Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "Eric M\u00fcller-Budack, Jonas Theiner, Sebastian 
2
  "author": "Eric M\u00fcller-Budack, Jonas Theiner, Sebastian 
            
3
Diering, Maximilian Idahl, Ralph Ewerth",
3
Diering, Maximilian Idahl, Ralph Ewerth",
            
4
  "author_email": "eric.mueller@tib.eu",
4
  "author_email": "eric.mueller@tib.eu",
            
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
6
  "doi": "10.25835/0084897",
6
  "doi": "10.25835/0084897",
            
7
  "doi_date_published": "2020-06-04",
7
  "doi_date_published": "2020-06-04",
            
8
  "doi_publisher": "LUIS",
8
  "doi_publisher": "LUIS",
            
9
  "doi_status": "true",
9
  "doi_status": "true",
            
10
  "domain": "https://data.uni-hannover.de",
10
  "domain": "https://data.uni-hannover.de",
            
11
  "groups": [],
11
  "groups": [],
            
12
  "have_copyright": "Yes",
12
  "have_copyright": "Yes",
            
13
  "id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
13
  "id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
14
  "isopen": false,
14
  "isopen": false,
            
15
  "license_id": "CC-BY-NC-3.0",
15
  "license_id": "CC-BY-NC-3.0",
            
16
  "license_title": "CC-BY-NC-3.0",
16
  "license_title": "CC-BY-NC-3.0",
            
17
  "maintainer": "Eric M\u00fcller-Budack",
17
  "maintainer": "Eric M\u00fcller-Budack",
            
18
  "maintainer_email": "eric.mueller@tib.eu",
18
  "maintainer_email": "eric.mueller@tib.eu",
            
19
  "metadata_created": "2021-10-14T10:16:03.098485",
19
  "metadata_created": "2021-10-14T10:16:03.098485",
            
n
20
  "metadata_modified": "2021-10-14T10:16:03.098491",
n
20
  "metadata_modified": "2023-01-12T13:14:21.448200",
            
21
  "name": "luh-news400",
21
  "name": "luh-news400",
            
22
  "notes": "# Multimodal Analytics for Real-world News using Measures 
22
  "notes": "# Multimodal Analytics for Real-world News using Measures 
            
23
of Cross-modal Entity Consistency\r\n\r\nThis repository contains the 
23
of Cross-modal Entity Consistency\r\n\r\nThis repository contains the 
            
24
*News400* dataset introduced in the paper:\r\n\r\n> Eric 
24
*News400* dataset introduced in the paper:\r\n\r\n> Eric 
            
25
M\u00fcller-Budack, Jonas Theiner, Sebastian Diering, Maximilian 
25
M\u00fcller-Budack, Jonas Theiner, Sebastian Diering, Maximilian 
            
26
Idahl, and Ralph Ewerth. 2020. \r\nMultimodal Analytics for Real-world 
26
Idahl, and Ralph Ewerth. 2020. \r\nMultimodal Analytics for Real-world 
            
27
News using Measures of Cross-modal Entity Consistency. \r\nIn 
27
News using Measures of Cross-modal Entity Consistency. \r\nIn 
            
28
Proceedings of the 2020 International Conference on Multimedia 
28
Proceedings of the 2020 International Conference on Multimedia 
            
29
Retrieval (ICMR '20). Association for Computing Machinery, New York, 
29
Retrieval (ICMR '20). Association for Computing Machinery, New York, 
            
30
NY, USA, 16\u201325. DOI: 
30
NY, USA, 16\u201325. DOI: 
            
31
https://doi.org/10.1145/3372278.3390670\r\n\r\n## Content\r\n\r\n- 
31
https://doi.org/10.1145/3372278.3390670\r\n\r\n## Content\r\n\r\n- 
            
32
**news400.tar.gz**:\r\n    - ```dataset.jsonl``` containing:\r\n        
32
**news400.tar.gz**:\r\n    - ```dataset.jsonl``` containing:\r\n        
            
33
- Web links to the news texts\r\n        - Web links to the news 
33
- Web links to the news texts\r\n        - Web links to the news 
            
34
image\r\n        - Outputs of the named entity recognition and 
34
image\r\n        - Outputs of the named entity recognition and 
            
35
disambiguation (NERD) approach\r\n        - Untampered and tampered 
35
disambiguation (NERD) approach\r\n        - Untampered and tampered 
            
36
entities\r\n    - ```<entity>.jsonl``` file for each entity type 
36
entities\r\n    - ```<entity>.jsonl``` file for each entity type 
            
37
containing the following information for each entity:\r\n        - 
37
containing the following information for each entity:\r\n        - 
            
38
Wikidata ID\r\n        - Wikidata label\r\n        - Meta information 
38
Wikidata ID\r\n        - Wikidata label\r\n        - Meta information 
            
