Dataset Groups Activity Stream DialogCC: Large-Scale Multi-Modal Dialogue Dataset A large-scale multi-modal dialogue dataset created by leveraging the automatic pipeline with filtering using CLIP similarity. BibTex: @dataset{Young-Jun_Lee_and_Byungsoo_Ko_and_Han-Gyu_Kim_and_Ho-Jin_Choi_2024, abstract = {A large-scale multi-modal dialogue dataset created by leveraging the automatic pipeline with filtering using CLIP similarity.}, author = {Young-Jun Lee and Byungsoo Ko and Han-Gyu Kim and Ho-Jin Choi}, doi = {10.57702/vepcqd6n}, institution = {No Organization}, keyword = {'CLIP similarity', 'large-scale dataset', 'multi-modal dialogue'}, month = {dec}, publisher = {TIB}, title = {DialogCC: Large-Scale Multi-Modal Dialogue Dataset}, url = {https://service.tib.eu/ldmservice/dataset/dialogcc--large-scale-multi-modal-dialogue-dataset}, year = {2024} }
