Changes

On December 2, 2024 at 6:21:38 PM UTC, admin:
Changed title to Conceptual 12m (previously Conceptual 12M)
Set author of Conceptual 12m to Soravit Changpino (previously Soravit Changpinyo)
Updated description of Conceptual 12m from
The dataset used in the paper for training and evaluation of the proposed method for training non-cascaded large scale pixel-space text-to-image diffusion models.
to
Conceptual 12m dataset for automatic image captioning
Removed the following tags from Conceptual 12m
Added the following tags to Conceptual 12m
Changed value of field landing_page to https://arxiv.org/abs/1809.11096 in Conceptual 12m
Changed value of field defined_in to https://doi.org/10.48550/arXiv.2203.13131 in Conceptual 12m
Changed value of field citation to [] in Conceptual 12m
Deleted resource Original Metadata from Conceptual 12m
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Soravit Changpinyo", n 3   "author": "Soravit Changpino",
            4   "author_email": "", 4   "author_email": "",
            n 5   "citation": [ n 5   "citation": [],
            6     "https://doi.org/10.48550/arXiv.2405.16759", 
            7     "https://doi.org/10.48550/arXiv.2306.03168", 
            8     "https://doi.org/10.48550/arXiv.2403.12037" 
            9   ], 
            10   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 11   "defined_in": "https://doi.org/10.48550/arXiv.2304.08480", n 7   "defined_in": "https://doi.org/10.48550/arXiv.2203.13131",
            12   "doi": "10.57702/8ihuxai8", 8   "doi": "10.57702/8ihuxai8",
            13   "doi_date_published": "2024-12-02", 9   "doi_date_published": "2024-12-02",
            14   "doi_publisher": "TIB", 10   "doi_publisher": "TIB",
            15   "doi_status": true, 11   "doi_status": true,
            16   "domain": "https://service.tib.eu/ldmservice", 12   "domain": "https://service.tib.eu/ldmservice",
            17   "extra_authors": [ 13   "extra_authors": [
            18     { 14     {
            19       "extra_author": "Piyush Sharma", 15       "extra_author": "Piyush Sharma",
            20       "orcid": "" 16       "orcid": ""
            21     }, 17     },
            22     { 18     {
            23       "extra_author": "Nan Ding", 19       "extra_author": "Nan Ding",
            24       "orcid": "" 20       "orcid": ""
            25     }, 21     },
            26     { 22     {
            27       "extra_author": "Radu Soricut", 23       "extra_author": "Radu Soricut",
            28       "orcid": "" 24       "orcid": ""
            29     } 25     }
            30   ], 26   ],
            31   "groups": [ 27   "groups": [
            32     { 28     {
            33       "description": "", 29       "description": "",
            34       "display_name": "Image Captioning", 30       "display_name": "Image Captioning",
            35       "id": "7a76ce67-2607-4da9-a837-d2017dc33ec6", 31       "id": "7a76ce67-2607-4da9-a837-d2017dc33ec6",
            36       "image_display_url": "", 32       "image_display_url": "",
            37       "name": "image-captioning", 33       "name": "image-captioning",
            38       "title": "Image Captioning" 34       "title": "Image Captioning"
            39     }, 35     },
            40     { 36     {
            41       "description": "", 37       "description": "",
            n 42       "display_name": "Image Generation", n 38       "display_name": "Multimodal Learning",
            43       "id": "be25a76c-def1-4e73-8b1c-b81222d63867", 39       "id": "a88cb918-103d-4226-a87d-9d9103c1f839",
            44       "image_display_url": "", 40       "image_display_url": "",
            n 45       "name": "image-generation", n 41       "name": "multimodal-learning",
            46       "title": "Image Generation" 42       "title": "Multimodal Learning"
            47     }, 
            48     { 
            49       "description": "", 
            50       "display_name": "Image-Text Pre-training", 
            51       "id": "03a3bb8b-20d3-40b2-b5ac-4fd948153611", 
            52       "image_display_url": "", 
            53       "name": "image-text-pre-training", 
            54       "title": "Image-Text Pre-training" 
            55     }, 
            56     { 
            57       "description": "", 
            58       "display_name": "Text-to-Image", 
            59       "id": "c68d7763-4eaf-4b60-a763-d8a968e4245e", 
            60       "image_display_url": "", 
            61       "name": "text-to-image", 
            62       "title": "Text-to-Image" 
            63     }, 
            64     { 
            65       "description": "", 
            66       "display_name": "Vision-and-Language Pre-training", 
