Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2022-08-24

AUTHORS

Amirreza Farnoosh, Sarah Ostadabbas

ABSTRACT

In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods. More... »

PAGES

2695-2706

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11263-022-01668-8

DOI

http://dx.doi.org/10.1007/s11263-022-01668-8

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1150460629


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA", 
          "id": "http://www.grid.ac/institutes/grid.261112.7", 
          "name": [
            "Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Farnoosh", 
        "givenName": "Amirreza", 
        "id": "sg:person.016466035730.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016466035730.45"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA", 
          "id": "http://www.grid.ac/institutes/grid.261112.7", 
          "name": [
            "Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ostadabbas", 
        "givenName": "Sarah", 
        "id": "sg:person.0744317364.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0744317364.47"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-1-4757-1904-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031639131", 
          "https://doi.org/10.1007/978-1-4757-1904-8"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2022-08-24", 
    "datePublishedReg": "2022-08-24", 
    "description": "In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s11263-022-01668-8", 
    "isAccessibleForFree": true, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.8566978", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "11", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "130"
      }
    ], 
    "keywords": [
      "pose data", 
      "approximate variational inference", 
      "skeleton data", 
      "skeleton movement", 
      "art methods", 
      "variational inference", 
      "motion data", 
      "latent framework", 
      "segmentation", 
      "superior performance", 
      "latent model", 
      "interpretable patterns", 
      "skeletal motion", 
      "temporal processes", 
      "dataset", 
      "salsa dance", 
      "spatial basis", 
      "model", 
      "data", 
      "framework", 
      "dynamical model", 
      "dynamical generation", 
      "latent modeling", 
      "set", 
      "inference", 
      "performance", 
      "modeling", 
      "process", 
      "vector", 
      "bat flight", 
      "state", 
      "order", 
      "experiments", 
      "method", 
      "generation", 
      "intrinsic states", 
      "time", 
      "motion", 
      "flight", 
      "dynamics", 
      "movement", 
      "walking", 
      "basis", 
      "patterns", 
      "comparison", 
      "regard", 
      "dance", 
      "paper"
    ], 
    "name": "Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion", 
    "pagination": "2695-2706", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1150460629"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11263-022-01668-8"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11263-022-01668-8", 
      "https://app.dimensions.ai/details/publication/pub.1150460629"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-11-24T21:09", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/article/article_947.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s11263-022-01668-8"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01668-8'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01668-8'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01668-8'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01668-8'


 

This table displays all metadata directly associated to this object as RDF triples.

118 TRIPLES      21 PREDICATES      73 URIs      64 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11263-022-01668-8 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N2d3ca481c73845a7b1ef3f5d224fad67
4 schema:citation sg:pub.10.1007/978-1-4757-1904-8
5 schema:datePublished 2022-08-24
6 schema:datePublishedReg 2022-08-24
7 schema:description In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods.
8 schema:genre article
9 schema:isAccessibleForFree true
10 schema:isPartOf Na2c9057075834e8bb8bdc18ebcc30572
11 Nf21977368563437e98baf4c6c1527b63
12 sg:journal.1032807
13 schema:keywords approximate variational inference
14 art methods
15 basis
16 bat flight
17 comparison
18 dance
19 data
20 dataset
21 dynamical generation
22 dynamical model
23 dynamics
24 experiments
25 flight
26 framework
27 generation
28 inference
29 interpretable patterns
30 intrinsic states
31 latent framework
32 latent model
33 latent modeling
34 method
35 model
36 modeling
37 motion
38 motion data
39 movement
40 order
41 paper
42 patterns
43 performance
44 pose data
45 process
46 regard
47 salsa dance
48 segmentation
49 set
50 skeletal motion
51 skeleton data
52 skeleton movement
53 spatial basis
54 state
55 superior performance
56 temporal processes
57 time
58 variational inference
59 vector
60 walking
61 schema:name Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
62 schema:pagination 2695-2706
63 schema:productId N642f78ba53ee4b92af79e47a267b3435
64 Nab4c2a686de340c0aa2d135bfb22d316
65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1150460629
66 https://doi.org/10.1007/s11263-022-01668-8
67 schema:sdDatePublished 2022-11-24T21:09
68 schema:sdLicense https://scigraph.springernature.com/explorer/license/
69 schema:sdPublisher Nf0e8422644ad430cbd7c8a3f3090d41d
70 schema:url https://doi.org/10.1007/s11263-022-01668-8
71 sgo:license sg:explorer/license/
72 sgo:sdDataset articles
73 rdf:type schema:ScholarlyArticle
74 N1f0e509468564de8b9acfefd8afc89f4 rdf:first sg:person.0744317364.47
75 rdf:rest rdf:nil
76 N2d3ca481c73845a7b1ef3f5d224fad67 rdf:first sg:person.016466035730.45
77 rdf:rest N1f0e509468564de8b9acfefd8afc89f4
78 N642f78ba53ee4b92af79e47a267b3435 schema:name dimensions_id
79 schema:value pub.1150460629
80 rdf:type schema:PropertyValue
81 Na2c9057075834e8bb8bdc18ebcc30572 schema:issueNumber 11
82 rdf:type schema:PublicationIssue
83 Nab4c2a686de340c0aa2d135bfb22d316 schema:name doi
84 schema:value 10.1007/s11263-022-01668-8
85 rdf:type schema:PropertyValue
86 Nf0e8422644ad430cbd7c8a3f3090d41d schema:name Springer Nature - SN SciGraph project
87 rdf:type schema:Organization
88 Nf21977368563437e98baf4c6c1527b63 schema:volumeNumber 130
89 rdf:type schema:PublicationVolume
90 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
91 schema:name Information and Computing Sciences
92 rdf:type schema:DefinedTerm
93 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
94 schema:name Artificial Intelligence and Image Processing
95 rdf:type schema:DefinedTerm
96 sg:grant.8566978 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-022-01668-8
97 rdf:type schema:MonetaryGrant
98 sg:journal.1032807 schema:issn 0920-5691
99 1573-1405
100 schema:name International Journal of Computer Vision
101 schema:publisher Springer Nature
102 rdf:type schema:Periodical
103 sg:person.016466035730.45 schema:affiliation grid-institutes:grid.261112.7
104 schema:familyName Farnoosh
105 schema:givenName Amirreza
106 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016466035730.45
107 rdf:type schema:Person
108 sg:person.0744317364.47 schema:affiliation grid-institutes:grid.261112.7
109 schema:familyName Ostadabbas
110 schema:givenName Sarah
111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0744317364.47
112 rdf:type schema:Person
113 sg:pub.10.1007/978-1-4757-1904-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031639131
114 https://doi.org/10.1007/978-1-4757-1904-8
115 rdf:type schema:CreativeWork
116 grid-institutes:grid.261112.7 schema:alternateName Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA
117 schema:name Augmented Cognition Lab, Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA
118 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...