Wireless Image Retrieval at the Edge
Open accessThe DOI matches its Crossref record; 42 of the 44 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize the accuracy of the retrieval task under power and bandwidth constraints over the wireless link. Due to the stringent delay constraint of the underlying application, sending the whole image at a sufficient quality is not possible. We propose two alternative schemes based on digital and analog communications, respectively. In the digital approach, we first propose a deep neural network (DNN) aided retrieval-oriented image compression scheme, whose output bit sequence is transmitted over the channel using conventional channel codes. In the analog joint source and channel coding (JSCC) approach, the feature vectors are directly mapped into channel symbols. We evaluate both schemes on image based re-identification (re-ID) tasks under different channel conditions, including both static and fading channels. We show that the JSCC scheme significantly increases the end-to-end accuracy, speeds up the encoding process, and provides graceful degradation with channel conditions. The proposed architecture is evaluated through extensive simulations on different datasets and channel conditions, as well as through ablation studies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The analog JSCC approach was presented in [234] to compress and then code the feature vectors, followed by leveraging the received perturbed signal directly for wireless image retrieval at the edge server via a fully-connected neural network.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [234]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Following the state-of-the-art retrieval methods [17], [21] we employ the ResNet-50 network [34], pretrained on Ima-”
MethodA Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Information Theory and Reliable Communication.
Lee, P. M., & Gallager, R. T. (1970) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2344305 · Cited by 5,399
Scalable Person Re-identification: A Benchmark
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.133 · Cited by 4,506 · cited 1×
“Market-1501 [40] contains 32217 images of 1501 pedestrians taken from a total of six cameras in front of a”
BackgroundLearning internal representations by error propagation
RUMELHART, D. E., HINTON, G. E., & WILLIAMS, R. J. (1988) · Readings in Cognitive Science · doi:10.1016/b978-1-4832-1446-7.50035-2 · Cited by 3,002 · cited 1×
“More recently, JSCC schemes based on autoencoders [30], which are DNNs aimed at unsupervised data coding, have been introduced [2], [3], [31], [32], and are shown to provide comparable or better performance than state-of-the-art digital schemes.”
BackgroundIn Defense of the Triplet Loss for Person Re-Identification
Hermans, A., Beyer, L., & Leibe, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.07737 · Cited by 2,687
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
Li, W., Zhao, R., Xiao, T., & Wang, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.27 · Cited by 2,611 · cited 8×
“In order to measure the performance of the retrieval task, we employ three widely used datasets: CUHK03 [39] is a benchmark for person retrieval that contains 14096 images of 1467 identities taken from two different camera views.”
MethodInfluentialGray, R. M., & Neuhoff, D. L. (1998) · IEEE Transactions on Information Theory · doi:10.1109/18.720541 · Cited by 1,642
Deep Joint Source-Channel Coding for Wireless Image Transmission
Bourtsoulatze, E., Burth Kurka, D., & Gunduz, D. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2919300 · Cited by 1,476
Cited by
Items 201–279 of 279
Deep Joint Transmission-Recognition for Multi-View CamerasPreprint
Özyılkan, E., & Jankowski, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01902 · Cited by 2
“Instead of single-step training the networks directly, the proposed multi-step training strategy allows the JSCC models to achieve superior classification accuracy, even with significantly low channel bandwidths (similar to the one discussed in [12]).”
BackgroundSelf-citationTask-Oriented Semantic Communications for Multimodal Data.Preprint
Xie, H., Qin, Z., & Li, G. Y. (2021) · arXiv (Cornell University) · Cited by 4
Progressive Transmission of High-Dimensional Data Features for Inference at the Network Edge
Lan, Q., Zeng, Q., Popovski, P., Gündüz, D., & Huang, K. (2022) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51304.2022.9834000 · Cited by 3
“The key of the former is utilizing an autoencoder architecture, consisting of an encoder for the device and an decoder for the server sub-models, jointly trained to simultaneously perform inference and efficient transmission [4], [5].”
