Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2017-03-11

AUTHORS

Wei-Chen Chiu , Fabio Galasso , Mario Fritz

ABSTRACT

Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique. More... »

PAGES

378-395

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-54193-8_24

DOI

http://dx.doi.org/10.1007/978-3-319-54193-8_24

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1084690581


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": "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chiu", 
        "givenName": "Wei-Chen", 
        "id": "sg:person.010551333272.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010551333272.36"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "OSRAM Corporate Technology, Munich, Germany", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "OSRAM Corporate Technology, Munich, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Galasso", 
        "givenName": "Fabio", 
        "id": "sg:person.012741654672.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012741654672.67"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Mario", 
        "id": "sg:person.013361072755.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2017-03-11", 
    "datePublishedReg": "2017-03-11", 
    "description": "Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique.", 
    "editor": [
      {
        "familyName": "Lai", 
        "givenName": "Shang-Hong", 
        "type": "Person"
      }, 
      {
        "familyName": "Lepetit", 
        "givenName": "Vincent", 
        "type": "Person"
      }, 
      {
        "familyName": "Nishino", 
        "givenName": "Ko", 
        "type": "Person"
      }, 
      {
        "familyName": "Sato", 
        "givenName": "Yoichi", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-54193-8_24", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-54192-1", 
        "978-3-319-54193-8"
      ], 
      "name": "Computer Vision \u2013 ACCV 2016", 
      "type": "Book"
    }, 
    "keywords": [
      "stereo video", 
      "segmentation technique", 
      "video segmentation technique", 
      "art segmentation methods", 
      "novel ensemble method", 
      "segmentation performance", 
      "differentiable proxy", 
      "segmentation method", 
      "ensemble method", 
      "data types", 
      "rich information", 
      "video", 
      "efficient scheme", 
      "depth cues", 
      "new benchmark", 
      "segmentation", 
      "such data", 
      "novel regressor", 
      "benchmarks", 
      "regressors", 
      "annotation", 
      "metrics", 
      "images", 
      "adaptive", 
      "ensemble", 
      "scheme", 
      "technique", 
      "information", 
      "method", 
      "performance", 
      "challenges", 
      "model", 
      "data", 
      "motion", 
      "cues", 
      "amount", 
      "state", 
      "progress", 
      "proxy", 
      "types", 
      "theory", 
      "appearance", 
      "baseline", 
      "spectral theory"
    ], 
    "name": "Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles", 
    "pagination": "378-395", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1084690581"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-54193-8_24"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-54193-8_24", 
      "https://app.dimensions.ai/details/publication/pub.1084690581"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:13", 
    "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/chapter/chapter_201.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-54193-8_24"
  }
]
 

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.10.1007/978-3-319-54193-8_24'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54193-8_24'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54193-8_24'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54193-8_24'


 

