Long-Short Graph Memory Network for Skeleton-based Action Recognition

Huang, Junqin; Huang, Zhenhuan; Xiang, Xiang; Gong, Xuan; Zhang, Baochang

doi:10.1109/wacv45572.2020.9093598

Cited by 23 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Except for the basic bidirectional LSTM, J. Huang et al [ 97 ] deployed GCN on LSTM to enhance its ability of extracting spatial features. Precisely, they provided a LSGM that consists of one original LSTM cell followed by two GCN layers.…”

Section: A New Taxonomy For Skeleton-gnn-based Harmentioning

confidence: 99%

“…Most papers [ 73 , 74 , 97 , 109 , 126 ] calculated the temporal attention map with the most popular recipe, which adopts a sequence consisted of a pooling layer, a fully connection (FC) layer or one 1DCNN layer, followed by Relu or softmax activation functions. For example, L. Shi et al [ 73 ] performed attention by 1DCNN.…”

Section: The Common Frameworkmentioning

confidence: 99%

“…The colors identity each dataset. In ( b ), the numbers around dots denote [ 12 , 13 , 29 , 56 , 59 , 61 , 69 , 72 , 74 , 75 , 83 , 85 , 87 , 88 , 89 , 90 , 92 , 97 , 110 , 115 , 135 , 136 , 138 , 141 , 182 ] respectively in ascending order.…”

Section: Figurementioning

confidence: 99%

“…Check for details. StateFarm [ 192 ] Safe Drive, Text-Right, Talk on the Phone-Right, Text-Left, Talk on the Phone-Left, Operate the Radio, Drink, Reach Behind, Hair and Makeup, Talk to Passenger DHG-14/28 [ 70 ] Grab, Tap, Expand, Pinch, Rotate Clockwise, Rotatr Couter Clockwise, Swipe Right, Swipe Left, Swipe Up, Swipe Down, Swipe X, Swipe V, Swipe +, Shake Volleyball [ 115 ] Wait, Set, Dig, Fall, Spike, Block, Jump, Move, Stand SYSU [ 62 , 69 , 72 , 75 , 85 , 90 , 97 , 135 , 136 ] Drink, Pour, Call Phone, Play Phone, Wear Backpacks, Pack Backpacks, Sit Chair, Move Chair, Take Out Wallet, Take From Wallet, Mope, Sweep SHREC’17 [ 70 ] Grab, Tap, Expand, Pinch, Rotate Clockwise, Rotatr Couter Clockwise, Swipe Right, Swipe Left, Swipe Up, Swipe Down, Swipe X, Swipe V, Swipe + and Shake Kinetics [ 13 , 14 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 57 , 60 , …”

Section: Table A1mentioning

confidence: 99%

See 3 more Smart Citations

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Feng

Meunier

2022

Sensors

View full text Add to dashboard Cite

Human action recognition has been applied in many fields, such as video surveillance and human computer interaction, where it helps to improve performance. Numerous reviews of the literature have been done, but rarely have these reviews concentrated on skeleton-graph-based approaches. Connecting the skeleton joints as in the physical appearance can naturally generate a graph. This paper provides an up-to-date review for readers on skeleton graph-neural-network-based human action recognition. After analyzing previous related studies, a new taxonomy for skeleton-GNN-based methods is proposed according to their designs, and their merits and demerits are analyzed. In addition, the datasets and codes are discussed. Finally, future research directions are suggested.

show abstract

Section: A New Taxonomy For Skeleton-gnn-based Harmentioning

confidence: 99%

Section: The Common Frameworkmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

Section: Table A1mentioning

confidence: 99%

See 2 more Smart Citations

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Feng

Meunier

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Huang et al [ 33 ] introduced a new recurrent network model—long-short graph memory network (LSGM). This type of neural network tries to combine the properties of GCN type layers with LSTM type layers.…”

Section: Related Workmentioning

confidence: 99%

Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition

Nan

Trăşcău

Florea

et al. 2021

Sensors

View full text Add to dashboard Cite

Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from videos that work with data represented in the form of skeleton poses. These methods are based on the most widely used techniques for this problem—Graph Convolutional Networks (GCNs), Temporal Convolutional Networks (TCNs) and Recurrent Neural Networks (RNNs). Initially, the paper explores and compares different ways to extract the most relevant spatial and temporal characteristics for a sequence of frames describing an action. Based on this comparative analysis, we show how a TCN type unit can be extended to work even on the characteristics extracted from the spatial domain. To validate our approach, we test it against a benchmark often used for human action recognition problems and we show that our solution obtains comparable results to the state-of-the-art, but with a significant increase in the inference speed.

show abstract