Learning Sequence Representations by Non-local Recurrent Neural Memory View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-08-14

AUTHORS

Wenjie Pei, Xin Feng, Canmiao Fu, Qiong Cao, Guangming Lu, Yu-Wing Tai

ABSTRACT

The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model one-order information interactions explicitly between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since the temporal features learned by one-order interactions cannot be maintained for a long term due to temporal information dilution and gradient vanishing. To tackle this limitation, we propose the non-local recurrent neural memory (NRNM) for supervised sequence representation learning, which performs non-local operations by means of self-attention mechanism to learn full-order interactions within a sliding temporal memory block and models global interactions between memory blocks in a gated recurrent manner. Consequently, our model is able to capture long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We validate the effectiveness and generalization of our NRNM on three types of sequence applications across different modalities, including sequence classification, step-wise sequential prediction and sequence similarity learning. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications. More... »

PAGES

2532-2552

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11263-022-01648-y

DOI

http://dx.doi.org/10.1007/s11263-022-01648-y

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1150235896


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": "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China", 
          "id": "http://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pei", 
        "givenName": "Wenjie", 
        "id": "sg:person.016522526053.44", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016522526053.44"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China", 
          "id": "http://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Feng", 
        "givenName": "Xin", 
        "id": "sg:person.016341302565.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016341302565.93"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Tecent, Shenzhen, China", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Tecent, Shenzhen, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fu", 
        "givenName": "Canmiao", 
        "id": "sg:person.07616033025.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07616033025.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "JD Explore Academy, Beijing, China", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "JD Explore Academy, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cao", 
        "givenName": "Qiong", 
        "id": "sg:person.010714255313.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010714255313.93"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China", 
          "id": "http://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lu", 
        "givenName": "Guangming", 
        "id": "sg:person.011722640217.50", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011722640217.50"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Kuaishou Technology, Beijing, China", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Kuaishou Technology, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tai", 
        "givenName": "Yu-Wing", 
        "id": "sg:person.0640617606.96", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0640617606.96"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-030-01246-5_49", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107454663", 
          "https://doi.org/10.1007/978-3-030-01246-5_49"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-58555-6_12", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1132652361", 
          "https://doi.org/10.1007/978-3-030-58555-6_12"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-58452-8_13", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1132270339", 
          "https://doi.org/10.1007/978-3-030-58452-8_13"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-46487-9_50", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017854486", 
          "https://doi.org/10.1007/978-3-319-46487-9_50"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-01267-0_19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107463400", 
          "https://doi.org/10.1007/978-3-030-01267-0_19"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-016-0001-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085379182", 
          "https://doi.org/10.1038/s41598-016-0001-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12859-018-2067-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1103887669", 
          "https://doi.org/10.1186/s12859-018-2067-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-01240-3_9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107463389", 
          "https://doi.org/10.1007/978-3-030-01240-3_9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-46448-0_31", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003201030", 
          "https://doi.org/10.1007/978-3-319-46448-0_31"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-01228-1_25", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107463260", 
          "https://doi.org/10.1007/978-3-030-01228-1_25"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-01246-5_7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107454666", 
          "https://doi.org/10.1007/978-3-030-01246-5_7"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2022-08-14", 
    "datePublishedReg": "2022-08-14", 
    "description": "The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model one-order information interactions explicitly between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since the temporal features learned by one-order interactions cannot be maintained for a long term due to temporal information dilution and gradient vanishing. To tackle this limitation, we propose the non-local recurrent neural memory (NRNM) for supervised sequence representation learning, which performs non-local operations by means of self-attention mechanism to learn full-order interactions within a sliding temporal memory block and models global interactions between memory blocks in a gated recurrent manner. Consequently, our model is able to capture long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We validate the effectiveness and generalization of our NRNM on three types of sequence applications across different modalities, including sequence classification, step-wise sequential prediction and sequence similarity learning. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s11263-022-01648-y", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "10", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "130"
      }
    ], 
    "keywords": [
      "long-range temporal dependencies", 
      "neural memory", 
      "temporal dependencies", 
      "representation learning", 
      "self-attention mechanism", 
      "long-range dependencies", 
      "recurrent neural network", 
      "sequence representation", 
      "different modalities", 
      "sequential prediction", 
      "temporal features", 
      "high-level features", 
      "learning", 
      "memory", 
      "similarity learning", 
      "gradient vanishing", 
      "information dilution", 
      "neural network", 
      "non-local operation", 
      "higher-order interactions", 
      "potential limitations", 
      "recurrent manner", 
      "information interaction", 
      "art methods", 
      "memory blocks", 
      "sequence classification", 
      "representation", 
      "interaction", 
      "long term", 
      "modalities", 
      "limitations", 
      "sequence application", 
      "model", 
      "dependency", 
      "generalization", 
      "features", 
      "global interactions", 
      "effectiveness", 
      "prediction", 
      "key challenges", 
      "typical methods", 
      "network", 
      "challenges", 
      "terms", 
      "types", 
      "mechanism", 
      "classification", 
      "state", 
      "manner", 
      "step", 
      "means", 
      "block", 
      "capability", 
      "method", 
      "sequence", 
      "time step", 
      "applications", 
      "operation", 
      "full-order interactions", 
      "adjacent time steps", 
      "vanishing", 
      "dilution"
    ], 
    "name": "Learning Sequence Representations by Non-local Recurrent Neural Memory", 
    "pagination": "2532-2552", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1150235896"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11263-022-01648-y"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11263-022-01648-y", 
      "https://app.dimensions.ai/details/publication/pub.1150235896"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-12-01T06:45", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/article/article_950.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s11263-022-01648-y"
  }
]
 

