Skip to content
Conference

Distilled Vision-Language Model Semantics for Edge-Deployable Content-Aware Adaptive Video Compression

Aug 2026 · 2026 IEEE/CIC International Conference on Communications in China (ICCC) · pp. 485-490 · 0 citations · 14 references

Abstract

With the proliferation of edge video services, content-aware adaptive video compression has become increasingly critical to balancing bandwidth efficiency and visual quality. However, conventional codec control methods mainly rely on low-level signal statistics, limiting their adaptability to high-level content semantics. Although vision-language models (VLMs) offer rich semantic understanding, their prohibitive inference costs preclude direct deployment in resource-constrained edge environments. To bridge this gap, this paper proposes CAVC, an edge-deployable content-aware adaptive video compression framework leveraging distilled VLM semantics. Specifically, semantic knowledge from a large VLM is distilled into a lightweight video feature extractor, yielding compact content representations that inform adaptive compression decisions. A soft actor-critic policy is then trained to optimize compression parameters under quality constraints. Experiments on UVG and MCL-JCV show that the proposed method improves rate-distortion efficiency over x265 and achieves competitive performance compared with representative learned compression baselines, while requiring substantially lower deployment overhead than end-to-end learned codecs. These results demonstrate the practicality of CAVC for resource-constrained edge video scenarios.

View source

Similar papers

Open access Sep 2026

Dynamic Token Pruning for Efficient Cross-Modal Alignment in Edge-IoT Video Analytics Systems

This study presents Dynamic Token Pruning for Cross-Modal Alignment (DTP-CMA), a framework that achieves faster inference speeds while maintaining semantic fidelity and positions DTP-CMA as a strong candidate framework across diverse edge-deployable multimodal video analytics challenges.

Mohaned Zkaria Salem, Ali Hussein Khalaf al-Sammarraie · 0 citations

VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs

VideoMM is introduced, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity and accelerates inference by 2.73 times over current leading methods, establishing a highly scalable paradigm for long-video understanding.

Hao-Yu Guo, Yuan Feng, Jun-Lin Lv et al. · 1 citation
Open access 2026

Context-Aware Semantic Video Coding via Content-Adaptive Parameter Overfitting

A context-aware framework that specializes a pretrained semantic decoder to each group of pictures by optimizing only its channel-wise scale factors and transposed-convolution biases, enabling the receiver to reproduce the adapted decoder without full-model retraining is introduced.

P. Samarathunga, Yasith Ganearachchi, Thanuj Fernando et al. · 0 citations
Preprint Aug 2026

MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding

This work systematically study MoE designs for vision encoder scaling and finds that fine-grained MoE topologies yield substantial gains over both dense and standard MoE counterparts, and proposes an auxiliary-loss-free balancing variant for better expert utilization, and designs a specialized MoE kernel to mitigate in...

Bonan Zhang, Shiyu Dong, Quan Hung Tran et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.