MethodAn End-to-End Channel-Adaptive Feature Compression Approach in Device-Edge Co-Inference Systems
Ouyang, Y., Wang, P., He, L., & Li, F. (2024) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew63481.2024.10645379 · Cited by 1
“However, the emphasis of the aforementioned joint source-channel research is on high-fidelity transmission of source information, which is not entirely aligned with the overall design objectives in our consideration [13].”
BackgroundImage Coding and Compression Method Based on Semantics of Pixels for Semantic Communication
Sun, Q., Guo, C., Tang, R., Liu, C., & Zhang, Y. (2024) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/icccworkshops62562.2024.10693763 · Cited by 1
Goal-Oriented Communications for federated learning in mobile networks
Costafreda, L., & Elayoubi, S. E. (2025) · Global Information Infrastructure and Networking Symposium · doi:10.1109/giis64151.2025.10922012 · Cited by 1
“For the results presented in the sequel, the channel conditions were set for the 8 users to the CQI vector [12 , 10 , 8 , 6 , 12 , 10 , 8 , 6] .”
An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
Wang, S., Li, Z., Huang, X., & Jiang, Q. (2025) · Applied Sciences · doi:10.3390/app15094608 · Cited by 1
“In [20], deep learning-based feature extraction with JSCC is leveraged to achieve efficient image retrieval in edge computing environments.”
Data Sourcing Random Access Using Semantic Queries for Massive IoT Scenarios
Kalør, A. E., Popovski, P., & Huang, K. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3610171 · Cited by 1
“…[15], [16], protocols for edge inference where the goal of the destination is to perform inference on the source [17], [18], [19], and an image transmission scheme that enables the destination to retrieve images from a local database that are similar to the one observed by the transmitter [20].”
On the Effectiveness of Task-Oriented Digital Semantic Communication System
Mao, X., Yan, Q., Dai, B., Tang, X., & Zhou, Z. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3628475 · Cited by 1
“A. Experimental Setup 1) Baselines: We select three task-oriented semantic communication schemes as baselines: DeepJSCC [11], [17], VL-VFE [19], and DT-JSCC [30].”
Wang, Y., Zhang, S., Zhang, A., Dang, S., Zhang, H., & Guo, S. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3618802 · Cited by 1
“For instance, [8] proposed an autoencoder-based semantic communication scheme, by which the features extracted by the encoder are directly used for image retrieval tasks.”
Zheng, Y., Zhang, T., Huang, R., & Wang, Y. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3632162 · Cited by 1
“…image retrieval tasks with DNN can be deployed at the edge to provide recognition service and the corresponding performance needs to be considered [5], and real-time network traffic classification task based on intelligent ensemble classifier requires online real-time traffic classification to improve…”
Abdi, M., Meneghello, F., & Restuccia, F. (2026) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3842721.3849671 · Cited by 1
Multi-User Semantic Communications With Interference-Mitigation Learning
Lee, K., Kim, K., & Yu, N. Y. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3648737 · Cited by 1
“In [1], the authors employed the ResNet as a feature extractor for image semantic transmission.”
Semantic Information Defense and Attack Detection for Consumer Semantic Communication
Guo, J., Cai, D., Khan, Z., Tan, J., Song, T., & LIU, Z. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3655435 · Cited by 2
“Representative examples include semantic compression for image classification [11], person re-identification via semantic distillation [12], edge inference based on the information bottleneck principle [13], and multimodal systems for visual question answering through cross-modal alignment [14].”
Fusion-Aware Unified Semantic Communication for Multimodal AIoT Service
Liu, C.-Y., Chiu, T.-C., & Huang, Y. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432275 · Cited by 1
“[8] presented an image retrieval task, demonstrating strong performance even under power and bandwidth constraints, while Weng et al .”
Ma, Z., Liang, H., Zhang, J., Wei, Z., Jin, X., Li, Z., Zhang, Y. Z., & Han, G. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3684443 · Cited by 1
“…representation space can be flexibly optimized through the JSCC designs according to the specific task requirements, thereby achieving greater adaptability and performance advantages in scenarios such as enhancing human visual perception quality [8] or adapting to downstream vision tasks [9], [10].”