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/s11263-022-01648-y'

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/s11263-022-01648-y'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01648-y'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01648-y'


 

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

205 TRIPLES      21 PREDICATES      97 URIs      78 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11263-022-01648-y schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N95917287118147528120ab094afb61af
4 schema:citation sg:pub.10.1007/978-3-030-01228-1_25
5 sg:pub.10.1007/978-3-030-01240-3_9
6 sg:pub.10.1007/978-3-030-01246-5_49
7 sg:pub.10.1007/978-3-030-01246-5_7
8 sg:pub.10.1007/978-3-030-01267-0_19
9 sg:pub.10.1007/978-3-030-58452-8_13
10 sg:pub.10.1007/978-3-030-58555-6_12
11 sg:pub.10.1007/978-3-319-46448-0_31
12 sg:pub.10.1007/978-3-319-46487-9_50
13 sg:pub.10.1038/s41598-016-0001-8
14 sg:pub.10.1186/s12859-018-2067-8
15 schema:datePublished 2022-08-14
16 schema:datePublishedReg 2022-08-14
17 schema:description The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model one-order information interactions explicitly between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since the temporal features learned by one-order interactions cannot be maintained for a long term due to temporal information dilution and gradient vanishing. To tackle this limitation, we propose the non-local recurrent neural memory (NRNM) for supervised sequence representation learning, which performs non-local operations by means of self-attention mechanism to learn full-order interactions within a sliding temporal memory block and models global interactions between memory blocks in a gated recurrent manner. Consequently, our model is able to capture long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We validate the effectiveness and generalization of our NRNM on three types of sequence applications across different modalities, including sequence classification, step-wise sequential prediction and sequence similarity learning. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications.
18 schema:genre article
19 schema:isAccessibleForFree false
20 schema:isPartOf N69b245cbea604a5d87086c24000ba7a9
21 N8e71613a62354d2e9cdc0defe3bdba7d
22 sg:journal.1032807
23 schema:keywords adjacent time steps
24 applications
25 art methods
26 block
27 capability
28 challenges
29 classification
30 dependency
31 different modalities
32 dilution
33 effectiveness
34 features
35 full-order interactions
36 generalization
37 global interactions
38 gradient vanishing
39 high-level features
40 higher-order interactions
41 information dilution
42 information interaction
43 interaction
44 key challenges
45 learning
46 limitations
47 long term
48 long-range dependencies
49 long-range temporal dependencies
50 manner
51 means
52 mechanism
53 memory
54 memory blocks
55 method
56 modalities
57 model
58 network
59 neural memory
60 neural network
61 non-local operation
62 operation
63 potential limitations
64 prediction
65 recurrent manner
66 recurrent neural network
67 representation
68 representation learning
69 self-attention mechanism
70 sequence
71 sequence application
72 sequence classification
73 sequence representation
