Spectrum Anomaly Detection: A Deep Learning Approach

Document Type : Special Issue

Authors

Motahareh Aghalari ¹

Hossein Khaleghi Bizaki ²

¹ Malek-Ashtar University of Technology, Tehran, Iran

² Malek Ashtar University of Technology

10.22067/cke.2025.91456.1144

Abstract

The frequency spectrum is a limited and valuable resource and faces challenges due to anomalies. Hence, the detection of anomalies in the frequency spectrum is crucial for maintaining the integrity and reliability of telecommunication systems. These anomalies, which include jamming signals and interference, can disrupt communication channels and degrade system performance. This paper presents a comprehensive review of deep learning applications in spectrum anomaly detection, focusing on research conducted between 2017 and 2024. The review examines various pre-processing techniques used in spectrum anomaly detection, highlighting the widespread use of spectrogram and short-time Fourier transform (STFT), particularly in reconstruction-based methods, due to their effectiveness in capturing time-frequency information despite their computational challenges. Additionally, the study underscores the importance of selecting appropriate problem-solving approaches, such as classification, segmentation, or object detection, and tailoring models to suit specific tasks. These findings underscore the potential of deep learning-based approaches in enhancing spectrum monitoring and interference management.

Keywords

Anomaly

Deep learning

Interference

Spectrum

Subjects

• Special Issues

---

References

[1]  Y. Zhang & Z. Luo. (2023). A review of research on spectrum sensing based on deep learning. Electronics. [Online]. 12(21), p. 4514. Available: https://doi.org/10.3390/electronics12214514

[2]  Y. Molina‑Tenorio, A. Prieto‑Guerrero, R. Aguilar‑Gonzalez, & S. Ruiz‑Boqué. (2019). Machine learning techniques applied to multiband spectrum sensing in cognitive radios. Sensors. [Online]. 19(21), p. 4715. Available: https://doi.org/10.3390/s19214715

[3]  V. Chandola, A. Banerjee, & V. Kumar. (2009). Anomaly detection: A survey. ACM Computing Surveys (CSUR). [Online]. 41(3), pp. 1–58. Available: https://doi.org/10.1145/1541880.1541882

[4]  Z. Yang & R. J. Radke, “Context‑aware video anomaly detection in long‑term datasets,” In Proceeding IEEE/CVF Conference computer vision and pattern recognition (cvpr), 2024, pp. 4002–4011. Available: https://doi.org/10.1109/CVPR52733.2024.00372

[5]  Y. Sreeraman, D. Jagadeesan, J. Jegan, T. Vivekanandan, A. Srinivasan, & G. Asha. (2024). Enhancing anomaly detection in pedestrian walkways using improved sparrow search algorithm with parallel features fusion model. Fusion: Practice & Applications. [Online]. 14(2), pp. 119–131. Available: https://doi.org/10.54216/FPA.140210

[6]  S. N. Chary & V. Ganesan, "Detection of abnormal events using deep learning in pedestrian walkways," In G. H. L. Gururaj, F. Flammini, S. Srividhya, M. L. Chayadevi, & S. Selvam (Eds.), Computer Science Engineering: Proceedings of First International Conference on Information and Communication Technology for Intelligent Systems (ICCIIS 2024), Bengaluru, India: CRC Press, 2024, pp. 299–306.

[7]  P. Bonte, S. K. Hashemi, H. Hellbruck, and F. Jondral, “Unsupervised anomaly detection for communication networks: an autoencoder approach,” in Proceeding International Workshop IoT, Edge, and Mobile for Embedded Machine Learning, Cham, Switzerland: Springer, 2020, pp. 160–172. Available: https://doi.org/10.1007/978-3-030-66770-2_12

[8]  B. Lindemann, B. Maschler, N. Sahlab, & M. Weyrich. (2021). A survey on anomaly detection for technical systems using LSTM networks. Computers in Industry. [Online]. 131, p. 103498. Available: https://doi.org/10.1016/j.compind.2021.103498

[9]  T.-Y. Kim & S.-B. Cho. (2018). Web traffic anomaly detection using C‑LSTM neural networks. Expert Systems with Applications. [Online]. 106, pp. 66–76. Available: https://doi.org/10.1016/j.eswa.2018.04.004

