action ... See more keywords

MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2022.3142675

Abstract: In the task of skeleton-based action recognition, long-term temporal dependencies are significant cues for sequential skeleton data. State-of-the-art methods rarely have access to long-term temporal information, due to the limitations of their receptive fields. Meanwhile,… read more here.

Keywords: multi scale; action recognition; action; skeleton ... See more keywords

Dynamic Channel-Aware Subgraph Interactive Networks for Skeleton-Based Action Recognition

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2022.3227816

Abstract: Skeleton-based action recognition has obtained remarkable success due to the rapid development of Graph Neural Networks (GNNs). Existing skeleton-based methods primarily focus on the spatial aspect of skeleton graphs, but rarely mine long-range temporal relationships… read more here.

Keywords: aware subgraph; dynamic channel; action recognition; channel aware ... See more keywords

Discovering Schema-based Action Sequences through Play in Situated Humanoid Robots

Sign Up to like & get
recommendations!
0 Published in 2021 at "IEEE Transactions on Cognitive and Developmental Systems"

DOI: 10.1109/tcds.2021.3094513

Abstract: Exercising sensorimotor and cognitive functions allows humans, including infants, to interact with the environment and objects within it. In particular, during everyday activities, infants continuously enrich their repertoire of actions, and by playing, they experimentally… read more here.

Keywords: schema based; sequences play; discovering schema; action sequences ... See more keywords

Skeleton-Based Action Recognition With Gated Convolutional Neural Networks

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Transactions on Circuits and Systems for Video Technology"

DOI: 10.1109/tcsvt.2018.2879913

Abstract: For skeleton-based action recognition, most of the existing works used recurrent neural networks. Using convolutional neural networks (CNNs) is another attractive solution considering their advantages in parallelization, effectiveness in feature learning, and model base sufficiency.… read more here.

Keywords: skeleton; action recognition; neural networks; skeleton based ... See more keywords