Changes

On December 3, 2024 at 10:35:47 AM UTC, admin:

Changed title to LAION-400M: Open dataset of clip-filtered 400 million image-text pairs (previously Laion-400M: Open dataset of CLIP-filtered 400 million image-text pairs)

Set author of LAION-400M: Open dataset of clip-filtered 400 million image-text pairs to C. Schuhmann (previously Christoph Schuhmann)

Updated description of LAION-400M: Open dataset of clip-filtered 400 million image-text pairs from
This dataset contains 400 million image-text pairs, which are used to train the CLIP model.
to
LAION-Aesthetic is a large-scale dataset for training next generation image-text models.

Removed the following tags from LAION-400M: Open dataset of clip-filtered 400 million image-text pairs

Added the following tags to LAION-400M: Open dataset of clip-filtered 400 million image-text pairs
- Image-Text Dataset
- LAION-Aesthetic

Changed value of field defined_in to https://doi.org/10.48550/arXiv.2310.13828 in LAION-400M: Open dataset of clip-filtered 400 million image-text pairs

Changed value of field landing_page to https://arxiv.org/abs/2111.02114 in LAION-400M: Open dataset of clip-filtered 400 million image-text pairs

Deleted resource Original Metadata from LAION-400M: Open dataset of clip-filtered 400 million image-text pairs