[10] J. S. Mambou, “Classification framework for anomaly detection in medical images,” Ph.D. dissertation, Faculty of Informatics and Management, Univ. of Hradec Králové, Hradec Králové, Czech Republic, 2021. [Online]. Available: https://theses.cz/id/34y9tk

[11]  C. Baur, B. Wiestler, M. Muehlau, C. Zimmer, N. Navab, & S. Albarqouni. (2021). Modeling healthy anatomy with artificial intelligence for unsupervised anomaly detection in brain MRI. Radiology: Artificial Intelligence. [Online]. 3(3), p. e190169. Available: https://doi.org/10.1148/ryai.2020190169

[12]         P. Qi, T. Jiang, J. Xu, J. He, S. Zheng, & Z. Li. (2024). Unsupervised spectrum anomaly detection with distillation and memory‑enhanced autoencoders. IEEE Internet of Things Journal. [Online]. 11(24), pp. 39361–39374. Available: https://doi.org/10.1109/JIOT.2024.3424837

[13] S. Rajendran, W. Meert, V. Lenders, & S. Pollin. (2019). Unsupervised wireless spectrum anomaly detection with interpretable features. IEEE Transactions on Cognitive Communications and Networking. [Online]. 5(3), pp. 637–647. Available: https://doi.org/10.1109/TCCN.2019.2911524

[14] M. Khaleel, A. Jebrel, & D. M. Shwehdy. (2024). Artificial intelligence in computer science. International Journal of Electrical Engineering and Sustainability. [Online]. pp. 01–21. Available: https://doi.org/10.5281/zenodo.10937515

[15] Z. Zamanzadeh Darban, G. I. Webb, S. Pan, C. Aggarwal, & M. Salehi. (2024). Deep learning for time series anomaly detection: A survey. ACM Computing Surveys. [Online]. 57(1), pp. 1–42. Available: https://doi.org/10.1145/3625506

[16] D. Fährmann, L. Martín, L. Sánchez, & N. Damer. (2024). Anomaly detection in smart environments: A comprehensive survey. IEEE Access. [Online]. 12, 64006–64049. Available: https://doi.org/10.1109/ACCESS.2024.3402107

[17] M. Rahmani & R. Ghazizadeh. (2022). Spectrum monitoring based on end‑to‑end learning by deep learning. International Journal of Wireless Information Networks. [Online]. 29(2), 180–192. Available: https://doi.org/10.1007/s10776-021-00530-4

[18] M. Kulin, T. Kazaz, I. Moerman, & E. De Poorter. (2018). End‑to‑end learning from spectrum data: A deep learning approach for wireless signal identification in spectrum monitoring applications. IEEE Access. [Online]. 6, 18484–18501. Available: https://doi.org/10.1109/ACCESS.2018.2818794

[19] F. A. Bhatti, M. J. Khan, A. Selim, & F. Paisana. (2021). Shared spectrum monitoring using deep learning. IEEE Transactions on Cognitive Communications and Networking. [Online]. 7(4), pp. 1171–1185. Available: https://doi.org/10.1109/TCCN.2021.3071149

[20]         A. Selim, F. Paisana, J. A. Arokkiam, Y. Zhang, L. Doyle, and L. A. DaSilva, “Spectrum Monitoring for Radar Bands Using Deep Convolutional Neural Networks,” in Proceeding 2017 IEEE Global Communications Conference, GLOBECOM, Singapore, 2017, pp. 1-6. https://doi.org/10.1109/GLOCOM.2017.8254105

[21] C. Hou, D. Fu, Z. Zhou, & X. Wu. (2023). A deep learning‑based multi‑signal radio spectrum monitoring method for UAV communication. Drones. [Online]. 7(8), p. 511. Available: https://doi.org/10.3390/drones7080511

[22]H. Pirayesh & H. Zeng. (2022). Jamming attacks and anti‑jamming strategies in wireless networks: A comprehensive survey. IEEE Communications Surveys & Tutorials. [Online]. 24(2), pp. 767–809. 2022. Available: https://doi.org/10.1109/COMST.2022.3159185

