Dataset Groups Activity Stream VideoXum VideoXum is a large-scale video summarization dataset that contains 14,001 long videos with corresponding human-annotated video and text summaries. BibTex: @dataset{Jingyang_Lin_and_Hang_Hua_and_Ming_Chen_and_Yikang_Li_and_Jenhao_Hsiao_and_Chiuman_Ho_and_Jiebo_Luo_2024, abstract = {VideoXum is a large-scale video summarization dataset that contains 14,001 long videos with corresponding human-annotated video and text summaries.}, author = {Jingyang Lin and Hang Hua and Ming Chen and Yikang Li and Jenhao Hsiao and Chiuman Ho and Jiebo Luo}, doi = {10.57702/7157h28n}, institution = {No Organization}, keyword = {'cross-modal summarization', 'video summarization', 'video-text summarization'}, month = {dec}, publisher = {TIB}, title = {VideoXum}, url = {https://service.tib.eu/ldmservice/dataset/videoxum}, year = {2024} }
