{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:48:05Z","timestamp":1791686885547,"version":"4.3.4"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109431","type":"journal-article","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T19:25:14Z","timestamp":1785698714000},"page":"109431","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["DSF-Net: Dual-strategy fusion for efficient audio-visual sound event localization and detection"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8490-6541","authenticated-orcid":false,"given":"Rendong","family":"Pi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingchao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng-Siong","family":"Chng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9514-9515","authenticated-orcid":false,"given":"Xiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109431_bib0001","unstructured":"Adavanne, S., Parascandolo, G., Pertil\u00e4, P., Heittola, T., & Virtanen, T. (2017). Sound event detection in multichannel audio using spatial and harmonic features. arXiv preprint arXiv: 1706.02293."},{"key":"10.1016\/j.neunet.2026.109431_bib0002","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"8816","article-title":"Fusion of audio and visual embeddings for sound event localization and detection","author":"Berghi","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0003","series-title":"Spoken Language Technology Workshop (SLT)","first-page":"302","article-title":"An investigation of incorporating mamba for speech enhancement","author":"Chao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0004","doi-asserted-by":"crossref","unstructured":"Das, S., Mundra, D., Dayal, P., & Sharma, R. (2026). LweaDT: A light-weight edge-aware distilled transformer for remote sensing image captioning. IEEE Geoscience and Remote Sensing Letters, (pp. 1\u20131). 10.1109\/LGRS.2026.3704222.","DOI":"10.1109\/LGRS.2026.3704222"},{"key":"10.1016\/j.neunet.2026.109431_bib0005","series-title":"2026 International Conference on Wireless Communications Signal Processing and Networking (wiSPNET)","first-page":"1","article-title":"Fd-hsm: Integrating feature diversity and hierarchical semantic modeling for rs image captioning","author":"Das","year":"2026"},{"key":"10.1016\/j.neunet.2026.109431_bib0006","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2026.109431_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18827","article-title":"Collecting cross-modal presence-absence evidence for weakly-supervised audio-visual event perception","author":"Gao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109431_bib0008","series-title":"Ieee Spoken Language Technology Workshop (slt)","first-page":"1","article-title":"Speech-mamba: Long-context speech recognition with selective state spaces models","author":"Gao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0009","first-page":"1","article-title":"Avs-mamba: Exploring temporal and multi-modal mamba for audio-visual segmentation","author":"Gong","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109431_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2024.101148","article-title":"Cnn-lstm based deep learning application on jetson nano: Estimating electrical energy consumption for future smart homes","author":"Gozuoglu","year":"2024","journal-title":"Internet of Things"},{"key":"10.1016\/j.neunet.2026.109431_bib0011","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv: 2312.00752."},{"key":"10.1016\/j.neunet.2026.109431_bib0012","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109431_bib0013","series-title":"International Conference on Learning Representations (ICLR)","article-title":"How to train your HIPPO: State space models with generalized orthogonal basis projections","author":"Gu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109431_bib0014","unstructured":"Hasani, R., Lechner, M., Wang, T.-H., Chahine, M., Amini, A., & Rus, D. (2022). Liquid structural state-space models. arXiv preprint arXiv: 2209.12951."