Jiajun Liu, Yibing Wang, Hanghang Ma, Xiaoping Wu, Xiaoqi Ma, Xiaoming Wei, Jianbin Jiao, Enhua Wu, Jie Hu 0019. Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input. International Journal of Computer Vision, 134(3):114, March 2026. [doi]
Abstract is missing.