[23] P. Lohan, B. Kantarci, M. A. Ferrag, N. Tihanyi, & Y. Shi. (2024). From 5G to 6G networks: A survey on AI‑based jamming and interference detection and mitigation. IEEE Open Journal of the Communications Society. [Online]. 5, pp. 3920–3974. Available: https://doi.org/10.1109/OJCOMS.2024.3416808

[24] T. Oyedare, V. K. Shah, D. J. Jakubisin, & J. H. Reed. (2022). Interference suppression using deep learning: Current approaches and open challenges. IEEE Access. [Online]. 10, pp. 66238–66266. Available: https://doi.org/10.1109/ACCESS.2022.3185124

[25] A. Lancho, J. Palacios, M. Selim, L. González, A. Krause, P. Casari, & X. Costa‑Pérez. (2025). RF Challenge: The data‑driven radio frequency signal separation challenge. IEEE Open Journal of the Communications Society. [Online]. 6, pp. 4083–4100. Available: https://doi.org/10.22067/cke.2025.91456.1144

[26] X. Yang, A. Li, M. Wei, X. Zhang, S. Lu, and W. Wang, “Jamming Signal Detection Based on TSVD Method,” in IEEE International Conference on Advances in Electrical Engineering and Computer Applications( AEECA), Dalian, China, 2020, pp. 558-562.

[27] R. Morales Ferre, A. De La Fuente, & E. S. Lohan. (2019). Jammer classification in GNSS bands via machine learning algorithms. Sensors. [Online]. 19(22), p. 4841. Available: https://doi.org/10.3390/s19224841

[28] M. Liu, Z. Liu, W. Lu, Y. Chen, X. Gao, & N. Zhao. (2021). Distributed few‑shot learning for intelligent recognition of communication jamming. IEEE Journal of Selected Topics in Signal Processing. [Online]. 16(3), pp. 395–405. Available: https://doi.org/10.1109/JSTSP.2021.3137028

[29] Y. Huang, S. Yuan, N. Liu, Q. Li, W. Liang, & L. Liu. (2023). Unsupervised interpolation recovery method for spectrum anomaly detection and localization. Space: Science & Technology. [Online]. 3, p. 0082. Available: https://doi.org/10.34133/space.0082

[30] S. Hong, K. Kim, & S.-H. Lee. (2023). A hybrid jamming detection algorithm for wireless communications: Simultaneous classification of known attacks and detection of unknown attacks. IEEE Communications Letters. [Online]. 27(7), pp. 1769–1773. Available: https://doi.org/10.1109/LCOMM.2023.3275694

[31]M. Zhou, M. Kong, Y. Ye, B. Deng, & Y. Tang. (2024). Identifying sources of interference in civil aviation radio communication. EURASIP Journal on Advances in Signal Processing. [Online]. (1), p. 88. Available: https://doi.org/10.1186/s13634-024-01185-5

[32] X. Zhou, J. Xiong, X. Zhang, X. Liu, & J. Wei. (2021). A radio anomaly detection algorithm based on modified generative adversarial network. IEEE Wireless Communications Letters. [Online]. 10(7), pp. 1552–1556. Available: https://doi.org/10.1109/LWC.2021.3079899

[33]  K. Cohen & Q. Zhao. (2015). Active hypothesis testing for anomaly detection. IEEE Transactions on Information Theory. [Online]. 61(3), pp. 1432–1450. Available: https://doi.org/10.1109/TIT.2014.2371464

[34] M. Aghalari, A. Aghagolzadeh, & M. Ezoji. (2021). Brain tumor image segmentation via asymmetric/symmetric U‑Net based on two‑pathway‑residual blocks. Biomedical Signal Processing and Control. [Online]. 69, p. 102841. https://doi.org/10.1016/j.bspc.2021.102841

[35] M. Aghalari & H. K. Bizaki. (2025). Enhancing of polyp image segmentation in colonoscopy images: A comprehensive approach using modified U‑Net, hybrid color space, and ensemble learning. Multimedia Tools and Applications. [Online]. 84(17), pp. 17491–17516. Available: https://doi.org/10.1007/s11042-024-19703-w

