Dataset Groups Activity Stream CrowdCaption Dataset The CrowdCaption dataset contains 11,161 images with 21,794 group region and 43,306 group captions. Each group has an average of 2 captions. BibTex: @dataset{Gwanghyun_Kim_and_Dong_Un_Kang_and_Hoigi_Seo_and_Haeon_Kim_and_Se_Young_Chun_2024, abstract = {The CrowdCaption dataset contains 11,161 images with 21,794 group region and 43,306 group captions. Each group has an average of 2 captions.}, author = {Gwanghyun Kim and Dong Un Kang and Hoigi Seo and Haeon Kim and Se Young Chun}, doi = {10.57702/s6lce0n6}, institution = {No Organization}, keyword = {'Crowd Scene Understanding', 'Group Region', 'Image Captioning'}, month = {dec}, publisher = {TIB}, title = {CrowdCaption Dataset}, url = {https://service.tib.eu/ldmservice/dataset/crowdcaption-dataset}, year = {2024} }