VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

Kangsan Kim, Geon Park, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang. VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025. pages 3295-3305, Computer Vision Foundation / IEEE, 2025. [doi]

Abstract

Abstract is missing.