            67       "id": "3e9c0249-6f01-4a87-aba1-46afaf268b22", 
            68       "image_display_url": "", 
            69       "name": "vision-and-language-pre-training", 
            70       "title": "Vision-and-Language Pre-training" 
            71     }, 
            72     { 
            73       "description": "", 
            74       "display_name": "Visual Concepts", 
            75       "id": "a5e78018-6689-40da-9bfc-121c955db376", 
            76       "image_display_url": "", 
            77       "name": "visual-concepts", 
            78       "title": "Visual Concepts" 
            79     } 43     }
            80   ], 44   ],
            81   "id": "1ef20fa9-4ccd-4bef-bd76-1da37630fab9", 45   "id": "1ef20fa9-4ccd-4bef-bd76-1da37630fab9",
            82   "isopen": false, 46   "isopen": false,
            n 83   "landing_page": "https://arxiv.org/abs/2106.09528", n 47   "landing_page": "https://arxiv.org/abs/1809.11096",
            84   "license_title": null, 48   "license_title": null,
            85   "link_orkg": "", 49   "link_orkg": "",
            86   "metadata_created": "2024-12-02T17:55:34.172836", 50   "metadata_created": "2024-12-02T17:55:34.172836",
            n 87   "metadata_modified": "2024-12-02T17:55:34.565393", n 51   "metadata_modified": "2024-12-02T18:21:37.512489",
            88   "name": "conceptual-12m", 52   "name": "conceptual-12m",
            n 89   "notes": "The dataset used in the paper for training and evaluation  n 53   "notes": "Conceptual 12m dataset for automatic image captioning",
            90 of the proposed method for training non-cascaded large scale  
            91 pixel-space text-to-image diffusion models.", 
            92   "num_resources": 1, 54   "num_resources": 0,
            93   "num_tags": 10, 55   "num_tags": 3,
            94   "organization": { 56   "organization": {
            95     "approval_status": "approved", 57     "approval_status": "approved",
            96     "created": "2024-11-25T12:11:38.292601", 58     "created": "2024-11-25T12:11:38.292601",
            97     "description": "", 59     "description": "",
            98     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 60     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            99     "image_url": "", 61     "image_url": "",
            100     "is_organization": true, 62     "is_organization": true,
            101     "name": "no-organization", 63     "name": "no-organization",
            102     "state": "active", 64     "state": "active",
            103     "title": "No Organization", 65     "title": "No Organization",
            104     "type": "organization" 66     "type": "organization"
            105   }, 67   },
            106   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 68   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            107   "private": false, 69   "private": false,
            108   "relationships_as_object": [], 70   "relationships_as_object": [],
            109   "relationships_as_subject": [], 71   "relationships_as_subject": [],
            n 110   "resources": [ n 72   "resources": [],
            111     { 
            112       "cache_last_updated": null, 
            113       "cache_url": null, 
            114       "created": "2024-12-02T18:38:42", 
            115       "data": [ 
            116         "dcterms:title", 
            117         "dcterms:accessRights", 
            118         "dcterms:creator", 
            119         "dcterms:description", 
            120         "dcterms:issued", 
            121         "dcterms:language", 
            122         "dcterms:identifier", 
            123         "dcat:theme", 
            124         "dcterms:type", 
            125         "dcat:keyword", 
            126         "dcat:landingPage", 
            127         "dcterms:hasVersion", 
            128         "dcterms:format", 
            129         "mls:task", 
            130         "datacite:isDescribedBy" 
            131       ], 
            132       "description": "The json representation of the dataset with its  
            133 distributions based on DCAT.", 
            134       "format": "JSON", 
            135       "hash": "", 
            136       "id": "d1b5d5f0-c6d5-4dbd-a6ee-9b2d889d86f2", 
            137       "last_modified": "2024-12-02T17:55:34.557141", 
            138       "metadata_modified": "2024-12-02T17:55:34.568168", 
            139       "mimetype": "application/json", 
            140       "mimetype_inner": null, 
            141       "name": "Original Metadata", 
            142       "package_id": "1ef20fa9-4ccd-4bef-bd76-1da37630fab9", 
