SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM

Ming Nie, Dan Ding, Chunwei Wang, Yuanfan Guo, Jianhua Han +2 more
2/3/2026

Abstract

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to simultaneously retain high-quality frame-level semantic information ( i.e. , a sufficient number of tokens per frame) and comprehensive video-level temporal information ( i.e. , an adequate number of sampled frames per video). This limitation hinders the advancement of Vid-LLMs towards fine-grained video understanding. To address this issue, we introduce the SlowFocus mechanism, which significantly enhances the equivalent sampling frequency without compromising the quality of frame-level visual tokens. SlowFocus begins by identifying the query-related temporal segment based on the posed question, then performs dense sampling on this segment to extract local high-frequency features. A multi-frequency mixing attention module is further leveraged to aggregate these local high-frequency details with global low-frequency contexts for enhanced temporal comprehension. Additionally, to tailor Vid-LLMs to this innovative mechanism, we introduce a set of training strategies aimed at bolstering both temporal grounding and detailed temporal reasoning capabilities. Furthermore, we establish FineAction-CGR, a benchmark specifically devised to assess the ability of Vid-LLMs to process fine-grained temporal understanding tasks. Comprehensive experiments demonstrate the superiority of our mechanism across both existing public video understanding benchmarks and our proposed FineAction-CGR.

DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{nie2026slowfocus,
  title  = {SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM},
  author = {Ming Nie and Dan Ding and Chunwei Wang and Yuanfan Guo and Jianhua Han and Hang Xu and Li Zhang},
  year   = {2026},
  doi    = {10.52202/079017-2599},
  url    = {https://doi.org/10.52202/079017-2599},
  journal = {NEURIPS 2024 2024}
}

Discussion