Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
n
2
  "author": "Eric M\u00fcller-Budack, Jonas Theiner, Sebastian 
n
2
  "author": "Eric M\u00fcller-Budack",
            
3
Diering, Maximilian Idahl, Ralph Ewerth",

            
4
  "author_email": "eric.mueller@tib.eu",
3
  "author_email": "eric.mueller@tib.eu",
            
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
6
  "doi": "10.25835/0084897",
5
  "doi": "10.25835/0084897",
            
7
  "doi_date_published": "2020-06-04",
6
  "doi_date_published": "2020-06-04",
            
8
  "doi_publisher": "LUIS",
7
  "doi_publisher": "LUIS",
            
9
  "doi_status": "true",
8
  "doi_status": "true",
            
10
  "domain": "https://data.uni-hannover.de",
9
  "domain": "https://data.uni-hannover.de",
            
n
n
10
  "extra_authors": [
            
11
    {
            
12
      "extra_author": " Jonas Theiner"
            
13
    },
            
14
    {
            
15
      "extra_author": " Sebastian Diering"
            
16
    },
            
17
    {
            
18
      "extra_author": " Maximilian Idahl"
            
19
    },
            
20
    {
            
21
      "extra_author": " Ralph Ewerth"
            
22
    }
            
23
  ],
            
11
  "groups": [],
24
  "groups": [],
            
12
  "have_copyright": "Yes",
25
  "have_copyright": "Yes",
            
13
  "id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
26
  "id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
14
  "isopen": false,
27
  "isopen": false,
            
15
  "license_id": "CC-BY-NC-3.0",
28
  "license_id": "CC-BY-NC-3.0",
            
16
  "license_title": "CC-BY-NC-3.0",
29
  "license_title": "CC-BY-NC-3.0",
            
17
  "maintainer": "Eric M\u00fcller-Budack",
30
  "maintainer": "Eric M\u00fcller-Budack",
            
18
  "maintainer_email": "eric.mueller@tib.eu",
31
  "maintainer_email": "eric.mueller@tib.eu",
            
19
  "metadata_created": "2021-10-14T10:16:03.098485",
32
  "metadata_created": "2021-10-14T10:16:03.098485",
            
n
20
  "metadata_modified": "2023-01-12T13:14:21.448200",
n
33
  "metadata_modified": "2023-08-04T08:46:40.898926",
            
21
  "name": "luh-news400",
34
  "name": "luh-news400",
            
22
  "notes": "# Multimodal Analytics for Real-world News using Measures 
35
  "notes": "# Multimodal Analytics for Real-world News using Measures 
            
23
of Cross-modal Entity Consistency\r\n\r\nThis repository contains the 
36
of Cross-modal Entity Consistency\r\n\r\nThis repository contains the 
            
24
*News400* dataset introduced in the paper:\r\n\r\n> Eric 
37
*News400* dataset introduced in the paper:\r\n\r\n> Eric 
            
25
M\u00fcller-Budack, Jonas Theiner, Sebastian Diering, Maximilian 
38
M\u00fcller-Budack, Jonas Theiner, Sebastian Diering, Maximilian 
            
26
Idahl, and Ralph Ewerth. 2020. \r\nMultimodal Analytics for Real-world 
39
Idahl, and Ralph Ewerth. 2020. \r\nMultimodal Analytics for Real-world 
            
27
News using Measures of Cross-modal Entity Consistency. \r\nIn 
40
News using Measures of Cross-modal Entity Consistency. \r\nIn 
            
28
Proceedings of the 2020 International Conference on Multimedia 
41
Proceedings of the 2020 International Conference on Multimedia 
            
29
Retrieval (ICMR '20). Association for Computing Machinery, New York, 
42
Retrieval (ICMR '20). Association for Computing Machinery, New York, 
            
30
NY, USA, 16\u201325. DOI: 
43
NY, USA, 16\u201325. DOI: 
            
31
https://doi.org/10.1145/3372278.3390670\r\n\r\n## Content\r\n\r\n- 
44
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        
45
**news400.tar.gz**:\r\n    - ```dataset.jsonl``` containing:\r\n        
            
33
- Web links to the news texts\r\n        - Web links to the news 
46
- Web links to the news texts\r\n        - Web links to the news 
            