39
used for tampering\r\n        - Web links to all reference images 
39
used for tampering\r\n        - Web links to all reference images 
            
40
crawled from Google, Bing, and Wikidata\r\n    - splits for testing 
40
crawled from Google, Bing, and Wikidata\r\n    - splits for testing 
            
41
and validation\r\n- **news400_features.tar.gz**:\r\n    - Visual 
41
and validation\r\n- **news400_features.tar.gz**:\r\n    - Visual 
            
42
features of the news images for persons, locations, and scenes\r\n    
42
features of the news images for persons, locations, and scenes\r\n    
            
43
- Visual features of the reference images for persons, locations, and 
43
- Visual features of the reference images for persons, locations, and 
            
44
scenes\r\n- **news400_wordembeddings.tar.gz**: Word embeddings of all 
44
scenes\r\n- **news400_wordembeddings.tar.gz**: Word embeddings of all 
            
45
nouns in the news texts\r\n\r\n## Source Code\r\n\r\nThe source code 
45
nouns in the news texts\r\n\r\n## Source Code\r\n\r\nThe source code 
            
46
to reproduce our results as well as download scripts to crawl news 
46
to reproduce our results as well as download scripts to crawl news 
            
47
texts and images can be found on our GitHub page: 
47
texts and images can be found on our GitHub page: 
            
48
https://github.com/TIBHannover/cross-modal_entity_consistency\r\n",
48
https://github.com/TIBHannover/cross-modal_entity_consistency\r\n",
            
n
49
  "num_resources": 4,
n
49
  "num_resources": 3,
            
50
  "num_tags": 5,
50
  "num_tags": 5,
            
51
  "organization": {
51
  "organization": {
            
52
    "approval_status": "approved",
52
    "approval_status": "approved",
            
53
    "created": "2017-11-23T17:30:37.757128",
53
    "created": "2017-11-23T17:30:37.757128",
            
54
    "description": "The German National Library of Science and 
54
    "description": "The German National Library of Science and 
            
55
Technology, abbreviated TIB, is the national library of the Federal 
55
Technology, abbreviated TIB, is the national library of the Federal 
            
56
Republic of Germany for all fields of engineering, technology, and the 
56
Republic of Germany for all fields of engineering, technology, and the 
            
57
natural sciences.",
57
natural sciences.",
            
58
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
58
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
59
    "image_url": 
59
    "image_url": 
            
60
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
60
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
61
    "is_organization": true,
61
    "is_organization": true,
            
62
    "name": "tib",
62
    "name": "tib",
            
63
    "state": "active",
63
    "state": "active",
            
64
    "title": "TIB",
64
    "title": "TIB",
            
65
    "type": "organization"
65
    "type": "organization"
            
66
  },
66
  },
            
67
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
67
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
68
  "private": false,
68
  "private": false,
            
69
  "relationships_as_object": [],
69
  "relationships_as_object": [],
            
70
  "relationships_as_subject": [],
70
  "relationships_as_subject": [],
            
71
  "repository_name": "Leibniz University Hannover",
71
  "repository_name": "Leibniz University Hannover",
            
72
  "resources": [
72
  "resources": [
            
73
    {
73
    {
            
74
      "cache_last_updated": null,
74
      "cache_last_updated": null,
            
75
      "cache_url": null,
75
      "cache_url": null,
            
76
      "created": "2020-06-04T13:54:05.550568",
76
      "created": "2020-06-04T13:54:05.550568",
            
n
77
      "datastore_active": false,
n

            
78
      "description": "",
77
      "description": "",
            
79
      "format": "TAR",
78
      "format": "TAR",
            
80
      "hash": "",
79
      "hash": "",
            
81
      "id": "af85e355-88e1-4d4d-91ec-785e1801dd47",
80
      "id": "af85e355-88e1-4d4d-91ec-785e1801dd47",
            
82
      "last_modified": "2020-06-04T13:54:05.503139",
81
      "last_modified": "2020-06-04T13:54:05.503139",
            
n
83
      "metadata_modified": "2021-10-14T10:16:03.085395",
n
82
      "metadata_modified": "2023-01-12T13:14:21.451741",
            
84
      "mimetype": "application/x-tar",
83
      "mimetype": "application/x-tar",
            
85
      "mimetype_inner": null,
84
      "mimetype_inner": null,
            
86
      "name": "news400.tar.gz",
85
      "name": "news400.tar.gz",
            
87
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
86
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
88
      "position": 0,
87
      "position": 0,
            
89
      "resource_type": null,
88
      "resource_type": null,
            
n
90
      "revision_id": "c67ae631-53d5-4c15-a24d-ee0d99e8c4bf",
n

            
91
      "size": 7478569,
89
      "size": 7478569,
            
92
      "state": "active",
90
      "state": "active",
            
93
      "url": 
91
      "url": 
            
