{"url":"/dataset/nocaps","name":"NoCaps","full_name":null,"description_markdown":"The nocaps benchmark consists of 166,100 human-generated captions describing 15,100 images from the OpenImages validation and test sets.\r\n\r\nSource: [nocaps: novel object captioning at scale](/paper/nocaps-novel-object-captioning-at-scale)\r\nImage Source: [https://nocaps.org/](https://nocaps.org/)","description_withheld":null,"homepage":"https://nocaps.org/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/nocaps-novel-object-captioning-at-scale","title":"nocaps: novel object captioning at scale","first_author":"Harsh Agrawal","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[],"variants":["nocaps val","nocaps-val-overall","nocaps-val-out-domain","nocaps-val-near-domain","nocaps-val-in-domain","nocaps-XD out-of-domain","nocaps-XD near-domain","nocaps-XD in-domain","nocaps-XD entire","nocaps out-of-domain","nocaps near-domain","nocaps in-domain","nocaps entire","NoCaps"],"data_loaders":[],"num_papers_in_archive":175,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-nocaps-in-domain","task":"Image Captioning","dataset_variant":"nocaps in-domain","rows":41,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"PaLI","paper":"/paper/pali-a-jointly-scaled-multilingual-language","metrics":{"CIDEr":"149.1"},"code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-near-domain","task":"Image Captioning","dataset_variant":"nocaps near-domain","rows":40,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"GIT2, Single Model","paper":"/paper/git-a-generative-image-to-text-transformer","metrics":{"B1":"88.9","B2":"75.86","B3":"58.9","B4":"38.95","CIDEr":"125.51","METEOR":"32.95","ROUGE-L":"63.66","SPICE":"16.11"},"code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-out-of-domain","task":"Image Captioning","dataset_variant":"nocaps out-of-domain","rows":40,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"PaLI","paper":"/paper/pali-a-jointly-scaled-multilingual-language","metrics":{"B1":"86.28","B2":"71.19","B3":"52.63","B4":"32.0","CIDEr":"126.67","METEOR":"30.99","ROUGE-L":"61.35","SPICE":"15.49"},"code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-entire","task":"Image Captioning","dataset_variant":"nocaps entire","rows":39,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"Lyrics","paper":"/paper/lyrics-boosting-fine-grained-language-vision","metrics":{"CIDEr":"126.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-entire","task":"Image Captioning","dataset_variant":"nocaps-XD entire","rows":12,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"GIT2","paper":"/paper/git-a-generative-image-to-text-transformer","metrics":{"B1":"88.43","B2":"75.02","B3":"57.87","B4":"37.65","CIDEr":"124.77","METEOR":"32.56","ROUGE-L":"63.19","SPICE":"16.06"},"code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset_variant":"nocaps-val-in-domain","rows":11,"metrics":["CIDEr","SPICE","Pre-train (#images)"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"CIDEr":"123.7","Pre-train (#images)":"1.1B","SPICE":"16.3"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset_variant":"nocaps-val-overall","rows":11,"metrics":["CIDEr","SPICE","Pretrain (#images)"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"CIDEr":"121.6","Pretrain (#images)":"1.1B","SPICE":"15.8"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-in-domain","task":"Image Captioning","dataset_variant":"nocaps-XD in-domain","rows":11,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"GIT2","paper":"/paper/git-a-generative-image-to-text-transformer","metrics":{"B1":"88.86","B2":"75.86","B3":"59.94","B4":"41.1","CIDEr":"124.18","METEOR":"33.83","ROUGE-L":"63.82","SPICE":"16.36"},"code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-near-domain","task":"Image Captioning","dataset_variant":"nocaps-XD near-domain","rows":11,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"GIT2","paper":"/paper/git-a-generative-image-to-text-transformer","metrics":{"B1":"88.9","B2":"75.86","B3":"58.9","B4":"38.95","CIDEr":"125.51","METEOR":"32.95","ROUGE-L":"63.66","SPICE":"16.11"},"code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-out-of-domain","task":"Image Captioning","dataset_variant":"nocaps-XD out-of-domain","rows":11,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"GIT2","paper":"/paper/git-a-generative-image-to-text-transformer","metrics":{"B1":"86.28","B2":"71.15","B3":"52.36","B4":"30.15","CIDEr":"122.27","METEOR":"30.15","ROUGE-L":"60.91","SPICE":"15.62"},"code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset_variant":"nocaps-val-near-domain","rows":10,"metrics":["CIDEr","SPICE","Pre-train (#images)"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"CIDEr":"120.2","Pre-train (#images)":"1.1B","SPICE":"15.9"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset_variant":"nocaps-val-out-domain","rows":10,"metrics":["CIDEr","SPICE","Pretrain (#images)"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"CIDEr":"124.8","Pretrain (#images)":"1.1B","SPICE":"15.1"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-nocaps-val","task":"Image Captioning","dataset_variant":"nocaps val","rows":3,"metrics":["CIDEr","SPICE"],"first_row_in_archive_order":{"model":"Prismer","paper":"/paper/prismer-a-vision-language-model-with-an","metrics":{"CIDEr":"107.9","SPICE":"14.8"},"code_links":[{"title":"nvlabs/prismer","url":"https://github.com/nvlabs/prismer"},{"title":"KastanDay/video-pretrained-transformer","url":"https://github.com/KastanDay/video-pretrained-transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","rows_on_this_dataset":12,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/grit-faster-and-better-image-captioning","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","date":"2022-07-20","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-general-purpose","title":"Language Models are General-Purpose Interfaces","date":"2022-06-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","rows_on_this_dataset":15,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":0,"samples_unverified":21,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/blip-bootstrapping-language-image-pre","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","date":"2022-01-28","rows_on_this_dataset":8,"code_links":9,"syntology":null},{"paper":"/paper/scaling-up-vision-language-pre-training-for","title":"Scaling Up Vision-Language Pre-training for Image Captioning","date":"2021-11-24","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","rows_on_this_dataset":8,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","rows_on_this_dataset":8,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":37,"samples_ran":18,"samples_unverified":19,"pointer_only_for_licence":28,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conceptual-12m-pushing-web-scale-image-text","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","date":"2021-02-17","rows_on_this_dataset":4,"code_links":3,"syntology":null},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":2,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","rows_on_this_dataset":8,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vivo-surpassing-human-performance-in-novel","title":"VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning","date":"2020-09-28","rows_on_this_dataset":8,"code_links":0,"syntology":null},{"paper":"/paper/oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":11,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":113,"samples_ran":42,"samples_unverified":71,"pointer_only_for_licence":30,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}