74 sequential prediction
75 similarity learning
76 state
77 step
78 temporal dependencies
79 temporal features
80 terms
81 time step
82 types
83 typical methods
84 vanishing
85 schema:name Learning Sequence Representations by Non-local Recurrent Neural Memory
86 schema:pagination 2532-2552
87 schema:productId N4f9e3182a4c546b1b6fb78672a2c503d
88 Ne124164265aa4101b45ad03fd49b1a6e
89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1150235896
90 https://doi.org/10.1007/s11263-022-01648-y
91 schema:sdDatePublished 2022-12-01T06:45
92 schema:sdLicense https://scigraph.springernature.com/explorer/license/
93 schema:sdPublisher N22f6a07a2df644c79e06b9d24f672da9
94 schema:url https://doi.org/10.1007/s11263-022-01648-y
95 sgo:license sg:explorer/license/
96 sgo:sdDataset articles
97 rdf:type schema:ScholarlyArticle
98 N1d2a934292b84324845e4e72396dc765 rdf:first sg:person.07616033025.22
99 rdf:rest Naf1df4655d7e45a5aa80828c860e49d6
100 N1d5d2502fba64009a2b5cfb6a0360d0a rdf:first sg:person.011722640217.50
101 rdf:rest Ndc5dade978b5484497494a690f03beec
102 N22f6a07a2df644c79e06b9d24f672da9 schema:name Springer Nature - SN SciGraph project
103 rdf:type schema:Organization
104 N4f9e3182a4c546b1b6fb78672a2c503d schema:name doi
105 schema:value 10.1007/s11263-022-01648-y
106 rdf:type schema:PropertyValue
107 N69b245cbea604a5d87086c24000ba7a9 schema:volumeNumber 130
108 rdf:type schema:PublicationVolume
109 N8e71613a62354d2e9cdc0defe3bdba7d schema:issueNumber 10
110 rdf:type schema:PublicationIssue
111 N95917287118147528120ab094afb61af rdf:first sg:person.016522526053.44
112 rdf:rest Nbd738781c5df492baaf987f8d79ce46c
113 Naf1df4655d7e45a5aa80828c860e49d6 rdf:first sg:person.010714255313.93
114 rdf:rest N1d5d2502fba64009a2b5cfb6a0360d0a
115 Nbd738781c5df492baaf987f8d79ce46c rdf:first sg:person.016341302565.93
116 rdf:rest N1d2a934292b84324845e4e72396dc765
117 Ndc5dade978b5484497494a690f03beec rdf:first sg:person.0640617606.96
118 rdf:rest rdf:nil
119 Ne124164265aa4101b45ad03fd49b1a6e schema:name dimensions_id
120 schema:value pub.1150235896
121 rdf:type schema:PropertyValue
122 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
123 schema:name Information and Computing Sciences
124 rdf:type schema:DefinedTerm
125 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
126 schema:name Artificial Intelligence and Image Processing
127 rdf:type schema:DefinedTerm
128 sg:journal.1032807 schema:issn 0920-5691
129 1573-1405
130 schema:name International Journal of Computer Vision
131 schema:publisher Springer Nature
132 rdf:type schema:Periodical
133 sg:person.010714255313.93 schema:affiliation grid-institutes:None
134 schema:familyName Cao
135 schema:givenName Qiong
136 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010714255313.93
137 rdf:type schema:Person
138 sg:person.011722640217.50 schema:affiliation grid-institutes:grid.19373.3f
139 schema:familyName Lu
140 schema:givenName Guangming
141 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011722640217.50
142 rdf:type schema:Person
143 sg:person.016341302565.93 schema:affiliation grid-institutes:grid.19373.3f
144 schema:familyName Feng
145 schema:givenName Xin
146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016341302565.93
147 rdf:type schema:Person
