An Attention Enhanced Graph Convolutional LSTM Network for
- Slides: 70
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition Chenyang Si Wentao Chen Wei Wang Liang Wang Tieniu Tan National Lab of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences (CASIA) CVPR 2019 1
Related Methods o Outline Routing AAAI 2019 CVPR 2019 AS-GCN ST-GCN AAAI 2018 Motif AAAI 2019 IJCAI 2018 HCN MTLN CVPR 2017 CVPR 2016 VA-LSTM MANs IJCAI 2018 ECCV 2018 CVPR 2019 SLR AGC-LSTM
Related Methods o Outline Routing GCNs: AAAI 2019 CVPR 2019 AS-GCN ST-GCN AAAI 2018 Motif AAAI 2019 IJCAI 2018 CNNs: HCN MTLN CVPR 2017 RNNs: CVPR 2016 VA-LSTM MANs IJCAI 2018 ECCV 2018 CVPR 2019 SLR AGC-LSTM
Related Methods o Outline Routing GCNs: AAAI 2019 CVPR 2019 AS-GCN ST-GCN AAAI 2018 Motif AAAI 2019 IJCAI 2018 CNNs: HCN MTLN CVPR 2017 RNNs: CVPR 2016 VA-LSTM MANs IJCAI 2018 ECCV 2018 CVPR 2019 SLR AGC-LSTM
Overview o Background What is skeleton-based action Recognition? Classification Model
Background o Two notable characteristics for human skeleton sequences: o 1) There are strong correlations between each node and its adjacent nodes so that the skeleton frames contain abundant body structural information o 2) There is a co-occurrence relationship between spatial and temporal domains
Background o Two notable characteristics for human skeleton sequences: o 1) There are strong correlations between each node and its adjacent nodes so that the skeleton frames contain abundant body structural information o 2) There is a co-occurrence relationship between spatial and temporal domains GCNs (spatial) RNNs (temporal)
Background o Motivation: synchronously learning spatio-temporal characteristics o Method: = + GCNs (spatial) RNNs (temporal) AGC-LSTM (spatial+ temporal)
Method o Architecture:
Method o Architecture:
Method Tim e o Joints Feature Representation:
Method o Joints Feature Representation: map the 3 D coordinate of each joint into a high-dimensional feature space (joint num) (feature dimension) Frame difference features:
Method o Joints Feature Representation: Feature Augmentation:
Method o Joints Feature Representation: Feature Augmentation: Dispel scale variance between both features:
Method o Joints Feature Representation:
Method o Architecture:
Method o Architecture:
Method o Architecture:
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM How to perform graph convolutional here ?
Formulation F 1 F 3 F 2 3 4 Uni-labeling : W = [w 1 ] 1 2 F 6 6 F 4 5 F 5 7 Output feature: F 7 1. 1 1 1 2. 3 1 1 1. 2 × 1 F 2 ·W 1 1 2. 1 1 1 3. 1 1 4. 4 1 F 1 1 3. 2 Input feature: T T 1 = F 3 F 4 F 5 F 6 1 F 7
Formulation F 1 F 3 F 2 3 4 Uni-labeling : W = [w 1 ] 1 2 F 6 6 F 4 5 F 5 7 Output feature: F 7 1. 1 1 1 2. 3 1 1 1. 2 1 1 F 2 ·W 1 1 2. 1 1 1 3. 1 1 4. 4 Define × F 1 1 3. 2 Input feature: T T 1 = F 3 F 4 F 5 F 6 1 F 7
Formulation F 1 F 3 F 2 3 4 Uni-labeling : W = [w 1 ] 1 2 F 6 6 F 4 5 F 5 7 Output feature: F 7 T T 1. 1 1 1 2. 3 1 1 1. 2 × Define F 2 ·W 1 1 2. 1 1 1 3. 1 1 4. 4 Input feature: 1 1 3. 2 Output feature = W 1 F 1 1 = F 3 F 4 F 5 F 6 1 Input feature F 7
Method o Attention Enhanced Graph Convolutional LSTM How to perform graph convolutional here ?
Method o Attention Enhanced Graph Convolutional LSTM How to perform graph convolutional here ?
Method o Attention Enhanced Graph Convolutional LSTM How to perform graph convolutional here ?