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

135 TRIPLES      22 PREDICATES      68 URIs      61 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-54193-8_24 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N39d081aba0184e0e84a92bbb8ee7e45e
4 schema:datePublished 2017-03-11
5 schema:datePublishedReg 2017-03-11
6 schema:description Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique.
7 schema:editor Nfcb7e85bcd654b25b60f9949fae417fd
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N8c3f8ca77e744eca80a856cbf1fa7316
11 schema:keywords adaptive
12 amount
13 annotation
14 appearance
15 art segmentation methods
16 baseline
17 benchmarks
18 challenges
19 cues
20 data
21 data types
22 depth cues
23 differentiable proxy
24 efficient scheme
25 ensemble
26 ensemble method
27 images
28 information
29 method
30 metrics
31 model
32 motion
33 new benchmark
34 novel ensemble method
35 novel regressor
36 performance
37 progress
38 proxy
39 regressors
40 rich information
41 scheme
42 segmentation
43 segmentation method
44 segmentation performance
45 segmentation technique
46 spectral theory
47 state
48 stereo video
49 such data
50 technique
51 theory
52 types
53 video
54 video segmentation technique
55 schema:name Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles
56 schema:pagination 378-395
57 schema:productId N27369dfbccb64e01a2f701ac87120cf1
58 N855a57ddf06643ca966732602cd8af74
59 schema:publisher Nbabd7fde304742a699a3f2e7f2db963f
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084690581
61 https://doi.org/10.1007/978-3-319-54193-8_24
62 schema:sdDatePublished 2022-11-24T21:13
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher N2c3f3f6693154ec4951c4abb82e11fd0
65 schema:url https://doi.org/10.1007/978-3-319-54193-8_24
66 sgo:license sg:explorer/license/
67 sgo:sdDataset chapters
68 rdf:type schema:Chapter
69 N14a6967cc9cf4d0d8d78bf49dea2bb63 schema:familyName Nishino
70 schema:givenName Ko
71 rdf:type schema:Person
72 N27369dfbccb64e01a2f701ac87120cf1 schema:name dimensions_id
73 schema:value pub.1084690581
74 rdf:type schema:PropertyValue
75 N2c3f3f6693154ec4951c4abb82e11fd0 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 N2ccce12f8f7c409c92812e20a4b622de schema:familyName Sato
78 schema:givenName Yoichi
79 rdf:type schema:Person
80 N39d081aba0184e0e84a92bbb8ee7e45e rdf:first sg:person.010551333272.36
81 rdf:rest N65f866e489cb46d9bd1a38586c3fd895
82 N5d991f6eeab542fa87b085d64e629d2e schema:familyName Lepetit
83 schema:givenName Vincent
84 rdf:type schema:Person
85 N5eac4d9fc4e440d7a27680f69ed4e53f rdf:first N5d991f6eeab542fa87b085d64e629d2e
86 rdf:rest Nc835875f711544428841c94ac8a09b4d
87 N65f866e489cb46d9bd1a38586c3fd895 rdf:first sg:person.012741654672.67
88 rdf:rest Nc6054c586c804459b3eb0b0787fea855
89 N75472b7dbd8e4041a8eaf26b503f9054 rdf:first N2ccce12f8f7c409c92812e20a4b622de
90 rdf:rest rdf:nil
91 N855a57ddf06643ca966732602cd8af74 schema:name doi
92 schema:value 10.1007/978-3-319-54193-8_24
93 rdf:type schema:PropertyValue
94 N8c3f8ca77e744eca80a856cbf1fa7316 schema:isbn 978-3-319-54192-1
95 978-3-319-54193-8
96 schema:name Computer Vision – ACCV 2016
97 rdf:type schema:Book
98 Na28c7d33a9664de5a17805a9393c4952 schema:familyName Lai
99 schema:givenName Shang-Hong
100 rdf:type schema:Person
101 Nbabd7fde304742a699a3f2e7f2db963f schema:name Springer Nature
102 rdf:type schema:Organisation
103 Nc6054c586c804459b3eb0b0787fea855 rdf:first sg:person.013361072755.17
104 rdf:rest rdf:nil
105 Nc835875f711544428841c94ac8a09b4d rdf:first N14a6967cc9cf4d0d8d78bf49dea2bb63
106 rdf:rest N75472b7dbd8e4041a8eaf26b503f9054
107 Nfcb7e85bcd654b25b60f9949fae417fd rdf:first Na28c7d33a9664de5a17805a9393c4952
108 rdf:rest N5eac4d9fc4e440d7a27680f69ed4e53f
109 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
110 schema:name Information and Computing Sciences
111 rdf:type schema:DefinedTerm
112 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
113 schema:name Artificial Intelligence and Image Processing
114 rdf:type schema:DefinedTerm
115 sg:person.010551333272.36 schema:affiliation grid-institutes:grid.419528.3
116 schema:familyName Chiu
117 schema:givenName Wei-Chen
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010551333272.36
119 rdf:type schema:Person
120 sg:person.012741654672.67 schema:affiliation grid-institutes:None
121 schema:familyName Galasso
122 schema:givenName Fabio
123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012741654672.67
124 rdf:type schema:Person
125 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.419528.3
126 schema:familyName Fritz
127 schema:givenName Mario
128 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
129 rdf:type schema:Person
130 grid-institutes:None schema:alternateName OSRAM Corporate Technology, Munich, Germany
131 schema:name OSRAM Corporate Technology, Munich, Germany
132 rdf:type schema:Organization
133 grid-institutes:grid.419528.3 schema:alternateName Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany
134 schema:name Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany
135 rdf:type schema:Organization
 




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


...