Age of Semantics (AoS)-driven Adaptive Frame/Segment Control for Machine-centric Streaming Transmission

Ruichao Zhang; Lizhuang Tan; Maher Guizani; Wei Zhang; Hongxia Zhang; Peiying Zhang

doi:10.64509/jicn.22.110

Authors

Ruichao Zhang Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Ji'nan 250014, China; Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Ji’nan 250353, China Author
Lizhuang Tan Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Ji'nan 250014, China; Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Ji’nan 250353, China Author
Maher Guizani Department of Computer Science and Engineering, University of Texas Arlington, Arlington TX 76019, USA Author
Wei Zhang Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Ji'nan 250014, China; Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Ji’nan 250353, China Author
Hongxia Zhang Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China Author
Peiying Zhang Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China Author

DOI:

https://doi.org/10.64509/jicn.22.110

Keywords:

Age of Information, Machine-centric Streaming Transmission, Real-time Control, Adaptive Transmission Control

Abstract

Machine-centric streaming transmission for inference needs to ensure both information freshness and receiver-side semantic capture rate that is available in time for inference. However, dynamic bandwidth and scene variations make these two requirements difficult to satisfy at the same time. Relying only on freshness-oriented metrics or fixed transmission modes cannot fully characterize the trade-off between freshness and semantic capture rate in Frame-by-Frame (FBF) and Segment-by-Segment (SBS) transmission. We propose Age of Semantics (AoS), which uses a computable semantic cost to jointly measure information freshness, receiver-side semantic capture rate, and the impact of scene dynamics. Based on AoS, we construct a real-time adaptive control strategy. In each control interval, the strategy compares FBF and SBS under the current network and scene states, and selects the mode with lower semantic cost. A hysteresis mechanism is used to suppress frequent switching near the decision boundary and improve online control stability. Experiments cover multiple public datasets, bandwidth levels, ablation settings, and dynamic bandwidth traces. The results show that our strategy reduces semantic transmission cost under different network and scene conditions, while maintaining stable real-time control behavior.

Downloads

Download data is not yet available.

References

[1] Shi, W., Li, Q., Yu, Q., Wang, F., Shen, G., Jiang, Y., Xu, Y., Ma, L., Muntean, G.-M.: A Survey on Intelligent Solutions for Increased Video Delivery Quality in Cloud-Edge-End Networks. IEEE Communications Surveys & Tutorials 27(2), 1363-1394 (2025). https://doi.org/10.1109/COMST.2024.3427360

[2] Xu, R., Razavi, S., Zheng, R.: Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques. IEEE Communications Surveys & Tutorials 25(4), 2951-2982 (2023). https://doi.org/10.1109/COMST.2023.3323091

[3] Shao, J., Zhang, X., Zhang, J.: Task-Oriented Communication for Edge Video Analytics. IEEE Transactions on Wireless Communications 23(5), 4141-4154 (2024). https://doi.org/10.1109/TWC.2023.3314888

[4] Zhang, Y., Zhang, W., Du, H., Yan, C., Liu, L., Zheng, Q.: FHVAC: Feature-Level Hybrid Video Adaptive Configuration for Machine-Centric Live Streaming. IEEE Transactions on Parallel and Distributed Systems 35(5), 780-795 (2024). https://doi.org/10.1109/TPDS.2024.3372046

[5] Xiao, X., Zuo, Y., Yan, M., Wang, W., He, J., Zhang, Q.: Task-Oriented Video Compressive Streaming for Real-Time Semantic Segmentation. IEEE Transactions on Mobile Computing 23(12), 14396-14413 (2024). https://doi.org/10.1109/TMC.2024.3446185

[6] Chen, S., Yin, J., Zhong, R., Liu, F.: DeVA: An Edge-Assisted Video Analytics Framework for Depth Estimation. IEEE Transactions on Mobile Computing 24(12), 13177-13190 (2025). https://doi.org/10.1109/TMC.2025.3588864

[7] Yates, R.D., Sun, Y., Brown, D.R., Kaul, S.K., Modiano, E., Ulukus, S.: Age of Information: An Introduction and Survey. IEEE Journal on Selected Areas in Communications 39(5), 1183-1210 (2021). https://doi.org/10.1109/JSAC.2021.3065072

[8] Huang, Z., Wu, W., Wu, K., Gao, G., Wang, J.: Minimizing Age of Semantic Information for Analytics-Oriented Video Streaming Systems. IEEE Transactions on Mobile Computing 24(12), 12885-12902 (2025). https://doi.org/10.1109/TMC.2025.3588474

[9] Feng, D., Wang, L., Chen, S., Tung, L., Liu, F.: X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics. In Proceedings of IEEE INFOCOM 2024 - IEEE Conference on Computer Communications, pp. 1-10 (2024). https://doi.org/10.1109/INFOCOM52122.2024.10621341

