Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

TL;DR

Flash-VStream is a real-time, memory-efficient video-language model designed for online video streams, capable of understanding long videos and answering user queries with reduced latency and VRAM usage, outperforming existing methods.

Contribution

The paper introduces Flash-VStream, a novel memory-based model for online video understanding, and proposes VStream-QA, a new benchmark for streaming video question answering.

Findings

Achieves state-of-the-art performance on offline video understanding benchmarks.

Reduces inference latency and VRAM consumption significantly.

Demonstrates superior performance on the proposed online streaming benchmark.

Abstract

Benefiting from the advancements in large language models and cross-modal alignment, existing multi-modal video understanding methods have achieved prominent performance in offline scenario. However, online video streams, as one of the most common media forms in the real world, have seldom received attention. Compared to offline videos, the 'dynamic' nature of online video streams poses challenges for the direct application of existing models and introduces new problems, such as the storage of extremely long-term information, interaction between continuous visual content and 'asynchronous' user questions. Therefore, in this paper we present Flash-VStream, a video-language model that simulates the memory mechanism of human. Our model is able to process extremely long video streams in real-time and respond to user queries simultaneously. Compared to existing models, Flash-VStream achieves significant reductions in inference latency and VRAM consumption, which is intimately related to performing understanding of online streaming video. In addition, given that existing video understanding benchmarks predominantly concentrate on offline scenario, we propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding. Comparisons with popular existing methods on the proposed benchmark demonstrate the superiority of our method for such challenging setting. To verify the generalizability of our approach, we further evaluate it on existing video understanding benchmarks and achieves state-of-the-art performance in offline scenarios as well. All code, models, and datasets are available at the https://invinciblewyq.github.io/vstream-page/