Sethuraman TV Savya Khosla Vignesh Srinivasakumar Jiahui Huang Seoung Wug Oh Simon Jenni Derek Hoiem Joon-Young Lee FRAME: Pre-Training Video Feature Representations via Anticipation and Memory. 2025 June abs/2506.05543 CoRR https://doi.org/10.48550/arXiv.2506.05543 db/journals/corr/corr2506.html#abs-2506-05543 streams/journals/corr