94
esource/af85e355-88e1-4d4d-91ec-785e1801dd47/download/news400.tar.gz",
92
esource/af85e355-88e1-4d4d-91ec-785e1801dd47/download/news400.tar.gz",
            
95
      "url_type": ""
93
      "url_type": ""
            
96
    },
94
    },
            
97
    {
95
    {
            
98
      "cache_last_updated": null,
96
      "cache_last_updated": null,
            
99
      "cache_url": null,
97
      "cache_url": null,
            
100
      "created": "2020-06-04T14:00:14.775286",
98
      "created": "2020-06-04T14:00:14.775286",
            
n
101
      "datastore_active": false,
n

            
102
      "description": "",
99
      "description": "",
            
103
      "format": "TAR",
100
      "format": "TAR",
            
104
      "hash": "",
101
      "hash": "",
            
105
      "id": "23365241-435b-4dda-921c-09bd5f908010",
102
      "id": "23365241-435b-4dda-921c-09bd5f908010",
            
106
      "last_modified": "2020-06-04T14:00:14.728423",
103
      "last_modified": "2020-06-04T14:00:14.728423",
            
n
107
      "metadata_modified": "2021-10-14T10:16:03.086664",
n
104
      "metadata_modified": "2023-01-12T13:14:21.451934",
            
108
      "mimetype": "application/x-tar",
105
      "mimetype": "application/x-tar",
            
109
      "mimetype_inner": null,
106
      "mimetype_inner": null,
            
110
      "name": "news400_features.tar.gz",
107
      "name": "news400_features.tar.gz",
            
111
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
108
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
112
      "position": 1,
109
      "position": 1,
            
113
      "resource_type": null,
110
      "resource_type": null,
            
n
114
      "revision_id": "3df57a77-e3cf-43bd-9692-c36d6a06d547",
n

            
115
      "size": 471094303,
111
      "size": 471094303,
            
116
      "state": "active",
112
      "state": "active",
            
117
      "url": 
113
      "url": 
            
118
3365241-435b-4dda-921c-09bd5f908010/download/news400_features.tar.gz",
114
3365241-435b-4dda-921c-09bd5f908010/download/news400_features.tar.gz",
            
119
      "url_type": ""
115
      "url_type": ""
            
120
    },
116
    },
            
121
    {
117
    {
            
122
      "cache_last_updated": null,
118
      "cache_last_updated": null,
            
123
      "cache_url": null,
119
      "cache_url": null,
            
124
      "created": "2020-06-04T14:02:51.017611",
120
      "created": "2020-06-04T14:02:51.017611",
            
n
125
      "datastore_active": false,
n

            
126
      "description": "",
121
      "description": "",
            
127
      "format": "TAR",
122
      "format": "TAR",
            
128
      "hash": "",
123
      "hash": "",
            
129
      "id": "5500907c-2e5c-4967-a99d-4d64b6cde975",
124
      "id": "5500907c-2e5c-4967-a99d-4d64b6cde975",
            
130
      "last_modified": "2020-06-04T14:02:50.971063",
125
      "last_modified": "2020-06-04T14:02:50.971063",
            
n
131
      "metadata_modified": "2021-10-14T10:16:03.087921",
n
126
      "metadata_modified": "2023-01-12T13:14:21.452095",
            
132
      "mimetype": "application/x-tar",
127
      "mimetype": "application/x-tar",
            
133
      "mimetype_inner": null,
128
      "mimetype_inner": null,
            
134
      "name": "news400_wordembeddings.tar.gz",
129
      "name": "news400_wordembeddings.tar.gz",
            
135
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
130
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
136
      "position": 2,
131
      "position": 2,
            
137
      "resource_type": null,
132
      "resource_type": null,
            
n
138
      "revision_id": "e1347495-f742-4f60-863c-95d8d2e66d5f",
n

            
139
      "size": 43316706,
133
      "size": 43316706,
            
140
      "state": "active",
134
      "state": "active",
            
141
      "url": 
135
      "url": 
            
142
c-2e5c-4967-a99d-4d64b6cde975/download/news400_wordembeddings.tar.gz",
136
c-2e5c-4967-a99d-4d64b6cde975/download/news400_wordembeddings.tar.gz",
            
143
      "url_type": ""
137
      "url_type": ""
            
n
144
    },
n

            
145
    {

            
146
      "cache_last_updated": null,

            
147
      "cache_url": null,

            
148
      "created": "2020-06-08T13:11:48.406760",

            
149
      "datastore_active": false,

            
150
      "description": "",

            
151
      "downloadall_datapackage_hash": 

