Literature Database Entry

chi2026evod-roi

Xuejian Chi, Bowen Han, Yifei Zou, Yong Zhang, Falko Dressler and Dongxiao Yu, "EVOD-RoI: Adaptive Edge-Assisted Video Object Detection System Based on RoI Transmission and Processing," Proceedings of 34th ACM International Conference on Multimedia (MM 2026), Rio de Janeiro, Brazil, November 2026. (to appear)

Abstract

With the continuous convergence of edge intelligence and multimedia applications, edge-assisted video object detection has attracted increasing attention. To enhance system quality of service (QoS), existing studies primarily focus on full-frame scheduling and resource allocation, often overlooking the dominant role of the region of interest (RoI) in detection accuracy and lacking robust detection models for regionally blurred scenarios. To address these challenges, this paper proposes EVOD-RoI, an edge-assisted video object detection system based on RoI transmission and processing. It adaptively adjusts detection location, non-RoI resolution, and model selection to reduce non-RoI resolution during edge upload, minimizing overall latency. Meanwhile, it improves accuracy by fine-tuning a model specifically for regionally blurred frames. Specifically, EVOD-RoI introduces three key innovations: (1) a spatiotemporal joint sliding window algorithm to determine the optimal RoI, which saves bandwidth during transmission stage; (2) regionally blurred feature-aware model fine-tuning to improve detection accuracy in processing stage; and (3) a deep reinforcement learning–based approach to dynamically and adaptively optimize transmission and resource scheduling under heterogeneous environments. Experiments on a real-world testbed demonstrate that, compared with SOTA methods, EVOD-RoI improves detection accuracy by 15.9%–30.1% while reducing overall system latency by 16.8%–41.8%, significantly enhancing QoS in resource-constrained edge scenarios.

Quick access

Authors' Version PDF (PDF on this web site)
BibTeX BibTeX

Contact

Xuejian Chi
Bowen Han
Yifei Zou
Yong Zhang
Falko Dressler
Dongxiao Yu

BibTeX reference

@inproceedings{chi2026evod-roi,
    author = {Chi, Xuejian and Han, Bowen and Zou, Yifei and Zhang, Yong and Dressler, Falko and Yu, Dongxiao},
    note = {to appear},
    title = {{EVOD-RoI: Adaptive Edge-Assisted Video Object Detection System Based on RoI Transmission and Processing}},
    publisher = {ACM},
    address = {Rio de Janeiro, Brazil},
    booktitle = {34th ACM International Conference on Multimedia (MM 2026)},
    month = {11},
    year = {2026},
   }
   
   

Copyright notice

Links to final or draft versions of papers are presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or distributed for commercial purposes without the explicit permission of the copyright holder.

The following applies to all papers listed above that have IEEE copyrights: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The following applies to all papers listed above that are in submission to IEEE conference/workshop proceedings or journals: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

The following applies to all papers listed above that have ACM copyrights: ACM COPYRIGHT NOTICE. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) 869-0481, or permissions@acm.org.

The following applies to all SpringerLink papers listed above that have Springer Science+Business Media copyrights: The original publication is available at www.springerlink.com.

This page was automatically generated using BibDB and bib2web.

Last modified: 2026-08-10