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM Similarly…
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Attention Enhanced Graph Convolutional LSTM
Method o Architecture:
Method o Architecture:
Method o Architecture:
Method o Architecture: at the last AGC-LSTM layer, for each frame t : Global Feature: Local Feature:
Method o Architecture: at the last AGC-LSTM layer, for each frame t : Global Feature: (at time step t) Local Feature: (at time step t)
Method o Learning AGC-LSTM: and are transformed into scores and
Method o Learning AGC-LSTM: and are transformed into scores and
Method o Learning AGC-LSTM:
Method o Learning AGC-LSTM: For classification
Method o Learning AGC-LSTM: (the number of time step on 3 rd AGC-LSTM layer) (the number of classes) (global) (local)
Method o Learning AGC-LSTM:
Method o Learning AGC-LSTM:
Method o Learning AGC-LSTM: (layer of AGC-LSTM)
Method o Learning AGC-LSTM: (time step) (layer of AGC-LSTM) (the number of time step on j-th AGC-LSTM layer)
Method o Learning AGC-LSTM: (joint dimension) (layer of AGC-LSTM) (time step) (the number of time step on j-th AGC-LSTM layer)
Method o Learning AGC-LSTM: (joint Feature dimension) (layer of AGC-LSTM) (time step) (the number of time step on j-th AGC-LSTM layer) aims to pay equal attention to different joints
Method o Learning AGC-LSTM:
Method o Learning AGC-LSTM: limit the number of interested nodes
Experiments o NTU RGB+D dataset
Experiments o NTU RGB+D dataset
Experiments o NTU RGB+D dataset
Experiments o NTU RGB+D dataset (basic LSTM) (LSTM + Graph) (LSTM + timepooling)
Experiments o Northwestern-UCLA Dataset
Experiments o Northwestern-UCLA Dataset UCLA: 1494 samples covering 10 categories (NTU: 56, 880 samples covering 60 categories)
Experiments o Northwestern-UCLA Dataset UCLA: 1494 samples covering 10 categories (NTU: 56, 880 samples covering 60 categories)
Thanks!
- Convolutional lstm network
- Modeling relational data with graph convolutional networks
- Convolution neural network ppt
- Alternatives to convolutional neural networks
- Feature map in cnn
- Michelle benjamin phd
- Cpesn pharmacy locator
- Rnn andrew ng
- Rnn lstm
- Structure of lstm
- Mxnet lstm
- Cec lstm
- Pixel rnn
- Iamtrask github
- Lstm
- Lstm lecture
- Jazz improvisation with lstm
- Nvida stock
- Cs 7643 github
- Lstm audio
- Lstm julia
- Iso 22301 utbildning
- Visualizing and understanding convolutional neural networks
- Novell typiska drag
- Nationell inriktning för artificiell intelligens
- Ekologiskt fotavtryck
- Varför kallas perioden 1918-1939 för mellankrigstiden
- En lathund för arbete med kontinuitetshantering
- Särskild löneskatt för pensionskostnader
- Convolutional encoder
- Convolutional neural networks for visual recognition
- Leon gatys
- Personlig tidbok
- Anatomi organ reproduksi
- Förklara densitet för barn
- Convolutional codes solved examples
- Datorkunskap för nybörjare
- Convolutional codes
- Boverket ka
- Hur skriver man en tes
- Autokratiskt ledarskap
- Nyckelkompetenser för livslångt lärande
- Påbyggnader för flakfordon
- Lufttryck formel
- Svenskt ramverk för digital samverkan
- Urban torhamn
- Presentera för publik crossboss
- Argument för teckenspråk som minoritetsspråk
- Kanaans land
- Treserva lathund
- Image super resolution using deep convolutional networks
- Luftstrupen för medicinare
- Bästa kameran för astrofoto
- Centrum för kunskap och säkerhet
- Programskede byggprocessen
- Bra mat för unga idrottare
- Verktyg för automatisering av utbetalningar
- Rutin för avvikelsehantering
- Smärtskolan kunskap för livet
- Ministerstyre för och nackdelar
- Tack för att ni har lyssnat
- Vad är referatmarkeringar
- Redogör för vad psykologi är
- Borstål, egenskaper
- Atmosfr
- Borra hål för knoppar
- Orubbliga rättigheter
- Hur räknar man standardavvikelse
- Tack för att ni har lyssnat
- Steg för steg rita
- Csrmm