34
image\r\n        - Outputs of the named entity recognition and 
47
image\r\n        - Outputs of the named entity recognition and 
            
35
disambiguation (NERD) approach\r\n        - Untampered and tampered 
48
disambiguation (NERD) approach\r\n        - Untampered and tampered 
            
36
entities\r\n    - ```<entity>.jsonl``` file for each entity type 
49
entities\r\n    - ```<entity>.jsonl``` file for each entity type 
            
37
containing the following information for each entity:\r\n        - 
50
containing the following information for each entity:\r\n        - 
            
38
Wikidata ID\r\n        - Wikidata label\r\n        - Meta information 
51
Wikidata ID\r\n        - Wikidata label\r\n        - Meta information 
            
39
used for tampering\r\n        - Web links to all reference images 
52
used for tampering\r\n        - Web links to all reference images 
            
40
crawled from Google, Bing, and Wikidata\r\n    - splits for testing 
53
crawled from Google, Bing, and Wikidata\r\n    - splits for testing 
            
41
and validation\r\n- **news400_features.tar.gz**:\r\n    - Visual 
54
and validation\r\n- **news400_features.tar.gz**:\r\n    - Visual 
            
42
features of the news images for persons, locations, and scenes\r\n    
55
features of the news images for persons, locations, and scenes\r\n    
            
43
- Visual features of the reference images for persons, locations, and 
56
- Visual features of the reference images for persons, locations, and 
            
44
scenes\r\n- **news400_wordembeddings.tar.gz**: Word embeddings of all 
57
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 
58
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 
59
to reproduce our results as well as download scripts to crawl news 
            
47
texts and images can be found on our GitHub page: 
60
texts and images can be found on our GitHub page: 
            
48
https://github.com/TIBHannover/cross-modal_entity_consistency\r\n",
61
https://github.com/TIBHannover/cross-modal_entity_consistency\r\n",
            
49
  "num_resources": 3,
62
  "num_resources": 3,
            
50
  "num_tags": 5,
63
  "num_tags": 5,
            
51
  "organization": {
64
  "organization": {
            
52
    "approval_status": "approved",
65
    "approval_status": "approved",
            
53
    "created": "2017-11-23T17:30:37.757128",
66
    "created": "2017-11-23T17:30:37.757128",
            
54
    "description": "The German National Library of Science and 
67
    "description": "The German National Library of Science and 
            
55
Technology, abbreviated TIB, is the national library of the Federal 
68
Technology, abbreviated TIB, is the national library of the Federal 
            
56
Republic of Germany for all fields of engineering, technology, and the 
69
Republic of Germany for all fields of engineering, technology, and the 
            
57
natural sciences.",
70
natural sciences.",
            
58
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
71
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
59
    "image_url": 
72
    "image_url": 
            
60
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
73
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
61
    "is_organization": true,
74
    "is_organization": true,
            
62
    "name": "tib",
75
    "name": "tib",
            
63
    "state": "active",
76
    "state": "active",
            
64
    "title": "TIB",
77
    "title": "TIB",
            
65
    "type": "organization"
78
    "type": "organization"
            
66
  },
79
  },
            
67
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
80
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
68
  "private": false,
81
  "private": false,
            
69
  "relationships_as_object": [],
82
  "relationships_as_object": [],
            
70
  "relationships_as_subject": [],
83
  "relationships_as_subject": [],
            
71
  "repository_name": "Leibniz University Hannover",
84
  "repository_name": "Leibniz University Hannover",
            
72
  "resources": [
85
  "resources": [
            
73
    {
86
    {
            
74
      "cache_last_updated": null,
87
      "cache_last_updated": null,
            
75
      "cache_url": null,
88
      "cache_url": null,
            
76
      "created": "2020-06-04T13:54:05.550568",
89
      "created": "2020-06-04T13:54:05.550568",
            
77
      "description": "",
90
      "description": "",
            
78
      "format": "TAR",
91
      "format": "TAR",
            
79
      "hash": "",
92
      "hash": "",
            
80
      "id": "af85e355-88e1-4d4d-91ec-785e1801dd47",
93
      "id": "af85e355-88e1-4d4d-91ec-785e1801dd47",
            
81
      "last_modified": "2020-06-04T13:54:05.503139",
94
      "last_modified": "2020-06-04T13:54:05.503139",
            
n
82
      "metadata_modified": "2023-01-12T13:14:21.451741",
n
95
      "metadata_modified": "2023-08-04T08:46:40.902402",
            