[36] M. U. Muzaffar & R. Sharqi. (2024). A review of spectrum sensing in modern cognitive radio networks. Telecommunication Systems. [Online]. 85(2), pp.347–363. Available: https://doi.org/10.1007/s11235-023-01079-1

[37] S. Peng, S. Sun, & Y.-D. Yao. (2021). A survey of modulation classification using deep learning: Signal representation and data preprocessing. IEEE Transactions on Neural Networks and Learning Systems. [Online]. 33(12), 7020–7038. Available: https://doi.org/10.1109/TNNLS.2021.3085433

[38]O. V. Ribeiro‑Filho, M. A. Ponti, M. Curilem, & R. A. Rios. (2025). Integrating wavelet transformation for end‑to‑end direct signal classification. Digital Signal Processing. [Online]. 156, p. 104878. Available: https://doi.org/10.1016/j.dsp.2024.104878

[39]  F. R. Guimarães, J. M. B. da Silva, Jr., C. C. Cavalcante, G. Fodor, M. Bengtsson, & C. Fischione. (2024). Machine learning for spectrum sharing: A survey. Foundations and Trends in Networking. [Online]. 14(1–2), pp. 1–159. Available: https://doi.org/10.1561/1300000073

[40] K. Davaslioglu, S. Soltani, T. Erpek, & Y. E. Sagduyu. (2021). DeepWiFi: Cognitive WiFi with deep learning. IEEE Transactions on Mobile Computing. [Online]. 20(2), pp. 429–444. Available: https://doi.org/10.1109/TMC.2019.2949815

[41] H. Xu et al. (2022). A neural network approach for wireless spectrum anomaly detection in 5G‑unlicensed network. CCF Transactions on Pervasive Computing and Interaction. [Online]. 4(4), pp. 465–473. Available:  https://doi.org/10.1007/s42486-021-00075-1

[42] A. Reda, T. Mekkawy, T. A. Tsiftsis, & A. Mahran. (2024). Deep learning approach for GNSS jamming detection based on PCA and Bayesian optimization feature selection algorithm. IEEE Transactions on Aerospace and Electronic Systems. [Online]. 60(6), pp. 8349–8363. Available: https://doi.org/10.1109/TAES.2024.3429049

[43] C. Natalino, A. Udalcovs, L. Wosinska, O. Ozolins, & M. Furdek. (2021). Spectrum anomaly detection for optical network monitoring using deep unsupervised learning. IEEE Communications Letters. [Online]. 25(5), pp. 1583–1586. Available: https://doi.org/10.1109/LCOMM.2021.3055064

[44] S. Peng, H. Jiang, H. Wang, H. Alwageed, and Y.-D. Yao, “Modulation Classification Using Convolutional Neural Network Based Deep Learning Model,” in 26th Wireless and Optical Communication Conference (WOCC), Newark, NJ, USA, 2017, pp. 1-5. Available: https://doi.org/10.1109/WOCC.2017.7929000

 [45] C. Peng, W. Hu, & L. Wang. (2022). Spectrum anomaly detection based on spatio‑temporal network prediction. Electronics. [Online]. 11(11), p. 1770. Available: https://doi.org/10.3390/electronics11111770

[46] S. Ujan, N. Navidi, & R. Landry, Jr. (2020). An efficient radio frequency interference (RFI) recognition and characterization using end‑to‑end transfer learning. Applied Sciences. [Online]. 10(19), p. 6885. Available: https://doi.org/10.3390/app10196885

[47] N. Manakitsa, G. S. Maraslidis, L. Moysis, & G. F. Fragulis. (2024). A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision. Technologies. [Online]. 12(2), p. 15p. Available: https://doi.org/10.3390/technologies12020015

[48] K. Tekbıyık, Ö. Akbunar, A. R. Ekti, A. Görçin, G. K. Kurt, & K. A. Qaraqe. (2021). Spectrum sensing and signal identification with deep learning based on spectral correlation function. IEEE Transactions on Vehicular Technology. [Online]. 70(10), pp. 10514–10527. Available: https://doi.org/10.1109/TVT.2021.3108184

