Dataset Groups Activity Stream Multi-Modal CelebA-HQ A large-scale face image dataset that contains real face images and corresponding semantic segmentation map, sketch, and textual descriptions. BibTex: @dataset{Weihao_Xia_and_Yujiu_Yang_and_Jing-Hao_Xue_and_Baoyuan_Wu_2024, abstract = {A large-scale face image dataset that contains real face images and corresponding semantic segmentation map, sketch, and textual descriptions.}, author = {Weihao Xia and Yujiu Yang and Jing-Hao Xue and Baoyuan Wu}, doi = {10.57702/fpdk0ryi}, institution = {No Organization}, keyword = {'face images', 'semantic segmentation', 'sketch', 'textual descriptions'}, month = {dec}, publisher = {TIB}, title = {Multi-Modal CelebA-HQ}, url = {https://service.tib.eu/ldmservice/dataset/multi-modal-celeba-hq}, year = {2024} }
