# Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory

Source: [Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory](<https://www.sota2.com/research/paper/68fa77821e209131cea73b00>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:20:40.032Z

Authors: Saket Gurukar, Asim Kadav

Published: 2025-03-17T20:25:41.000Z

## Abstract

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To tackle this issue, we present Long-Video Memory Network, Long-VMNet, a novel video understanding method that employs a fixed-size memory representation to store discriminative patches sampled from the input video. Long-VMNet achieves improved efficiency by leveraging a neural sampler that identifies discriminative tokens. Additionally, Long-VMNet only needs one scan through the video, greatly boosting efficiency. Our results on the Rest-ADL dataset demonstrate an 18x -- 75x improvement in inference times for long-form video retrieval and answering questions, with a competitive predictive performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.13707>)

[PDF](<https://arxiv.org/pdf/2503.13707.pdf>)
