# BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics

arXiv: https://arxiv.org/abs/2607.19515 · HTML: https://mlsanity.com/paper/2607.19515/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [A Technical Overview of AV1](https://mlsanity.com/paper/2008.06091/) (2020)
- [CHAD: Charlotte Anomaly Dataset](https://mlsanity.com/paper/2212.09258/) (2022)
- [Advances In Video Compression System Using Deep Neural Network: A Review And Case Studies](https://mlsanity.com/paper/2101.06341/) (2021)
- [Recent Standard Development Activities on Video Coding for Machines](https://mlsanity.com/paper/2105.12653/) (2021)
- [On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures](https://mlsanity.com/paper/2007.14314/) (2020)
- [Small Vision-Language Models are Smart Compressors for Long Video Understanding](https://mlsanity.com/paper/2604.08120/) (2026)
- [Does Video Compression Impact Tracking Accuracy?](https://mlsanity.com/paper/2202.00892/) (2022)
- [Impact of Video Compression on the Performance of Object Detection Systems for Surveillance Applications](https://mlsanity.com/paper/2211.05805/) (2022)

## Abstract (arXiv)

Continuous surveillance video creates a growing storage, transmission, and inference burden for enterprise video analytics systems. While modern codecs such as H.265 reduce bitrate for human-viewable video, aggressive compression can degrade downstream computer-vision performance and does not necessarily reduce the number of vision-language model (VLM) inference calls required for semantic video understanding. This paper evaluates BLUE, a fixed-camera surveillance compression approach that suppresses static-background redundancy while preserving foreground activity, for its effect on VLM-based event and anomaly understanding. We compare raw H.265 and BLUE-compressed H.265 video on two surveillance datasets: VIRAT, comprising 227 paired event samples from 106 clips, and CHAD, comprising 54 human-activity anomaly clips. For each pair, the same frame index is evaluated using a VLM captioning pipeline, and outputs are scored against annotation-derived ground truth using a blind judging protocol. The results show no measurable degradation in semantic inference quality. On VIRAT, the mean VLM score remains effectively unchanged between raw H.265 and BLUE, with a mean difference of approximately -0.01 on a 0-10 scale. On CHAD, raw H.265 and BLUE obtain near-equivalent mean scores of 4.31 and 4.26, respectively. Compression saving is also uncorrelated with VLM score change on VIRAT (r = 0.004), indicating that higher BLUE compression does not predict semantic quality loss. Beyond storage reduction, BLUE increases the share of skip-heavy P-frames on CHAD from 1.4% to 53.2%, enabling an estimated 53% reduction in VLM calls through packet-size-based frame skipping. These findings suggest that BLUE functions as a machine-centric compression layer for surveillance video, reducing bandwidth and inference cost while preserving VLM semantic performance.