Changes

On December 3, 2024 at 9:26:52 AM UTC, admin:
Changed title to LAION 400M (previously LaION-400M)
Set author of LAION 400M to Roy Ganz (previously Omri Avrahami)
Updated description of LAION 400M from
The LaION-400M dataset contains 400 million image-text pairs, with a focus on diverse and high-quality images.
to
The dataset used in the paper is a large-scale image-text dataset, which is a concatenation of SBU, CC-3M, and CC-12M datasets, and a downsampled version of LAION 400M.
Removed the following tags from LAION 400M
Added the following tags to LAION 400M
Changed value of field defined_in to https://doi.org/10.48550/arXiv.2306.16805 in LAION 400M
Changed value of field extra_authors to [{'extra_author': 'Michael Elad', 'orcid': ''}] in LAION 400M
Changed value of field citation to [] in LAION 400M
Changed value of field landing_page to https://arxiv.org/abs/2110.04627 in LAION 400M
Deleted resource Original Metadata from LAION 400M
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Omri Avrahami", n 3   "author": "Roy Ganz",
            4   "author_email": "", 4   "author_email": "",
            n 5   "citation": [ n 5   "citation": [],
            6     "https://doi.org/10.48550/arXiv.2309.16671", 
            7     "https://doi.org/10.48550/arXiv.2403.20312" 
            8   ], 
            9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 10   "defined_in": "https://doi.org/10.48550/arXiv.2403.04279", n 7   "defined_in": "https://doi.org/10.48550/arXiv.2306.16805",
            11   "doi": "10.57702/2w4mj8iq", 8   "doi": "10.57702/2w4mj8iq",
            12   "doi_date_published": "2024-12-02", 9   "doi_date_published": "2024-12-02",
            13   "doi_publisher": "TIB", 10   "doi_publisher": "TIB",
            14   "doi_status": true, 11   "doi_status": true,
            15   "domain": "https://service.tib.eu/ldmservice", 12   "domain": "https://service.tib.eu/ldmservice",
            16   "extra_authors": [ 13   "extra_authors": [
            17     { 14     {
            n 18       "extra_author": "Ohad Fried", n 15       "extra_author": "Michael Elad",
            19       "orcid": "" 
            20     }, 
            21     { 
            22       "extra_author": "Dani Lischinski", 
            23       "orcid": "" 16       "orcid": ""
            24     } 17     }
            25   ], 18   ],
            26   "groups": [ 19   "groups": [
            n 27     { n 
            28       "description": "", 
            29       "display_name": "Data Collection", 
            30       "id": "e5407d18-d3c2-4737-9f55-070f579cca99", 
            31       "image_display_url": "", 
            32       "name": "data-collection", 
            33       "title": "Data Collection" 
            34     }, 
            35     { 
            36       "description": "", 
            37       "display_name": "Image Generation", 
            38       "id": "be25a76c-def1-4e73-8b1c-b81222d63867", 
            39       "image_display_url": "", 
            40       "name": "image-generation", 
            41       "title": "Image Generation" 
            42     }, 
            43     { 
            44       "description": "", 
            45       "display_name": "Image-Text Data", 
            46       "id": "56fc5067-0287-4290-87df-53fe63e00adc", 
            47       "image_display_url": "", 
            48       "name": "image-text-data", 
            49       "title": "Image-Text Data" 
            50     }, 
            51     { 20     {
            52       "description": "", 21       "description": "",
            53       "display_name": "Image-Text Dataset", 22       "display_name": "Image-Text Dataset",
            54       "id": "2f287fa5-3ac1-43a4-a75c-5c8776dce8e8", 23       "id": "2f287fa5-3ac1-43a4-a75c-5c8776dce8e8",
            55       "image_display_url": "", 24       "image_display_url": "",
            56       "name": "image-text-dataset", 25       "name": "image-text-dataset",
            57       "title": "Image-Text Dataset" 26       "title": "Image-Text Dataset"
            n 58     }, n 
            59     { 
            60       "description": "", 
            61       "display_name": "Image-Text Matching", 
            62       "id": "0635db3c-45c8-49b1-b083-80ec6966b144", 
            63       "image_display_url": "", 
            64       "name": "image-text-matching", 
            65       "title": "Image-Text Matching" 
            66     }, 
            67     { 
            68       "description": "", 
            69       "display_name": "Text-to-Image Synthesis", 
            70       "id": "731bfb4e-0ea0-48f6-a46f-03bc7eb9e4fe", 