[49] R. Liu, Q. Zhang, Y. Zhang, and C. Ma, “An Improved Wireless Spectrum Anomaly Detection Model with Adaptive Attention Mechanism,” in Proc. 2024 8th International Conference on Control Engineering and Artificial Intelligenc, Shanghai, China, 2024, pp. 79-84. Available: https://doi.org/10.1145/3640824.3640836

[50] Q. Feng, Y. Zhang, C. Li, Z. Dou, & J. Wang. (2017). Anomaly detection of spectrum in wireless communication via deep auto‑encoders. The Journal of Supercomputing. [Online]. 73(7), pp. 3161–3178. https://doi.org/10.1007/s11227-017-2017-7

[51] J. Kim, H. Kim, B. Kim, & S. Choi. (2024). Wireless anomaly signal dataset (WASD): An open dataset for wireless cellular spectrum monitoring and anomaly detection. IEEE Access. [Online]. 12, pp. 196240–196248. Available: https://doi.org/10.1109/ACCESS.2024.3521946

[52] J. Steiner & J. Pešík. (2024). Machine learning image recognition for GNSS jamming signals categorization. Neural Network World. [Online]. 34(6), pp. 341–360.

[53] M. Jiang, Z. Ye, Y. Xiao, and X. Gou, “Federated Transfer Learning Aided Interference Classification in GNSS Signals,” in IEEE/CIC International Conference on Communications China (ICCC), Hangzhou, China, Aug. 2024, pp. 1988-1993. Available: https://doi.org/10.1109/ICCC62479.2024.10681801

[54] C. J. Swinney and J. C. Woods, “GNSS Jamming Clustering Using Unsupervised Learning and Radio Frequency Signals,” in Proceeding International Conference Cybersecurity, Situational Awareness Social Media (ICCSSA), Cyber Science, C. Onwubiko, P. Rosati, A. Rege, A. Erola, X. Bellekens, H. Hindy, and M. G. Jaatun, Eds. Copenhagen, Denmark: Springer, 2023, pp. 25-34. Available: https://doi.org/10.1007/978-981-99-6974-6_2

[55] J. Qin, F. Zhang, K. Wang, Y. Zuo, & C. Deng. (2022). Interference signal feature extraction and pattern classification algorithm based on deep learning. Electronics. [Online]. 11(14), p. 2251. Available: https://doi.org/10.3390/electronics11142251

[56] O. Özhan. (2022). Short‑time Fourier transform. In Basic Transforms for Electrical Engineering. Cham, Switzerland: Springer, 2022, pp. 441–464. Available: https://doi.org/10.1007/978-3-030-98846-3_7

[57] National Instruments, “STFT Spectrograms VI,” LabVIEW API Ref., 2024. [Online]. Available: https://www.ni.com/docs/en-US/bundle/labview-api-ref/page/vi-lib/gmath/trans-llb/stft-spectrograms-vi.html

[58] A. Toma, A. Krayani, L. Marcenaro, Y. Gao, and C. S. Regazzoni, “Deep Learning for Spectrum Anomaly Detection in Cognitive mmWave Radios,” in IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, London, U.K., 2020, pp. 1-7. Available: https://doi.org/10.1109/PIMRC48278.2020.9217240

[59] M. Chitgarha, A. Bozorgchenani, & M. J. Dehghani. (2017). On time compression overlap‑add technique in linear frequency modulation pulse compression radar systems: Design and performance evaluation. IEEE Access. [Online]. 5, pp. 27525–27537. Available: https://doi.org/10.1109/ACCESS.2017.2771799

 [60] M. Priyadarshini, M. Bajaj, L. Prokop, & M. Berhanu. (2024). Perception of power quality disturbances using Fourier, short‑time Fourier, continuous and discrete wavelet transforms. Scientific Reports. [Online]. 14(1), p. 3443. Available: https://doi.org/10.1038/s41598-024-53792-9

[61] P. N. Portela, “Improving speech prosody assessment through artificial intelligence,” M.S. thesis, Fac. Eng., Univ. of Porto, Porto, Portugal, Oct. 2024.