[10] Zhang, X., Xu, H., Zou, L., Duan, J., Wu, C., Xue, Y., Chen, Z., Chen, X.: Rosevin: Employing Resource- and Rate-Adaptive Edge Super-Resolution for Video Streaming. In Proceedings of IEEE INFOCOM 2024 - IEEE Conference on Computer Communications, pp. 491-500 (2024). https://doi.org/10.1109/INFOCOM52122.2024.10621341

[11] He, Y., Yang, P., Qin, T., Hou, J., Zhang, N.: Joint Encoding and Enhancement for Low-Light Video Analytics in Mobile Edge Networks. IEEE Transactions on Mobile Computing 24(4), 3330-3345 (2025). https://doi.org/10.1109/TMC.2024.3514214

[12] Zhu, A., Zhang, S., Cheng, K., Shi, X., Qian, Z., Lu, S.: AdaStreamer: Machine-Centric High-Accuracy Multi-Video Analytics with Adaptive Neural Codecs. In Proceedings of IEEE INFOCOM 2024 - IEEE Conference on Computer Communications, pp. 1161-1170 (2024). https://doi.org/10.1109/INFOCOM52122.2024.10621074

[13] Cen, S., Zhang, M., Zhu, Y., Liu, J.: AdaDSR: Adaptive Configuration Optimization for Neural Enhanced Video Analytics Streaming. IEEE Internet of Things Journal 11(7), 11919-11929 (2024). https://doi.org/10.1109/JIOT.2023.3331699

[14] Li, Z., Zhang, M., Zhu, Y.: OAVS: Efficient Online Learning of Streaming Policies for Drone-sourced Live Video Analytics. In 2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS), pp. 1-10 (2024). https://doi.org/10.1109/IWQoS61813.2024.10682870

[15] Zhang, Y., Zhang, W., Yuan, M., Xu, L., Yan, C., Gong, T., Du, H.: Lightweight Configuration Adaptation With Multi-Teacher Reinforcement Learning for Live Video Analytics. IEEE Transactions on Mobile Computing 24(5), 4466-4480 (2025). https://doi.org/10.1109/TMC.2025.3526359

[16] Li, X., Bi, S., Wang, S., Li, X., Zhang, Y.-J.A.: Digital semantic device-edge co-inference with task-oriented ARQ. IEEE Transactions on Vehicular Technology 73(9), 13986-13990 (2024). https://doi.org/10.1109/TVT.2024.3390213

[17] Peng, Y., Xiang, L., Yang, K., Wang, K., Debbah, M.: Semantic Communications With Computer Vision Sensing for Edge Video Transmission. IEEE Transactions on Mobile Computing 25(6), 7988-8001 (2026). https://doi.org/10.1109/TMC.2025.3646710

[18] Gao, G., Dong, Y., Wang, R., Zhou, X.: EdgeVision: Towards Collaborative Video Analytics on Distributed Edges for Performance Maximization. IEEE Transactions on Multimedia 26, 9083-9094 (2024). https://doi.org/10.1109/TMM.2024.3385678

[19] Dai, X., Zhang, Z., Yang, P., Xu, Y., Liu, X., Lui, J.C.S.: AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics. In Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7229-7238 (2024). https://doi.org/10.1145/3664647.3681269

[20] Liu, Z., Wang, Y., Zhao, Y., Qiu, C., Zhang, C., Wang, X., Dong, M.: Enabling Real-Time Video Detection With Adaptive and Distributed Scheduling in Mobile Edge Computing. IEEE Transactions on Mobile Computing 24(12), 12784-12801 (2025). https://doi.org/10.1109/TMC.2025.3588142

[21] Kaul, S., Yates, R., Gruteser, M.: Real-time status: How often should one update? In Proceedings of INFOCOM'12, pp. 2731-2735 (2012). https://doi.org/10.1109/INFOCOM.2012.6195689

[22] Chiariotti, F., Holm, J., Kalor, A.E., Soret, B., Jensen, S.K., Pedersen, T.B., Popovski, P.: Query Age of Information: Freshness in Pull-Based Communication. IEEE Transactions on Communications 70(3), 1606-1622 (2022). https://doi.org/10.1109/TCOMM.2022.3141786

[23] Maatouk, A., Assaad, M., Ephremides, A.: The Age of Incorrect Information: An Enabler of Semantics-Empowered Communication. IEEE Transactions on Wireless Communications 22(4), 2621-2635 (2023). https://doi.org/10.1109/TWC.2022.3213227

[24] Meesena, W., Nikunram, C., Turner, S.J., Supittayapornpong, S.: Minimizing Age of Processed Information Over Unreliable Wireless Network Channels. IEEE Transactions on Mobile Computing 24(5), 3567-3578 (2025). https://doi.org/10.1109/TMC.2024.3520913