83
      "mimetype": "application/x-tar",
96
      "mimetype": "application/x-tar",
            
84
      "mimetype_inner": null,
97
      "mimetype_inner": null,
            
85
      "name": "news400.tar.gz",
98
      "name": "news400.tar.gz",
            
86
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
99
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
87
      "position": 0,
100
      "position": 0,
            
88
      "resource_type": null,
101
      "resource_type": null,
            
89
      "size": 7478569,
102
      "size": 7478569,
            
90
      "state": "active",
103
      "state": "active",
            
91
      "url": 
104
      "url": 
            
92
esource/af85e355-88e1-4d4d-91ec-785e1801dd47/download/news400.tar.gz",
105
esource/af85e355-88e1-4d4d-91ec-785e1801dd47/download/news400.tar.gz",
            
93
      "url_type": ""
106
      "url_type": ""
            
94
    },
107
    },
            
95
    {
108
    {
            
96
      "cache_last_updated": null,
109
      "cache_last_updated": null,
            
97
      "cache_url": null,
110
      "cache_url": null,
            
98
      "created": "2020-06-04T14:00:14.775286",
111
      "created": "2020-06-04T14:00:14.775286",
            
99
      "description": "",
112
      "description": "",
            
100
      "format": "TAR",
113
      "format": "TAR",
            
101
      "hash": "",
114
      "hash": "",
            
102
      "id": "23365241-435b-4dda-921c-09bd5f908010",
115
      "id": "23365241-435b-4dda-921c-09bd5f908010",
            
103
      "last_modified": "2020-06-04T14:00:14.728423",
116
      "last_modified": "2020-06-04T14:00:14.728423",
            
n
104
      "metadata_modified": "2023-01-12T13:14:21.451934",
n
117
      "metadata_modified": "2023-08-04T08:46:40.902535",
            
105
      "mimetype": "application/x-tar",
118
      "mimetype": "application/x-tar",
            
106
      "mimetype_inner": null,
119
      "mimetype_inner": null,
            
107
      "name": "news400_features.tar.gz",
120
      "name": "news400_features.tar.gz",
            
108
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
121
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
109
      "position": 1,
122
      "position": 1,
            
110
      "resource_type": null,
123
      "resource_type": null,
            
111
      "size": 471094303,
124
      "size": 471094303,
            
112
      "state": "active",
125
      "state": "active",
            
113
      "url": 
126
      "url": 
            
114
3365241-435b-4dda-921c-09bd5f908010/download/news400_features.tar.gz",
127
3365241-435b-4dda-921c-09bd5f908010/download/news400_features.tar.gz",
            
115
      "url_type": ""
128
      "url_type": ""
            
116
    },
129
    },
            
117
    {
130
    {
            
118
      "cache_last_updated": null,
131
      "cache_last_updated": null,
            
119
      "cache_url": null,
132
      "cache_url": null,
            
120
      "created": "2020-06-04T14:02:51.017611",
133
      "created": "2020-06-04T14:02:51.017611",
            
121
      "description": "",
134
      "description": "",
            
122
      "format": "TAR",
135
      "format": "TAR",
            
123
      "hash": "",
136
      "hash": "",
            
124
      "id": "5500907c-2e5c-4967-a99d-4d64b6cde975",
137
      "id": "5500907c-2e5c-4967-a99d-4d64b6cde975",
            
125
      "last_modified": "2020-06-04T14:02:50.971063",
138
      "last_modified": "2020-06-04T14:02:50.971063",
            
n
126
      "metadata_modified": "2023-01-12T13:14:21.452095",
n
139
      "metadata_modified": "2023-08-04T08:46:40.902643",
            
127
      "mimetype": "application/x-tar",
140
      "mimetype": "application/x-tar",
            
128
      "mimetype_inner": null,
141
      "mimetype_inner": null,
            
129
      "name": "news400_wordembeddings.tar.gz",
142
      "name": "news400_wordembeddings.tar.gz",
            
130
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
143
      "package_id": "c729ffd9-8be1-49a9-8c43-dab2f8a87753",
            