Stable Diffusion-Driven Semantic Coding Method for Image Transmission Under Low SNR Conditions
Liu, S., Lv, R., Yang, Z., Qin, J., & Zhu, Y. (2026) · Electronics · doi:10.3390/electronics15112459 · Cited by 1
Deep-Learning-Based Stream-Sensing Method for Detecting Asynchronous Multiple Signals
Kim, Y., & Lee, H. (2022) · Applied Sciences · doi:10.3390/app12094534 · Cited by 1
Impact Analysis of Emerging Semantic Communication Systems on Network Performance
Lee, H., Ahn, H., & Park, Y. D. (2022) · Electronics · doi:10.3390/electronics11101567 · Cited by 2
Lee, H., Ahn, H., & Park, Y. D. (2022) · ICT Express · doi:10.1016/j.icte.2022.09.002 · Cited by 1
Transformation-Invariant Over-the-Air Combining for Multi-Sensor Wireless Inference
Tegin, B., & Duman, T. M. (2023) · Globecom · doi:10.1109/globecom54140.2023.10436926 · Cited by 1
2021 Index IEEE Journal on Selected Areas in Communications Vol. 39
(2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3132125
An End-to-End Scheme for Learning Over Compressed Data Transmitted Through a Noisy Channel
Tasdighi, A., & Dupraz, E. (2023) · IEEE Access · doi:10.1109/access.2023.3238795
“VAEs are composed of one encoder, which produces a latent vector, and of one decoder, which may either perform data reconstruction [8], [9], [35], [36], [37], [38], [39], or apply some specific learning tasks [40], [41], [42], [43] onto the latent vector.”
BackgroundGoal-Oriented Water-Filling for Dynamic Management of Edge-Assisted OFDM Communications
Binucci, F., & Banelli, P. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278684
“Another interesting way to perform GOCs is represent by Joint Source Channel Coding (JSCC) [11]–[14], where the outputs of specific neural networks (e.g., auto-encoders), are directly mapped on the channel symbols.”
MethodPrecoder and Detector Learning for Vision-based mmWave Received Power Prediction
Guo, J., Bennis, M., & Yang, C. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293875
“In [4], fully-connected neural network (FNN)-based source and channel This work is supported by National Natural Science Foundation of China (NSFC) under Grant 62271024. encoders and decoders (codecs) were trained in an end-to-end (E2E) manner to minimize the retrieval error, with the goal of…”
MethodDeep Learning Enabled Task-Oriented Semantic Communication for Memory-Limited Devices
Deng, H., Wang, W., & Liu, M. (2023) · Mobile Networks and Applications · doi:10.1007/s11036-023-02267-8
“[23] proposed an edge-end collaborative semantic communication method for image retrieval tasks, which greatly improved the performance of image retrieval tasks.”
End-to-End Semantic Information Transmission
Tao, X., Duan, Y., Qin, Z., Huang, D., & Wang, L. (2024) · Wireless networks · doi:10.1007/978-3-031-64155-8_5
Over-the-air multi-sensor inference with neural networks using memristor-based analog computing
Tegin, B., Ali, M. A., & Duman, T. M. (2024) · Physical Communication · doi:10.1016/j.phycom.2024.102582
Joint Channel Estimation and Classification for Task-Oriented Communications
Liu, Z., Shen, H., Xu, W., Jiang, F., Wang, S., Li, M., & Zhao, C. (2024) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp62071.2024.10827081
Remote Inference Over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector QuantizationPreprint
Ben-Knaan, E. F., Malka, M., Shlezinger, N., & Ginzach, S. (2025) · Qeios · doi:10.32388/48lhm4
Learning to compress via robust information bottleneck with digital modulation
Zhou, Y. Q., Zou, Y., Wu, Y., Shi, Y., & Zhang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-322073-9.00017-1
Learning to compress for multi-device cooperative edge inference
Zhou, Y., Zou, Y., Wu, Y., Shi, Y., & Zhang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-322073-9.00018-3
Learning to compress via information bottleneck
Zhou, Y., Zou, Y., Wu, Y., Shi, Y., & Zhang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-322073-9.00016-x
Reinforcement Learning‐Based Unicast and Broadcast Wireless Semantic Communications
Lu, Z., Li, R., Hossain, E., Zhao, Z., & Zhang, H. (2025) · Wiley eBooks · doi:10.1002/9781394247912.ch12
TAHENNI, A., Ouameur, M. A., Bagaa, M., Massicotte, D., de Figueiredo, F. A. P., Ksentini, A., & salmi, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5378489 · Cited by 1
Semantic Communication for Video Surveillance in Railway Intrusion Detection
Guo, J., Chen, W., Sun, Y., Li, Z., & Ai, B. (2025) · IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) · doi:10.1109/icmlcn64995.2025.11140128
“One potential solution is to offload the computational burden to the edge [5].”
