Point-Wise Mutual Information-Based Video Segmentation with High Temporal Consistency View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2016-11-24

AUTHORS

Margret Keuper , Thomas Brox

ABSTRACT

In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos. While finding the best high-level reasoning of region assignments in videos is the focus of much recent research, temporal consistency in boundary detection has so far only rarely been tackled. We argue that temporally consistent boundaries are a key component to temporally consistent region assignment. The proposed method is based on the point-wise mutual information (PMI) of spatio-temporal voxels. Temporal consistency is established by an evaluation of PMI-based point affinities in the spectral domain over space and time. Thus, the proposed method is independent of any optical flow computation or previously learned motion models. The proposed low-level video segmentation method outperforms the learning-based state of the art in terms of standard region metrics. More... »

PAGES

789-803

Book

TITLE

Computer Vision – ECCV 2016 Workshops

ISBN

978-3-319-49408-1
978-3-319-49409-8

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-49409-8_65

DOI

http://dx.doi.org/10.1007/978-3-319-49409-8_65

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111598750


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, University of Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Department of Computer Science, University of Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Keuper", 
        "givenName": "Margret", 
        "id": "sg:person.013477515133.33", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, University of Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Department of Computer Science, University of Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2016-11-24", 
    "datePublishedReg": "2016-11-24", 
    "description": "In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos. While finding the best high-level reasoning of region assignments in videos is the focus of much recent research, temporal consistency in boundary detection has so far only rarely been tackled. We argue that temporally consistent boundaries are a key component to temporally consistent region assignment. The proposed method is based on the point-wise mutual information (PMI) of spatio-temporal voxels. Temporal consistency is established by an evaluation of PMI-based point affinities in the spectral domain over space and time. Thus, the proposed method is independent of any optical flow computation or previously learned motion models. The proposed low-level video segmentation method outperforms the learning-based state of the art in terms of standard region metrics.", 
    "editor": [
      {
        "familyName": "Hua", 
        "givenName": "Gang", 
        "type": "Person"
      }, 
      {
        "familyName": "J\u00e9gou", 
        "givenName": "Herv\u00e9", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-49409-8_65", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-49408-1", 
        "978-3-319-49409-8"
      ], 
      "name": "Computer Vision \u2013 ECCV 2016 Workshops", 
      "type": "Book"
    }, 
    "keywords": [
      "point-wise mutual information", 
      "temporal consistency", 
      "boundary detection", 
      "video segmentation method", 
      "learning-based state", 
      "high-level reasoning", 
      "optical flow computation", 
      "region assignment", 
      "video segmentation", 
      "hierarchical segmentation", 
      "segmentation method", 
      "mutual information", 
      "high temporal consistency", 
      "motion model", 
      "video", 
      "segmentation", 
      "flow computations", 
      "consistent boundaries", 
      "spectral domain", 
      "key component", 
      "computation", 
      "detection", 
      "reasoning", 
      "metrics", 
      "consistency", 
      "assignment", 
      "recent research", 
      "information", 
      "method", 
      "art", 
      "voxels", 
      "domain", 
      "space", 
      "model", 
      "research", 
      "evaluation", 
      "terms", 
      "time", 
      "focus", 
      "components", 
      "state", 
      "boundaries", 
      "affinity", 
      "paper", 
      "problem"
    ], 
    "name": "Point-Wise Mutual Information-Based Video Segmentation with High Temporal Consistency", 
    "pagination": "789-803", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111598750"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-49409-8_65"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-49409-8_65", 
      "https://app.dimensions.ai/details/publication/pub.1111598750"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-09-02T16:15", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/chapter/chapter_369.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-49409-8_65"
  }
]
 

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.10.1007/978-3-319-49409-8_65'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-49409-8_65'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-49409-8_65'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-49409-8_65'


 