            
152
"87aa2e26bd640cbb4e7acb3177323ced",

            
153
      "downloadall_metadata_modified": "2020-06-04T14:04:33.377341",

            
154
      "format": "ZIP",

            
155
      "hash": "",

            
156
      "id": "d77bf15b-9cdd-473a-8110-9cd3132c3d8d",

            
157
      "last_modified": "2020-06-08T13:11:48.251282",

            
158
      "metadata_modified": "2021-10-14T10:16:03.089174",

            
159
      "mimetype": "application/zip",

            
160
      "mimetype_inner": null,

            
161
      "name": "All resource data",

            
162
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",

            
163
      "position": 3,

            
164
      "resource_type": null,

            
165
      "revision_id": "e1347495-f742-4f60-863c-95d8d2e66d5f",

            
166
      "size": 522044833,

            
167
      "state": "active",

            
168
      "url": 

            
169
rce/d77bf15b-9cdd-473a-8110-9cd3132c3d8d/download/news400-v4tceu.zip",

            
170
      "url_type": ""

            
171
    }
138
    }
            
172
  ],
139
  ],
            
173
  "source_metadata_created": "2020-06-04T13:53:33.217406",
140
  "source_metadata_created": "2020-06-04T13:53:33.217406",
            
t
174
  "source_metadata_modified": "2020-11-11T15:25:07.596446",
t
141
  "source_metadata_modified": "2022-01-20T10:59:42.198563",
            
175
  "state": "active",
142
  "state": "active",
            
176
  "tags": [
143
  "tags": [
            
177
    {
144
    {
            
178
      "display_name": "Cross-modal consistency",
145
      "display_name": "Cross-modal consistency",
            
179
      "id": "adf268b1-a8c7-4ced-9662-e5b4ef1db197",
146
      "id": "adf268b1-a8c7-4ced-9662-e5b4ef1db197",
            
180
      "name": "Cross-modal consistency",
147
      "name": "Cross-modal consistency",
            
181
      "state": "active",
148
      "state": "active",
            
182
      "vocabulary_id": null
149
      "vocabulary_id": null
            
183
    },
150
    },
            
184
    {
151
    {
            
185
      "display_name": "cross-modal entity verification",
152
      "display_name": "cross-modal entity verification",
            
186
      "id": "12a9c183-d4e8-4aef-9099-8b29d390f861",
153
      "id": "12a9c183-d4e8-4aef-9099-8b29d390f861",
            
187
      "name": "cross-modal entity verification",
154
      "name": "cross-modal entity verification",
            
188
      "state": "active",
155
      "state": "active",
            
189
      "vocabulary_id": null
156
      "vocabulary_id": null
            
190
    },
157
    },
            
191
    {
158
    {
            
192
      "display_name": "deep learning",
159
      "display_name": "deep learning",
            
193
      "id": "19e41883-3799-4184-9e0e-26c95795b119",
160
      "id": "19e41883-3799-4184-9e0e-26c95795b119",
            
194
      "name": "deep learning",
161
      "name": "deep learning",
            
195
      "state": "active",
162
      "state": "active",
            
196
      "vocabulary_id": null
163
      "vocabulary_id": null
            
197
    },
164
    },
            
198
    {
165
    {
            
199
      "display_name": "image repurposing detection",
166
      "display_name": "image repurposing detection",
            
200
      "id": "04bdab29-34f3-4093-bf54-1129fed5f7da",
167
      "id": "04bdab29-34f3-4093-bf54-1129fed5f7da",
            
201
      "name": "image repurposing detection",
168
      "name": "image repurposing detection",
            
202
      "state": "active",
169
      "state": "active",
            
203
      "vocabulary_id": null
170
      "vocabulary_id": null
            
204
    },
171
    },
            
205
    {
172
    {
            
206
      "display_name": "multimodal retrieval",
173
      "display_name": "multimodal retrieval",
            
207
      "id": "9a52a3c5-10e4-4056-8a1b-98a19044c62f",
174
      "id": "9a52a3c5-10e4-4056-8a1b-98a19044c62f",
            
208
      "name": "multimodal retrieval",
175
      "name": "multimodal retrieval",
            
209
      "state": "active",
176
      "state": "active",
            
210
      "vocabulary_id": null
177
      "vocabulary_id": null
            
211
    }
178
    }
            
212
  ],
179
  ],
            
213
  "terms_of_usage": "Yes",
180
  "terms_of_usage": "Yes",
            
214
  "title": "News400 Dataset",
181
  "title": "News400 Dataset",
            
215
  "type": "vdataset",
182
  "type": "vdataset",
            
216
  "url": "https://data.uni-hannover.de/dataset/news400",
183
  "url": "https://data.uni-hannover.de/dataset/news400",
            
217
  "version": ""
184
  "version": ""
            
218
}
185
}