Fu, Y., & Zhou, W. G. (2025) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625504821
VocoX: Adversarial Attack Against AI-based Voice Control Services in Semantic Communications
Hoang, V.-T., Nguyen, V.-L., Chang, R., Tangtrongpairoj, W., & Hwang, R. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162263
“The authors of [7] developed a computation framework to categorize pictures and decrease the required bandwidth.”
Federated Multi-Task Semantic Communications With Unified Encoder and Task-Specific Decoders
Huang, Y., Wang, X., & Li, G. Y. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3626558
“This approach has been successfully applied to tasks such as image retrieval [2], speech transmission [3], and image classification [4].”
Wei, X., Wu, D., & Zhou, L. (2025) · Wireless networks · doi:10.1007/978-3-032-00957-9_7
Wei, X., Wu, D., & Zhou, L. (2025) · Wireless networks · doi:10.1007/978-3-032-00957-9_5
Wyner-Ziv Coding for Compression of Large Multimodal Models
Balevi, E. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3639378
“Notice that the transmission details for split inference, including the comparison of analog and digital communication, are discussed in detail, e.g., [44], [45], [46], [47], [48].”
E2E Learning Massive MIMO for Multimodal Semantic Non-Orthogonal Transmission and Fusion
Wu, M., & Gao, Z. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3643817
“Specifically, [22] proposed a model for image retrieval tasks under power and bandwidth constraints, while [23] introduced a robust semantic communication system based on vector quantized variational autoencoders for image classifi-cation.”
Fu, H., Li, Y., Wang, X., Shi, Z., & Yang, G. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-1106-8_18
A Unified Framework for Task-Oriented Communication at Edge AI
Balevi, E. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3650276
“To this end, the image retrieval problem is studied for the digital transmission and JSCC in the context of edge AI [21].”
Ren, H., Jin, R., Liu, J., & Wang, X. (2025) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp68525.2025.1010373
Fang, J., Tang, H. L., Teng, Z., Shi, Z., Wu, S., Zhang, M., & Chen, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3666857
“Jankowski et al. [16] introduced DeepJSCC, which integrates joint source–channel coding with deep learning to enable end-to-end optimized feature transmission.”
InfluentialYan, M., Huang, L., Li, Q., Liu, R., Meng, Z., Tang, W., & Ge, X. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3670165
“Although efforts such as task-oriented JSCC schemes for image retrieval [24], image classification [25], and object detection [26] extend semantic communication to more complex applications, these methods still rely heavily on task-specific customization.”
Wu, Y., Huang, J., Shi, Y., Ma, S., Niu, K., Tao, M., & Letaief, K. B. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3671290 · Cited by 1
“As for wireless communication, without loss of generality, we consider the additive white Gaussian noise (AWGN) channel because of its widespread usage in the existing literature [1], [16], [17].”
Intelligent Computing Oriented Joint Model Deployment and Task Offloading in MEC Systems
Zheng, Y., Zhang, T., Wang, Z., Liu, Y., & Huang, R. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3679675
“These techniques can reduce data transmission and processing requirements while maintaining performance, especially for high-capacity data transfer in MEC systems [8].”