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

116 TRIPLES      22 PREDICATES      69 URIs      62 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-49409-8_65 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N35c25e7e1d57464095ed560ad38fa6ca
4 schema:datePublished 2016-11-24
5 schema:datePublishedReg 2016-11-24
6 schema:description In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos. While finding the best high-level reasoning of region assignments in videos is the focus of much recent research, temporal consistency in boundary detection has so far only rarely been tackled. We argue that temporally consistent boundaries are a key component to temporally consistent region assignment. The proposed method is based on the point-wise mutual information (PMI) of spatio-temporal voxels. Temporal consistency is established by an evaluation of PMI-based point affinities in the spectral domain over space and time. Thus, the proposed method is independent of any optical flow computation or previously learned motion models. The proposed low-level video segmentation method outperforms the learning-based state of the art in terms of standard region metrics.
7 schema:editor Nc060eefc536042c9932b682e337d2002
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N35224b7d3d344bf59b0042082dc61b2a
11 schema:keywords affinity
12 art
13 assignment
14 boundaries
15 boundary detection
16 components
17 computation
18 consistency
19 consistent boundaries
20 detection
21 domain
22 evaluation
23 flow computations
24 focus
25 hierarchical segmentation
26 high temporal consistency
27 high-level reasoning
28 information
29 key component
30 learning-based state
31 method
32 metrics
33 model
34 motion model
35 mutual information
36 optical flow computation
37 paper
38 point-wise mutual information
39 problem
40 reasoning
41 recent research
42 region assignment
43 research
44 segmentation
45 segmentation method
46 space
47 spectral domain
48 state
49 temporal consistency
50 terms
51 time
52 video
53 video segmentation
54 video segmentation method
55 voxels
56 schema:name Point-Wise Mutual Information-Based Video Segmentation with High Temporal Consistency
57 schema:pagination 789-803
58 schema:productId N0bd146e8954e45f085926b16cdd52106
59 N8437db17b0644a42b40c84e16051b595
60 schema:publisher Nbbd850fd7f3640f7afd2dbb4fb92a4a2
61 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111598750
62 https://doi.org/10.1007/978-3-319-49409-8_65
63 schema:sdDatePublished 2022-09-02T16:15
64 schema:sdLicense https://scigraph.springernature.com/explorer/license/
65 schema:sdPublisher N18248bcb1fc64b5aaa5a0bb61e18ffe9
66 schema:url https://doi.org/10.1007/978-3-319-49409-8_65
67 sgo:license sg:explorer/license/
68 sgo:sdDataset chapters
69 rdf:type schema:Chapter
70 N0bd146e8954e45f085926b16cdd52106 schema:name doi
71 schema:value 10.1007/978-3-319-49409-8_65
72 rdf:type schema:PropertyValue
73 N16e0e77559914aaf8f8e812e35703127 rdf:first Ne7b29bdfa4c74bae85225d523ffabd03
74 rdf:rest rdf:nil
75 N18248bcb1fc64b5aaa5a0bb61e18ffe9 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 N26e87c28391645f09493bfde33d7da6a schema:familyName Hua
78 schema:givenName Gang
79 rdf:type schema:Person
80 N35224b7d3d344bf59b0042082dc61b2a schema:isbn 978-3-319-49408-1
81 978-3-319-49409-8
82 schema:name Computer Vision – ECCV 2016 Workshops
83 rdf:type schema:Book
84 N35c25e7e1d57464095ed560ad38fa6ca rdf:first sg:person.013477515133.33
85 rdf:rest Ncac5ebc08491456b90d6e0cfa7977f02
86 N8437db17b0644a42b40c84e16051b595 schema:name dimensions_id
87 schema:value pub.1111598750
88 rdf:type schema:PropertyValue
89 Nbbd850fd7f3640f7afd2dbb4fb92a4a2 schema:name Springer Nature
90 rdf:type schema:Organisation
91 Nc060eefc536042c9932b682e337d2002 rdf:first N26e87c28391645f09493bfde33d7da6a
92 rdf:rest N16e0e77559914aaf8f8e812e35703127
93 Ncac5ebc08491456b90d6e0cfa7977f02 rdf:first sg:person.012443225372.65
94 rdf:rest rdf:nil
95 Ne7b29bdfa4c74bae85225d523ffabd03 schema:familyName Jégou
96 schema:givenName Hervé
97 rdf:type schema:Person
98 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
99 schema:name Information and Computing Sciences
100 rdf:type schema:DefinedTerm
101 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
102 schema:name Artificial Intelligence and Image Processing
103 rdf:type schema:DefinedTerm
104 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
105 schema:familyName Brox
106 schema:givenName Thomas
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
108 rdf:type schema:Person
109 sg:person.013477515133.33 schema:affiliation grid-institutes:grid.5963.9
110 schema:familyName Keuper
111 schema:givenName Margret
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33
113 rdf:type schema:Person
114 grid-institutes:grid.5963.9 schema:alternateName Department of Computer Science, University of Freiburg, Freiburg, Germany
115 schema:name Department of Computer Science, University of Freiburg, Freiburg, Germany
116 rdf:type schema:Organization
 




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


...