[62] S. Ujan, N. Navidi, & R. Landry, Jr. (2020). Hierarchical classification method for radio frequency interference recognition and characterization in Satcom. Applied Sciences. [Online]. 10(13), p. 4608. Available: https://doi.org/10.3390/app10134608

[63] N. El‑haryqy, Z. Madini, & Y. Zouine. (2024). Radio frequency interference detection and automatic modulation recognition based on Mask RCNN. International Journal of Computer Networks and Communications. [Online]. 16(5), pp. 23–42.

[64] J. Y. Chen & B. Z. Li. (2024). The short‑time Wigner–Ville distribution. Signal Processing. [Online]. 219, p. 109402. Available: https://doi.org/10.1016/j.sigpro.2024.109402

[65] T. Kuang, B. Zhou, J. Li, G. Ding, & Q. Wu. (2022). Abnormal communication signals recognition based on image enhancement and improved memory‑augmented autoencoder. Wireless Communications and Mobile Computing. [Online]. 2022, p. 7228511. Available: https://doi.org/10.1155/2022/7228511

[66] J. Zeng, X. Liu, & Z. Li. (2023). Radio anomaly detection based on improved denoising diffusion probabilistic models. IEEE Communications Letters. [Online]. 27(8), pp. 1979–1983. Available: https://doi.org/10.1109/LCOMM.2023.3290813

[67] K. Simonyan & A. Zisserman. (2014). Very deep convolutional networks for large‑scale image recognition. arXiv preprint arXiv:1409.1556. [Online]. Available: https://arxiv.org/abs/1409.1556

[68] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778.

[69] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, & K. Keutzer. (2016). SqueezeNet: AlexNet‑level accuracy with 50× fewer parameters and <0.5 MB model size. arXiv preprint arXiv:1602.07360. [Online]. Available: https://arxiv.org/abs/1602.07360

[70] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Columbus, OH, USA, 2014, pp. 580-587.

[71] R. Girshick. (2015). Fast R‑CNN. arXiv preprint arXiv:1504.08083. [Online]. Available: https://arxiv.org/abs/1504.08083

[72] S. Ren, K. He, R. Girshick, & J. Sun. (2017). Faster R‑CNN: Towards real‑time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. [Online]. 39(6), pp. 1130–1144. Available: https://doi.org/10.1109/TPAMI.2016.2577031

[73] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 2016, pp. 779-788.

[74] C. Liu, Y. Tao, J. Liang, K. Li, and Y. Chen, “Object Detection Based on YOLO Network,” in IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2018, pp. 799-803. https://doi.org/10.1109/ITOEC.2018.8740604

[75]  T. Diwan, G. Anirudh, & J. V. Tembhurne. (2023). Object detection using YOLO: Challenges, architectural successors, datasets and applications. Multimedia Tools and Applications. [Online]. 82(6), 9243–9275. Available: https://doi.org/10.1007/s11042-022-13644-y

[76] C. I. Bercea, D. Rueckert, and J. A. Schnabel, “What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection,” in Proc. Int. Medical Image Computing and Computer Assisted Intervention (MICCAI), Vancouver, BC, Canada, 2023, pp. 304-314. Available: https://doi.org/10.1007/978-3-031-43904-9_30

[77] K. Berahmand, F. Daneshfar, E. S. Salehi, Y. Li, & Y. Xu. (2024). Autoencoders and their applications in machine learning: A survey. Artificial Intelligence Review. [Online]. 57(2), p. 28. Available: https://doi.org/10.1007/s10462-023-10692-0

 [78] M. Schmidt, D. Block, and U. Meier, “Wireless Interference Identification With Convolutional Neural Networks,” in IEEE 15th IEEE 15th International Conference on Industrial Informatics  (INDIN), Emden, Germany, 2017, pp. 180-185. Available: https://doi.org/10.1109/INDIN.2017.8104767

[79] C. Szegedy et al., “Going deeper with convolutions,” in Proceeding IEEE conference on computer vision and pattern recognition (CVPR), 2015, pp. 1-9.

[80]  Y. Zhu and S. Newsam, “Densenet for dense flow,” in IEEE international conference on image processing (ICIP), 2017, pp. 790-794. Available: https://doi.org/10.1109/ICIP.2017.8296389