            71       "image_display_url": "", 
            72       "name": "text-to-image-synthesis", 
            73       "title": "Text-to-Image Synthesis" 
            74     }, 
            75     { 
            76       "description": "", 
            77       "display_name": "Vision-Language Models", 
            78       "id": "71ce768c-2180-446e-b8bd-7d0d2e73a077", 
            79       "image_display_url": "", 
            80       "name": "vision-language-models", 
            81       "title": "Vision-Language Models" 
            82     } 27     }
            83   ], 28   ],
            84   "id": "a08d7e35-d4e6-4456-9a4e-711422f5175d", 29   "id": "a08d7e35-d4e6-4456-9a4e-711422f5175d",
            85   "isopen": false, 30   "isopen": false,
            n 86   "landing_page": "https://arxiv.org/abs/2111.02114", n 31   "landing_page": "https://arxiv.org/abs/2110.04627",
            87   "license_title": null, 32   "license_title": null,
            88   "link_orkg": "", 33   "link_orkg": "",
            89   "metadata_created": "2024-12-02T17:55:36.175986", 34   "metadata_created": "2024-12-02T17:55:36.175986",
            n 90   "metadata_modified": "2024-12-02T18:20:40.111972", n 35   "metadata_modified": "2024-12-03T09:26:51.238270",
            91   "name": "laion-400m", 36   "name": "laion-400m",
            n 92   "notes": "The LaION-400M dataset contains 400 million image-text  n 37   "notes": "The dataset used in the paper is a large-scale image-text 
            93 pairs, with a focus on diverse and high-quality images.", 38 dataset, which is a concatenation of SBU, CC-3M, and CC-12M datasets, 
            39 and a downsampled version of LAION 400M.",
            94   "num_resources": 1, 40   "num_resources": 0,
            95   "num_tags": 10, 41   "num_tags": 3,
            96   "organization": { 42   "organization": {
            97     "approval_status": "approved", 43     "approval_status": "approved",
            98     "created": "2024-11-25T12:11:38.292601", 44     "created": "2024-11-25T12:11:38.292601",
            99     "description": "", 45     "description": "",
            100     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 46     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            101     "image_url": "", 47     "image_url": "",
            102     "is_organization": true, 48     "is_organization": true,
            103     "name": "no-organization", 49     "name": "no-organization",
            104     "state": "active", 50     "state": "active",
            105     "title": "No Organization", 51     "title": "No Organization",
            106     "type": "organization" 52     "type": "organization"
            107   }, 53   },
            108   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 54   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            109   "private": false, 55   "private": false,
            110   "relationships_as_object": [], 56   "relationships_as_object": [],
            111   "relationships_as_subject": [], 57   "relationships_as_subject": [],
            n 112   "resources": [ n 58   "resources": [],
            113     { 
            114       "cache_last_updated": null, 
            115       "cache_url": null, 
            116       "created": "2024-12-02T18:38:42", 
            117       "data": [ 
            118         "dcterms:title", 
            119         "dcterms:accessRights", 
            120         "dcterms:creator", 
            121         "dcterms:description", 
            122         "dcterms:issued", 
            123         "dcterms:language", 
            124         "dcterms:identifier", 
            125         "dcat:theme", 
            126         "dcterms:type", 
            127         "dcat:keyword", 
            128         "dcat:landingPage", 
            129         "dcterms:hasVersion", 
            130         "dcterms:format", 
            131         "mls:task", 
            132         "datacite:isDescribedBy" 
            133       ], 
            134       "description": "The json representation of the dataset with its  
            135 distributions based on DCAT.", 
            136       "format": "JSON", 
            137       "hash": "", 
            138       "id": "b622a55b-a404-4d0b-b902-3919d99aa99b", 
            139       "last_modified": "2024-12-02T18:20:40.103161", 
            140       "metadata_modified": "2024-12-02T18:20:40.114864", 
            141       "mimetype": "application/json", 
            142       "mimetype_inner": null, 
            143       "name": "Original Metadata", 