131
      "position": 2,
144
      "position": 2,
            
132
      "resource_type": null,
145
      "resource_type": null,
            
133
      "size": 43316706,
146
      "size": 43316706,
            
134
      "state": "active",
147
      "state": "active",
            
135
      "url": 
148
      "url": 
            
136
c-2e5c-4967-a99d-4d64b6cde975/download/news400_wordembeddings.tar.gz",
149
c-2e5c-4967-a99d-4d64b6cde975/download/news400_wordembeddings.tar.gz",
            
137
      "url_type": ""
150
      "url_type": ""
            
138
    }
151
    }
            
139
  ],
152
  ],
            
t
t
153
  "services_used_list": "",
            
140
  "source_metadata_created": "2020-06-04T13:53:33.217406",
154
  "source_metadata_created": "2020-06-04T13:53:33.217406",
            
141
  "source_metadata_modified": "2022-01-20T10:59:42.198563",
155
  "source_metadata_modified": "2022-01-20T10:59:42.198563",
            
142
  "state": "active",
156
  "state": "active",
            
143
  "tags": [
157
  "tags": [
            
144
    {
158
    {
            
145
      "display_name": "Cross-modal consistency",
159
      "display_name": "Cross-modal consistency",
            
146
      "id": "adf268b1-a8c7-4ced-9662-e5b4ef1db197",
160
      "id": "adf268b1-a8c7-4ced-9662-e5b4ef1db197",
            
147
      "name": "Cross-modal consistency",
161
      "name": "Cross-modal consistency",
            
148
      "state": "active",
162
      "state": "active",
            
149
      "vocabulary_id": null
163
      "vocabulary_id": null
            
150
    },
164
    },
            
151
    {
165
    {
            
152
      "display_name": "cross-modal entity verification",
166
      "display_name": "cross-modal entity verification",
            
153
      "id": "12a9c183-d4e8-4aef-9099-8b29d390f861",
167
      "id": "12a9c183-d4e8-4aef-9099-8b29d390f861",
            
154
      "name": "cross-modal entity verification",
168
      "name": "cross-modal entity verification",
            
155
      "state": "active",
169
      "state": "active",
            
156
      "vocabulary_id": null
170
      "vocabulary_id": null
            
157
    },
171
    },
            
158
    {
172
    {
            
159
      "display_name": "deep learning",
173
      "display_name": "deep learning",
            
160
      "id": "19e41883-3799-4184-9e0e-26c95795b119",
174
      "id": "19e41883-3799-4184-9e0e-26c95795b119",
            
161
      "name": "deep learning",
175
      "name": "deep learning",
            
162
      "state": "active",
176
      "state": "active",
            
163
      "vocabulary_id": null
177
      "vocabulary_id": null
            
164
    },
178
    },
            
165
    {
179
    {
            
166
      "display_name": "image repurposing detection",
180
      "display_name": "image repurposing detection",
            
167
      "id": "04bdab29-34f3-4093-bf54-1129fed5f7da",
181
      "id": "04bdab29-34f3-4093-bf54-1129fed5f7da",
            
168
      "name": "image repurposing detection",
182
      "name": "image repurposing detection",
            
169
      "state": "active",
183
      "state": "active",
            
170
      "vocabulary_id": null
184
      "vocabulary_id": null
            
171
    },
185
    },
            
172
    {
186
    {
            
173
      "display_name": "multimodal retrieval",
187
      "display_name": "multimodal retrieval",
            
174
      "id": "9a52a3c5-10e4-4056-8a1b-98a19044c62f",
188
      "id": "9a52a3c5-10e4-4056-8a1b-98a19044c62f",
            
175
      "name": "multimodal retrieval",
189
      "name": "multimodal retrieval",
            
176
      "state": "active",
190
      "state": "active",
            
177
      "vocabulary_id": null
191
      "vocabulary_id": null
            
178
    }
192
    }
            
179
  ],
193
  ],
            
180
  "terms_of_usage": "Yes",
194
  "terms_of_usage": "Yes",
            
181
  "title": "News400 Dataset",
195
  "title": "News400 Dataset",
            
182
  "type": "vdataset",
196
  "type": "vdataset",
            
183
  "url": "https://data.uni-hannover.de/dataset/news400",
197
  "url": "https://data.uni-hannover.de/dataset/news400",
            
184
  "version": ""
198
  "version": ""
            
185
}
199
}