Dataset Groups Activity Stream MSCOCO caption challenge dataset The MSCOCO caption challenge dataset is a subset of the MSCOCO caption dataset, containing 113,287 training images, 5,000 validation images, and 5,000 test images. BibTex: @dataset{Jiajun_Du_and_Yu_Qin_and_Hongtao_Lu_and_Yonghua_Zhang_2024, abstract = {The MSCOCO caption challenge dataset is a subset of the MSCOCO caption dataset, containing 113,287 training images, 5,000 validation images, and 5,000 test images.}, author = {Jiajun Du and Yu Qin and Hongtao Lu and Yonghua Zhang}, doi = {10.57702/knz565vz}, institution = {No Organization}, keyword = {'MSCOCO', 'captioning', 'image captioning'}, month = {dec}, publisher = {TIB}, title = {MSCOCO caption challenge dataset}, url = {https://service.tib.eu/ldmservice/dataset/mscoco-caption-challenge-dataset}, year = {2024} }