            144       "package_id": "a08d7e35-d4e6-4456-9a4e-711422f5175d", 
            145       "position": 0, 
            146       "resource_type": null, 
            147       "size": 1201, 
            148       "state": "active", 
            149       "url":  
            150 resource/b622a55b-a404-4d0b-b902-3919d99aa99b/download/metadata.json", 
            151       "url_type": "upload" 
            152     } 
            153   ], 
            154   "services_used_list": "", 59   "services_used_list": "",
            155   "state": "active", 60   "state": "active",
            156   "tags": [ 61   "tags": [
            157     { 62     {
            n 158       "display_name": "Data Collection", n 63       "display_name": "LAION 400M",
            159       "id": "7cec52fd-2eb1-4c11-9c4c-400d3278cc29", 64       "id": "80112b4e-f973-402c-a9d4-40ed22175f5b",
            160       "name": "Data Collection", 65       "name": "LAION 400M",
            161       "state": "active", 66       "state": "active",
            162       "vocabulary_id": null 67       "vocabulary_id": null
            163     }, 68     },
            164     { 69     {
            n 165       "display_name": "Image-Text Data", n 70       "display_name": "image-text dataset",
            166       "id": "b35ee7e4-b3d8-4ea4-af9c-e36b24a33e7f", 71       "id": "c336f98a-4e26-4b43-aea0-8fb569af8588",
            167       "name": "Image-Text Data", 72       "name": "image-text dataset",
            168       "state": "active", 73       "state": "active",
            169       "vocabulary_id": null 74       "vocabulary_id": null
            170     }, 75     },
            171     { 76     {
            n 172       "display_name": "LaION-400M", n 
            173       "id": "a19e7a5e-5c43-4d68-ba3b-83dd05ddbb2b", 
            174       "name": "LaION-400M", 
            175       "state": "active", 
            176       "vocabulary_id": null 
            177     }, 
            178     { 
            179       "display_name": "dataset", 77       "display_name": "large-scale dataset",
            180       "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b", 78       "id": "a9c694bf-f591-4625-a20e-d53d3f90d489",
            181       "name": "dataset", 79       "name": "large-scale dataset",
            182       "state": "active", 
            183       "vocabulary_id": null 
            184     }, 
            185     { 
            186       "display_name": "diverse images", 
            187       "id": "19140078-9432-4e2c-b156-d45da38604f3", 
            188       "name": "diverse images", 
            189       "state": "active", 
            190       "vocabulary_id": null 
            191     }, 
            192     { 
            193       "display_name": "high-quality images", 
            194       "id": "3761d4b0-93f6-4548-bdb6-0e0881fc5a20", 
            195       "name": "high-quality images", 
            196       "state": "active", 
            197       "vocabulary_id": null 
            198     }, 
            199     { 
            200       "display_name": "image generation", 
            201       "id": "96df81b4-32fd-4826-a903-affb005a0a60", 
            202       "name": "image generation", 
            203       "state": "active", 
            204       "vocabulary_id": null 
            205     }, 
            206     { 
            207       "display_name": "image-text pairs", 
            208       "id": "07cb3691-65c6-4b58-b3bf-5290980a86e3", 
            209       "name": "image-text pairs", 
            210       "state": "active", 
            211       "vocabulary_id": null 
            212     }, 
            213     { 
            214       "display_name": "text-to-image synthesis", 
            215       "id": "c37dcb7d-7577-4b8f-95ae-252797eb5cce", 
            216       "name": "text-to-image synthesis", 
            217       "state": "active", 
            218       "vocabulary_id": null 
            219     }, 
            220     { 
            221       "display_name": "vision-language models", 
            222       "id": "f02eea8d-0e99-468f-884c-6fcdf16465ce", 
            223       "name": "vision-language models", 
            224       "state": "active", 80       "state": "active",
            225       "vocabulary_id": null 81       "vocabulary_id": null
            226     } 82     }
            227   ], 83   ],
            t 228   "title": "LaION-400M", t 84   "title": "LAION 400M",
            229   "type": "dataset", 85   "type": "dataset",
            230   "version": "" 86   "version": ""
            231 } 87 }