Metraipolis › archive › dc_d3d549504f6e
StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models — arXiv:2608.27881
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27881
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:33:02.105Z
- SHA-256 of the archived text
b8a3b9ce50909bd547315128bf401137bbcf7f3ba56ae982728f85f850503b28- Stable URL of this page
https://metraipolis.com/documento/dc_d3d549504f6e
How to cite
StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models — arXiv:2608.27881 — arXiv (en), https://arxiv.org/abs/2608.27881 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3d549504f6e (Metraipolis archive dc_d3d549504f6e, sha256 b8a3b9ce50909bd547315128bf401137bbcf7f3ba56ae982728f85f850503b28)
BibTeX
@misc{dcd3d549504f6e,
title = {StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models — arXiv:2608.27881},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27881},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3d549504f6e; sha256 b8a3b9ce50909bd547315128bf401137bbcf7f3ba56ae982728f85f850503b28},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27881. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently, many streaming video understanding methods have been proposed by constructing an external memory to store historical data for computational reduction. Most methods focus on optimizing the injection procedure of current data (write) and retrieving informative historical data (read) from memory, while overlooking the opportunity to further enhancing the representational capability of memory itself. In this work, we present StreamEMS, a general mechanism for improving streaming video understanding by re-structuring the historical data stored in memory through self-evolving memory scheme, enabling more informative and robust memory representations. Specifically, we first introduce a Semantic Evolution Module to evolve the memory into more information-dense representations by exploiting informative memory entities discovered via progressively shrinking semantic scales from coarse to fine. In addition, we further introduce a Prior-informed Evolution Module to evolve memory into more robust representations by leveraging prior memory distributions to refine the current memory state. We validate the effectiveness of our proposed designs on widely-used streaming video understanding datasets, i.e., OVO-Bench and StreamingBench, and the results showcase that our method performs better than other methods. Moreover, the advantage of our method becomes consistently evident even under high token usage drop rate settings, indicating the effectiveness and robustness of our method in unleashing the potential of the memory itself. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.27881 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T11:10:05.274Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).