AI models for digital signal processing in future 6G-IoT networks
Larue, G. (2023) · theses.fr (ABES) · doi:10.70675/b70858e5z6800z430dza632z33528def55bb · Cited by 3
Information theory and reinforcement learning of mixed covert and non-covert wireless networks
Bounhar, A. (2024) · theses.fr (ABES) · doi:10.70675/f9afa67bzfc94z4c01z9992za4da7b6e5bd5
Semantic Communication for Machines: A Joint Transmission and Understanding Design
He, Q., Zhang, H., Yu, K., Wu, G., Chen, Z., & Quek, T. Q. S. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3683217
“For example, [21] studied the JSCC-based image retrieval task with frontend edge sensors under restricted wireless links, which largely enhances the end-to-end accuracy compared to the digital separate scheme.”
Lightweight Multitask-Oriented Semantic Communication via Foundational Knowledge Distillation
Liu, C., Teng, S., Zhang, Y., Yuan, L., & Gui, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462510
A Channel Adaptive Encoding and Decoding Method for Unmanned Aerial Vehicle Image Transmission
Zhang, Z., Zhang, S., Qiu, Q., Li, B., Zhang, C., & Shi, G. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3686205
“For the image transmission, Jankowski et al. [37] proposed two alternative schemes based on digital and analog communications.”
A Black-Box Hybrid-Attack for Image Semantic Communication Systems
Ai, K., Cai, D., Obaidat, M. S., Fang, F., & Fan, L. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3688319
“Existing studies on SC systems are broadly divided into two categories: data reconstruction [2], [3], [4], [5] and task-oriented execution [6], [7], [8], [9].”
Emmanuel, D. E., & Fernando, A. (2026) · Research Square · doi:10.21203/rs.3.rs-9542617/v1
Hoang, V.-T., Nguyen, V.-T., & Nguyen, V.-L. (2026) · Physical Communication · doi:10.1016/j.phycom.2026.103204
MAP-Based Task-Oriented Precoding for Multiuser Communication
Ahmadi, M., Zhang, Z., Schaefer, R. F., & Poor, H. V. (2026) · IEEE Communications Letters · doi:10.1109/lcomm.2026.3735912
“As a result, new system designs are required that account for both learning-based feature extraction and channel-aware signal processing in a unified framework [2], [3], [4], [5], [6], [7], [8].”
VerfSemCom: Deep Learning-Driven Verification for Trustworthy Image Semantic Communication
Tian, Z., Wang, W., Chen, L., & Yu, S. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3709187
“Current SemCom methods are largely task-oriented, tailored for specific applications such as image retrieval [7] or classification [8].”
Zhou, J., Yi, Y., & Zhang, Z. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11588294
SemCast: One Representation Semantic Communication for Multi-task Receivers
Yun, S., & Wang, P. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587635
“…added attention mechanisms [4], semantic segmentation [5], bandwidth-adaptive transmission [3], multi-task learning [6], wireless image retrieval [7], and nonlinear transforms [8], and explored variable-rate transmission, unequal error protection, and joint optimization with multiple antennas…”
A Source-Channel Tradeoff in Ultra-Low-Latency Edge Intelligent Sensing
Zeng, Q., Huang, J., Wang, Z., Huang, K., & Leung, K. K. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11588187
“Solutions like feature pruning [6] and joint source-channel coding [7] address this bottleneck but face challenges in adaptability and interoperability with digital techniques.”
LLSC: End-to-End Image Semantic Communication Framework for Low-Light Scenarios
Zhang, K., Xu, D., Lin, W., Guo, J., Li, L., & Han, Z. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11588060
“Multi-user and edge-intelligent systems further demonstrate that semantic compression effectively supports downstream vision tasks under limited bandwidth [13], [14].”
Kong, H., Wang, S., Li, L., Yang, N., & Yin, C. (2026) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops63917.2026.11586287
“And the decoder at the receiver then interprets the latent features to either reconstruct the core semantic information or directly execute a specific task [6].”
Samarathunga, P., Jayasinghe, U., Ganearachchi, Y., Fernando, T., Sivalingam, T., Rajatheva, N., & Fernando, A. (2026) · IEEE Access · doi:10.1109/access.2026.3716070
“Deep JSCC was applied to wireless image retrieval at the edge in [47], showing that task relevant features can be transmitted more efficiently than pixel level reconstructions.”
