Language Repository for Long Video Understanding
Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park, Michael S. Ryoo · 2025
Language has become a prominent modality in computer vision with the rise of LLMs.Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length.This becomes critical, especially in applications such as longform video understanding.In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., alltextual) representation.Our repository is updated iteratively based on multi-scale video chunks.We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales.The proposed framework is evaluated on zero-shot visual question-answering benchmarks, showing state-of-the-art performance at its scale.Our code is available at github.com/kkahatapitiya/LangRepo.