            143       "position": 0, 
            144       "resource_type": null, 
            145       "size": 1308, 
            146       "state": "active", 
            147       "url":  
            148 resource/d1b5d5f0-c6d5-4dbd-a6ee-9b2d889d86f2/download/metadata.json", 
            149       "url_type": "upload" 
            150     } 
            151   ], 
            152   "services_used_list": "", 73   "services_used_list": "",
            153   "state": "active", 74   "state": "active",
            154   "tags": [ 75   "tags": [
            155     { 76     {
            n 156       "display_name": "12 million pairs", n 77       "display_name": "Conceptual 12m",
            157       "id": "6ef28272-8c66-4d2c-8597-c68ae76e4494", 78       "id": "0d10ce61-89c5-498e-a7da-fb7ba37db90b",
            158       "name": "12 million pairs", 79       "name": "Conceptual 12m",
            159       "state": "active", 80       "state": "active",
            160       "vocabulary_id": null 81       "vocabulary_id": null
            161     }, 82     },
            162     { 83     {
            n 163       "display_name": "Image-Text Pre-training", n 84       "display_name": "Image Captioning",
            164       "id": "214a5ac3-3cf8-44b0-b122-1a14136f63cf", 85       "id": "c708cba4-0a1f-45c9-826f-898857783343",
            165       "name": "Image-Text Pre-training", 86       "name": "Image Captioning",
            166       "state": "active", 87       "state": "active",
            167       "vocabulary_id": null 88       "vocabulary_id": null
            168     }, 89     },
            169     { 90     {
            n 170       "display_name": "Long-tail Visual Concepts", n 
            171       "id": "47acd844-ffa8-465a-8cbd-24bf7e84bb5b", 
            172       "name": "Long-tail Visual Concepts", 
            173       "state": "active", 
            174       "vocabulary_id": null 
            175     }, 
            176     { 
            177       "display_name": "diffusion models", 
            178       "id": "67686580-d41a-4e00-875a-494e99951342", 
            179       "name": "diffusion models", 
            180       "state": "active", 
            181       "vocabulary_id": null 
            182     }, 
            183     { 
            184       "display_name": "image captioning", 91       "display_name": "Multimodal Learning",
            185       "id": "f1bbe827-a03a-4280-b9fa-0599ccfc0541", 92       "id": "41329983-d90e-4560-a97d-7fa2ba0a1f92",
            186       "name": "image captioning", 93       "name": "Multimodal Learning",
            187       "state": "active", 
            188       "vocabulary_id": null 
            189     }, 
            190     { 
            191       "display_name": "image generation", 
            192       "id": "96df81b4-32fd-4826-a903-affb005a0a60", 
            193       "name": "image generation", 
            194       "state": "active", 
            195       "vocabulary_id": null 
            196     }, 
            197     { 
            198       "display_name": "long-tail visual concepts", 
            199       "id": "4bd2e9bf-cf63-4ae0-ba9b-b4f5b06e7540", 
            200       "name": "long-tail visual concepts", 
            201       "state": "active", 
            202       "vocabulary_id": null 
            203     }, 
            204     { 
            205       "display_name": "text-to-image", 
            206       "id": "0b0e2f9a-321b-4b04-abc6-14130f66400c", 
            207       "name": "text-to-image", 
            208       "state": "active", 
            209       "vocabulary_id": null 
            210     }, 
            211     { 
            212       "display_name": "vision-and-language pre-training", 
            213       "id": "0d9c23b6-373f-46e2-9478-068178037f58", 
            214       "name": "vision-and-language pre-training", 
            215       "state": "active", 
            216       "vocabulary_id": null 
            217     }, 
            218     { 
            219       "display_name": "web-scale image-text pre-training", 
            220       "id": "2c7f0652-00fb-434b-92b5-3e244f0e6fa5", 
            221       "name": "web-scale image-text pre-training", 
            222       "state": "active", 94       "state": "active",
            223       "vocabulary_id": null 95       "vocabulary_id": null
            224     } 96     }
            225   ], 97   ],
            t 226   "title": "Conceptual 12M", t 98   "title": "Conceptual 12m",
            227   "type": "dataset", 99   "type": "dataset",
            228   "version": "" 100   "version": ""
            229 } 101 }