Multi-TAB: Multi-View Inference at the Edge with Resource-Aware Split Computing
Hassan, T. B., Chan, K. S., Dagefu, F. T., Ashdown, J., Esposito, F., & Restuccia, F. (2026) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom69805.2026.00022
“BottleNet [32] combines an on-device CNN with a JPEG encoder for image classification, while related methods address image retrieval [33], point-cloud analytics [34], and accuracy-preserving neural compression [35].”
Sanjalawe, Y. K., Makhadmeh, S. N., Al-E’mari, S., & Almiani, M. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3722709
Liu, Y., Chen, R., Xu, Y., & Zhou, K. (2026) · Future Internet · doi:10.3390/fi18080429
“A parallel strand re-tains only what a downstream task needs: the DeepSC text system [4] and its lightweight IoT realization [16], the information-bottleneck view of edge inference [17], and edge image retrieval that ships features rather than pixels [18].”
Pyramid-Based Unequal Error Protection for Task-Oriented Deep Joint Source-Channel Coding
Mao, X., Yan, Q., Shao, S., Dai, B., & Tang, X. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11654133
“2) Baselines: We compare UEP-DeepJSCC with four JSCC-based semantic communication schemes: DeepJSCC [3], [20], ADJSCC [4], DT-JSCC [5], and JCM [21].”
RNN–LSTM-assisted entropy-based source–channel coding for robust image transmission
Sankaran, S. V., & Jayaseeli, J. D. D. (2026) · Scientific Reports · doi:10.1038/s41598-026-65390-y
Dai, L., Yang, J., Liu, G., Meng, Y., & Yuan, H. (2026) · Vehicular Communications · doi:10.1016/j.vehcom.2026.101075
Task-Oriented Communication for Edge Inference: A Knowledge-Enhanced Information Bottleneck Approach
Chen, Y., & Sun, Z. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3994-8_14
Ahmadi, H., & Mesin, L. (2026) · Sensors · doi:10.3390/s26185728
“This interpretation is consistent with the paired low-SNR gains and with task-oriented communication studies in other data modalities, where representations optimized for the receiver task retained greater utility under restrictive or noisy links [21,23,24].”
Channel-adaptive semantic token transmission for multimodal edge perception over wireless uplinks
Liao, Y., Zhu, Z., Wu, D., & Wang, R. (2026) · Physical Communication · doi:10.1016/j.phycom.2026.103378
Zhao, W., & Zeng, J. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02208-w
“The first is task-oriented or semantic communication, where a transmitter sends a compact task-relevant representation instead of the raw signal; representative examples include fea-ture-transmission bottlenecks [13] and edge image retrieval over wireless links [14].”
Ioannou, I. I., & Javaid, S. (2026) · Energies · doi:10.3390/en19184444
CSI-Adaptive Semantic DeepJSCC for Bandwidth Efficient 6G Edge Networks
Duru, K. K., Jahnavi, K. V., Gadiparthi, H., Yogita, C. H. S., Sai, P. D. N., & Dodda, V. C. (2026) · IEEE International Conference on Recent Advances in Electronics, Communication, Computing, Automation and Power (RECCAP) · doi:10.1109/reccap69368.2026.11723507
“Here, the transmission process is not geared towards perfect pixel replication, but towards accurate image retrieval [9].”
Metadata
- Authors
- Jankowski, M., Gunduz, D., & Mikolajczyk, K.
- Affiliations
- Imperial College London (GB)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-01
- Volume
- 39
- Issue
- 1
- Pages
- 89-100
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3044258868
- Cited by
- 3
- References
- 44
- Citations by year
- 2025: 2
- FWCI
- 0.10
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Spiral (Imperial College London) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Research Council (ERC) through Starting Grant BEACON (677854)
- U.K. Engineering and Physical Sciences Research Council (EP/N007743/1, EP/S032398/1, EP/T023600/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Data Compression Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- edge computing, joint source-channel coding, fading channels, delay-constrained communication
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.