              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Christoph Schuhmann", n 3   "author": "C. Schuhmann",
            4   "author_email": "", 4   "author_email": "",
            5   "citation": [], 5   "citation": [],
            6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 7   "defined_in": "https://doi.org/10.48550/arXiv.2404.12908", n 7   "defined_in": "https://doi.org/10.48550/arXiv.2310.13828",
            8   "doi": "10.57702/r9lzeyzy", 8   "doi": "10.57702/r9lzeyzy",
            9   "doi_date_published": "2024-12-02", 9   "doi_date_published": "2024-12-02",
            10   "doi_publisher": "TIB", 10   "doi_publisher": "TIB",
            11   "doi_status": true, 11   "doi_status": true,
            12   "domain": "https://service.tib.eu/ldmservice", 12   "domain": "https://service.tib.eu/ldmservice",
            n 13   "extra_authors": [ n 
            14     { 
            15       "extra_author": "et al.", 
            16       "orcid": "" 
            17     } 
            18   ], 
            19   "groups": [ 13   "groups": [
            20     { 14     {
            21       "description": "", 15       "description": "",
            n 22       "display_name": "Image Generation", n 16       "display_name": "Image-Text Dataset",
            23       "id": "be25a76c-def1-4e73-8b1c-b81222d63867", 17       "id": "2f287fa5-3ac1-43a4-a75c-5c8776dce8e8",
            24       "image_display_url": "", 18       "image_display_url": "",
            n 25       "name": "image-generation", n 19       "name": "image-text-dataset",
            26       "title": "Image Generation" 20       "title": "Image-Text Dataset"
            27     }, 
            28     { 
            29       "description": "", 
            30       "display_name": "Text Generation", 
            31       "id": "e9d4b27d-4658-4981-ac71-43ba61d3f4fb", 
            32       "image_display_url": "", 
            33       "name": "text-generation", 
            34       "title": "Text Generation" 
            35     } 21     }
            36   ], 22   ],
            37   "id": "e1a34273-2816-4b72-9371-2a89ec826409", 23   "id": "e1a34273-2816-4b72-9371-2a89ec826409",
            38   "isopen": false, 24   "isopen": false,
            n 39   "landing_page": "https://arxiv.org/abs/2106.11196", n 25   "landing_page": "https://arxiv.org/abs/2111.02114",
            40   "license_title": null, 26   "license_title": null,
            41   "link_orkg": "", 27   "link_orkg": "",
            42   "metadata_created": "2024-12-02T21:41:06.597085", 28   "metadata_created": "2024-12-02T21:41:06.597085",
            n 43   "metadata_modified": "2024-12-02T21:41:07.201502", n 29   "metadata_modified": "2024-12-03T10:35:46.371228",
            44   "name":  30   "name": 
            45 ion-400m--open-dataset-of-clip-filtered-400-million-image-text-pairs", 31 ion-400m--open-dataset-of-clip-filtered-400-million-image-text-pairs",
            n 46   "notes": "This dataset contains 400 million image-text pairs, which  n 32   "notes": "LAION-Aesthetic is a large-scale dataset for training next 
            47 are used to train the CLIP model.", 33 generation image-text models.",
            48   "num_resources": 1, 34   "num_resources": 0,
            49   "num_tags": 3, 35   "num_tags": 2,
            50   "organization": { 36   "organization": {
            51     "approval_status": "approved", 37     "approval_status": "approved",
            52     "created": "2024-11-25T12:11:38.292601", 38     "created": "2024-11-25T12:11:38.292601",
            53     "description": "", 39     "description": "",
            54     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 40     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            55     "image_url": "", 41     "image_url": "",
            56     "is_organization": true, 42     "is_organization": true,
            57     "name": "no-organization", 43     "name": "no-organization",
            58     "state": "active", 44     "state": "active",
            59     "title": "No Organization", 45     "title": "No Organization",
            60     "type": "organization" 46     "type": "organization"
            61   }, 47   },
            62   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 48   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            63   "private": false, 49   "private": false,
            64   "relationships_as_object": [], 50   "relationships_as_object": [],
            65   "relationships_as_subject": [], 51   "relationships_as_subject": [],
            n 66   "resources": [ n 52   "resources": [],
            67     { 
            68       "cache_last_updated": null, 
            69       "cache_url": null, 
            70       "created": "2024-12-02T22:29:38", 
            71       "data": [ 
            72         "dcterms:title", 
            73         "dcterms:accessRights", 
            74         "dcterms:creator", 
            75         "dcterms:description", 
            76         "dcterms:issued", 
            77         "dcterms:language", 
            78         "dcterms:identifier", 
            79         "dcat:theme", 
            80         "dcterms:type", 
            81         "dcat:keyword", 
            82         "dcat:landingPage", 
            83         "dcterms:hasVersion", 
            84         "dcterms:format", 
            85         "mls:task", 
            86         "datacite:isDescribedBy" 
            87       ], 
            88       "description": "The json representation of the dataset with its  
            89 distributions based on DCAT.", 
            90       "format": "JSON", 
            91       "hash": "", 
            92       "id": "205fdab0-fe56-4db5-9d8f-b20ee2a33d99", 
            93       "last_modified": "2024-12-02T21:41:07.194351", 
            94       "metadata_modified": "2024-12-02T21:41:07.204184", 
            95       "mimetype": "application/json", 
            96       "mimetype_inner": null, 
            97       "name": "Original Metadata", 
            98       "package_id": "e1a34273-2816-4b72-9371-2a89ec826409", 
            99       "position": 0, 
            100       "resource_type": null, 
            101       "size": 773, 
            102       "state": "active", 
            103       "url":  
            104 resource/205fdab0-fe56-4db5-9d8f-b20ee2a33d99/download/metadata.json", 
            105       "url_type": "upload" 
            106     } 
            107   ], 
            108   "services_used_list": "", 53   "services_used_list": "",
            109   "state": "active", 54   "state": "active",
            110   "tags": [ 55   "tags": [
            111     { 56     {
            n 112       "display_name": "CLIP", n 57       "display_name": "Image-Text Dataset",
            113       "id": "b5ca1899-21f6-4744-b974-a72e6c60b3bb", 58       "id": "f924d950-f95d-42b8-8c89-d5aad8414389",
            114       "name": "CLIP", 59       "name": "Image-Text Dataset",
            115       "state": "active", 60       "state": "active",
            116       "vocabulary_id": null 61       "vocabulary_id": null
            117     }, 62     },
            118     { 63     {
            n 119       "display_name": "Image Generation", n 
            120       "id": "a0db1a78-8e9a-494f-8d75-462dc3a45472", 
            121       "name": "Image Generation", 
            122       "state": "active", 
            123       "vocabulary_id": null 
            124     }, 
            125     { 
            126       "display_name": "Text Generation", 64       "display_name": "LAION-Aesthetic",
            127       "id": "270f80ea-6ddb-4fb5-a54f-68a02f4b4916", 65       "id": "52220535-189a-4bbc-80d0-722da53836ff",
            128       "name": "Text Generation", 66       "name": "LAION-Aesthetic",
            129       "state": "active", 67       "state": "active",
            130       "vocabulary_id": null 68       "vocabulary_id": null
            131     } 69     }
            132   ], 70   ],
            t 133   "title": "Laion-400M: Open dataset of CLIP-filtered 400 million  t 71   "title": "LAION-400M: Open dataset of clip-filtered 400 million 
            134 image-text pairs", 72 image-text pairs",
            135   "type": "dataset", 73   "type": "dataset",
            136   "version": "" 74   "version": ""
            137 } 75 }