Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.07859 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908949247164416 |
|---|---|
| author | Li, Chenxing Duan, Yiping Jiao, Han Tao, Xiaoming Lin, Weiyao Lu, Mingquan |
| author_facet | Li, Chenxing Duan, Yiping Jiao, Han Tao, Xiaoming Lin, Weiyao Lu, Mingquan |
| contents | Traditional video coding (VVC, HEVC) prioritizes human visual perception, transmitting substantial texture redundancy that severely hinders machine decision-making under constrained bandwidths. In dynamic channels, this redundancy causes severe ``cliff effects'' and prohibitive latency. To address this, we propose a robust multimodal semantic communication framework based on an adaptive Object-Attribute-Relation (O-A-R) hierarchy. Bypassing pixel-level reconstruction entirely, our framework directly fuses visual, textual, and audio streams to construct a decision-oriented topological graph. A bandwidth-adaptive strategy dynamically allocates resources by semantic priority, while a cross-modal mechanism leverages text and audio priors to compensate for severe visual degradation. Experimental results demonstrate that under extreme low bandwidths (1-3 kbps), our method achieves over a 90% bandwidth saving (an approximately 10-fold reduction) compared to state-of-the-art digital schemes, maintaining superior scene-graph accuracy. In deep fading channels (SNR <= 4 dB), it completely eliminates the cliff effect, ensuring graceful degradation by strictly preserving foundational object anchors even when traditional codecs suffer 100% decoding failure. Coupled with an 89\% reduction in end-to-end latency, our framework comprehensively fulfills the real-time survival requirements of embodied agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07859 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Object-Attribute-Relation Model Driven Adaptive Hierarchical Transmission for Multimodal Semantic Communication Li, Chenxing Duan, Yiping Jiao, Han Tao, Xiaoming Lin, Weiyao Lu, Mingquan Signal Processing Traditional video coding (VVC, HEVC) prioritizes human visual perception, transmitting substantial texture redundancy that severely hinders machine decision-making under constrained bandwidths. In dynamic channels, this redundancy causes severe ``cliff effects'' and prohibitive latency. To address this, we propose a robust multimodal semantic communication framework based on an adaptive Object-Attribute-Relation (O-A-R) hierarchy. Bypassing pixel-level reconstruction entirely, our framework directly fuses visual, textual, and audio streams to construct a decision-oriented topological graph. A bandwidth-adaptive strategy dynamically allocates resources by semantic priority, while a cross-modal mechanism leverages text and audio priors to compensate for severe visual degradation. Experimental results demonstrate that under extreme low bandwidths (1-3 kbps), our method achieves over a 90% bandwidth saving (an approximately 10-fold reduction) compared to state-of-the-art digital schemes, maintaining superior scene-graph accuracy. In deep fading channels (SNR <= 4 dB), it completely eliminates the cliff effect, ensuring graceful degradation by strictly preserving foundational object anchors even when traditional codecs suffer 100% decoding failure. Coupled with an 89\% reduction in end-to-end latency, our framework comprehensively fulfills the real-time survival requirements of embodied agents. |
| title | Object-Attribute-Relation Model Driven Adaptive Hierarchical Transmission for Multimodal Semantic Communication |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2604.07859 |