[25] Xie, S., Ma, S., Ding, M., Shi, Y., Tang, M., Wu, Y.: Robust Information Bottleneck for Task-Oriented Communication With Digital Modulation. IEEE Journal on Selected Areas in Communications 41(8), 2577-2591 (2023). https://doi.org/10.1109/JSAC.2023.3288252

[26] Ma, S., Qiao, W., Wu, Y., Li, H., Shi, G., Gao, D., Shi, Y., Li, S., Al-Dhahir, N.: Task-Oriented Explainable Semantic Communications. IEEE Transactions on Wireless Communications 22(12), 9248-9262 (2023). https://doi.org/10.1109/TWC.2023.3269444

[27] Wu, W., Yang, Y., Deng, Y., Aghvami, A.-H.: Goal-Oriented Semantic Communications for Robotic Waypoint Transmission: The Value and Age of Information Approach. IEEE Transactions on Wireless Communications 23(12), 18903-18915 (2024). https://doi.org/10.1109/TWC.2024.3424493

[28] Wang, S., Bi, S., Zhang, Y.-J.A.: Edge Video Analytics With Adaptive Information Gathering: A Deep Reinforcement Learning Approach. IEEE Transactions on Wireless Communications 22(9), 5800-5813 (2023). https://doi.org/10.1109/TWC.2023.3237202

[29] Wang, S., Yang, J., Bi, S.: Adaptive Video Streaming in Multi-Tier Computing Networks: Joint Edge Transcoding and Client Enhancement. IEEE Transactions on Mobile Computing 23(4), 2657-2670 (2024). https://doi.org/10.1109/TMC.2023.3263046

[30] Dai, P., Chao, Y., Wu, X., Liu, K., Guo, S.: Context-aware offloading for edge-assisted on-device video analytics through online learning approach. IEEE Transactions on Mobile Computing 23(12), 12761-12777 (2024). https://doi.org/10.1109/TMC.2024.3418608

[31] Kong, Y., Yang, P., Cheng, Y.: Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments. In Proceedings of the 31st ACM International Conference on Multimedia, pp. 9051-9060 (2023). https://doi.org/10.1145/3581783.3612585

[32] Nan, Y., Jiang, S., Li, M.: Large-Scale Video Analytics with Cloud-Edge Collaborative Continuous Learning. ACM Transactions on Sensor Networks 20(1), 14-11423 (2024). https://doi.org/10.1145/3624478

[33] Wang, Z., Zhang, R., Zhang, S., Cheng, W., Wang, W., Cui, Y.: Edge-Assisted Adaptive Configuration for Serverless-Based Video Analytics. IEEE Transactions on Networking 33(3), 1144-1159 (2025). https://doi.org/10.1109/TON.2024.3523956

[34] Ayyoubzadeh, S.M., Liu, W., Kezele, I., Yu, Y., Wu, X., Wang, Y., Jin, T.: Test-time adaptation for optical flow estimation using motion vectors. IEEE Transactions on Image Processing 32, 4977-4988 (2023). https://doi.org/10.1109/TIP.2023.3309108

[35] Yan, Y., Zhang, S., Jin, Y., Cheng, F., Qian, Z., Lu, S.: Spatial and temporal detection with attention for real-time video analytics at edges. IEEE Transactions on Mobile Computing 23(10), 9254-9270 (2024). https://doi.org/10.1109/TMC.2024.3361016

[36] Shi, X., Zhang, S., Wu, J., Chen, N., Cheng, K., Liang, Y., Lu, S.: Adapyramid: Adaptive pyramid for accelerating high-resolution object detection on edge devices. IEEE Transactions on Mobile Computing 23(8), 8208-8224 (2023). https://doi.org/10.1109/TMC.2023.3343448

[37] Li, X., Zhang, S., Huang, Y., Ma, X., Wang, Z., Luo, H.: Towards timely video analytics services at the network edge. IEEE Transactions on Mobile Computing 23(11), 10443-10459 (2024). https://doi.org/10.1109/TMC.2024.3376769

[38] Dendorfer, P., Osep, A., Milan, A., Schindler, K., Cremers, D., Reid, I., Roth, S., Leal-Taixe, L.: MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking. International Journal of Computer Vision 129(4), 845-881 (2021). https://doi.org/10.1007/s11263-020-01393-0

[39] Varga, L.A., Kiefer, B., Messmer, M., Zell, A.: SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water. In Proceedings of 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2260-2270 (2022). https://doi.org/10.1109/WACV51458.2022.00374

[40] Cao, Y., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Van Gool, L., Han, J., et al.: VisDrone-DET2021: The Vision Meets Drone Object Detection Challenge Results. In Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2847-2854 (2021). https://doi.org/10.1109/ICCVW54120.2021.00319

[41] Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real-Time End-to-End Object Detection. In Proceedings of 38th Conference on Neural Information Processing Systems (NeurIPS 2024), pp. 107984-108011 (2024). https://doi.org/10.52202/079017-3429