148 sg:person.016522526053.44 schema:affiliation grid-institutes:grid.19373.3f
149 schema:familyName Pei
150 schema:givenName Wenjie
151 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016522526053.44
152 rdf:type schema:Person
153 sg:person.0640617606.96 schema:affiliation grid-institutes:None
154 schema:familyName Tai
155 schema:givenName Yu-Wing
156 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0640617606.96
157 rdf:type schema:Person
158 sg:person.07616033025.22 schema:affiliation grid-institutes:None
159 schema:familyName Fu
160 schema:givenName Canmiao
161 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07616033025.22
162 rdf:type schema:Person
163 sg:pub.10.1007/978-3-030-01228-1_25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463260
164 https://doi.org/10.1007/978-3-030-01228-1_25
165 rdf:type schema:CreativeWork
166 sg:pub.10.1007/978-3-030-01240-3_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463389
167 https://doi.org/10.1007/978-3-030-01240-3_9
168 rdf:type schema:CreativeWork
169 sg:pub.10.1007/978-3-030-01246-5_49 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454663
170 https://doi.org/10.1007/978-3-030-01246-5_49
171 rdf:type schema:CreativeWork
172 sg:pub.10.1007/978-3-030-01246-5_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454666
173 https://doi.org/10.1007/978-3-030-01246-5_7
174 rdf:type schema:CreativeWork
175 sg:pub.10.1007/978-3-030-01267-0_19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463400
176 https://doi.org/10.1007/978-3-030-01267-0_19
177 rdf:type schema:CreativeWork
178 sg:pub.10.1007/978-3-030-58452-8_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132270339
179 https://doi.org/10.1007/978-3-030-58452-8_13
180 rdf:type schema:CreativeWork
181 sg:pub.10.1007/978-3-030-58555-6_12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132652361
182 https://doi.org/10.1007/978-3-030-58555-6_12
183 rdf:type schema:CreativeWork
184 sg:pub.10.1007/978-3-319-46448-0_31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003201030
185 https://doi.org/10.1007/978-3-319-46448-0_31
186 rdf:type schema:CreativeWork
187 sg:pub.10.1007/978-3-319-46487-9_50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017854486
188 https://doi.org/10.1007/978-3-319-46487-9_50
189 rdf:type schema:CreativeWork
190 sg:pub.10.1038/s41598-016-0001-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085379182
191 https://doi.org/10.1038/s41598-016-0001-8
192 rdf:type schema:CreativeWork
193 sg:pub.10.1186/s12859-018-2067-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103887669
194 https://doi.org/10.1186/s12859-018-2067-8
195 rdf:type schema:CreativeWork
196 grid-institutes:None schema:alternateName JD Explore Academy, Beijing, China
197 Kuaishou Technology, Beijing, China
198 Tecent, Shenzhen, China
199 schema:name JD Explore Academy, Beijing, China
200 Kuaishou Technology, Beijing, China
201 Tecent, Shenzhen, China
202 rdf:type schema:Organization
203 grid-institutes:grid.19373.3f schema:alternateName Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China
204 schema:name Department of Computer Science, Harbin Institute of Technology at Shenzhen, 518057, Shenzhen, Guangdong, China
205 rdf:type schema:Organization
 




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


...