Dataset Groups Activity Stream VideoVista VideoVista is a comprehensive video evaluation benchmark for Video-LLMs that covers both video understanding and reasoning across 27 tasks. BibTex: @dataset{Yunxin_Li_and_Xinyu_Chen_and_Baotian_Hu_and_Longyue_Wang_and_Haoyuan_Shi_and_Min_Zhang_2025, abstract = {VideoVista is a comprehensive video evaluation benchmark for Video-LLMs that covers both video understanding and reasoning across 27 tasks.}, author = {Yunxin Li and Xinyu Chen and Baotian Hu and Longyue Wang and Haoyuan Shi and Min Zhang}, doi = {10.57702/o3rr84rn}, institution = {No Organization}, keyword = {'Video-LLMs', 'video reasoning', 'video understanding'}, month = {jan}, publisher = {TIB}, title = {VideoVista}, url = {https://service.tib.eu/ldmservice/dataset/videovista}, year = {2025} }