},{"key":"10.1016\/j.neunet.2026.109431_bib0015","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109431_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102779","article-title":"Pan-mamba: Effective pan-sharpening with state space model","volume":"115","author":"He","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109431_bib0017","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.neunet.2020.10.003","article-title":"Dmman: A two-stage audio\u2013visual fusion framework for sound separation and event localization","volume":"133","author":"Hu","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109431_bib0018","series-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops)","article-title":"Av-mamba: Cross-modality selective state space models for audio-visual question answering","author":"Huang","year":"2024"},{"issue":"93","key":"10.1016\/j.neunet.2026.109431_bib0019","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.adn4008","article-title":"Intrinsic sense of touch for intuitive physical human-robot interaction","volume":"9","author":"Iskandar","year":"2024","journal-title":"Science Robotics"},{"key":"10.1016\/j.neunet.2026.109431_bib0020","unstructured":"Jiang, X., Han, C., & Mesgarani, N. (2024a). Dual-path mamba: Short and long-term bidirectional selective structured state space models for speech separation. arXiv preprint arXiv: 2403.18257."},{"key":"10.1016\/j.neunet.2026.109431_bib0021","unstructured":"Jiang, X., Li, Y. A., Florea, A. N., Han, C., & Mesgarani, N. (2024b). Speech slytherin: Examining the performance and efficiency of mamba for speech separation, recognition, and synthesis. arXiv preprint arXiv: 2407.09732."},{"key":"10.1016\/j.neunet.2026.109431_bib0022","article-title":"The distillation system for sound event localization and deteciton of dcase2023 challenge","author":"Kang","year":"2023","journal-title":"Technical Report of DCASE Challenge"},{"key":"10.1016\/j.neunet.2026.109431_bib0023","article-title":"Data augmentation, neural networks, and ensemble methods for sound event localization and detection","author":"Kim","year":"2023","journal-title":"Technical Report of DCASE Challenge"},{"key":"10.1016\/j.neunet.2026.109431_bib0024","series-title":"ACM International Conference on Multimedia (ACM Multimedia, ACM MM)","first-page":"3926","article-title":"Selm: Selective mechanism based audio-visual segmentation","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0025","unstructured":"Li, K., Chen, G., Yang, R., & Hu, X. (2024b). Spmamba: State-space model is all you need in speech separation. arXiv preprint arXiv: 2404.02063."},{"issue":"5","key":"10.1016\/j.neunet.2026.109431_bib0026","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/MSP.2021.3090678","article-title":"Sound event detection: A tutorial","volume":"38","author":"Mesaros","year":"2021","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.neunet.2026.109431_bib0027","doi-asserted-by":"crossref","unstructured":"Miyazaki, K., Masuyama, Y., & Murata, M. (2024). Exploring the capability of mamba in speech applications. arXiv preprint arXiv: 2406.16808.","DOI":"10.21437\/Interspeech.2024-994"},{"key":"10.1016\/j.neunet.2026.109431_bib0028","series-title":"2025\u202fIEEE\/CVF Winter conference on applications of computer vision (WACV)","first-page":"9543","article-title":"Spectformer: Frequency and attention is what you need in a vision transformer","author":"Patro","year":"2025"},{"key":"10.1016\/j.neunet.2026.109431_bib0029","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"367","article-title":"Conformer: Local features coupling global representations for visual recognition","author":"Peng","year":"2021"},{"key":"10.1016\/j.neunet.2026.109431_bib0030","unstructured":"Politis, A., Shimada, K., Sudarsanam, P., Adavanne, S., Krause, D., Koyama, Y., Takahashi, N., Takahashi, S., Mitsufuji, Y., & Virtanen, T. (2022). Starss22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events. arXiv preprint arXiv: 2206.01948."},{"key":"10.1016\/j.neunet.2026.109431_bib0031","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1109\/TASLP.2022.3226330","article-title":"Audio-visual cross-attention network for robotic speaker tracking","volume":"31","author":"Qian","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neunet.2026.109431_bib0032","series-title":"Advances in neural information processing systems (neurIPS)","article-title":"Global filter networks for image classification","author":"Rao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109431_bib0033","unstructured":"Roman, A. S., Balamurugan, B., & Pothuganti, R. (2024a). Enhanced sound event localization and detection in real 360-degree audio-visual soundscapes. arXiv preprint arXiv: 2401.17129."},{"key":"10.1016\/j.neunet.2026.109431_bib0034","series-title":"Icassp 2024 - 2024 ieee international conference on acoustics, speech and signal processing (icassp)","article-title":"Spatial scaper: A library to simulate and augment soundscapes for sound event localization and detection in realistic rooms","author":"Roman","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0035","series-title":"Advances in neural information processing systems","first-page":"72931","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume":"vol. 36","author":"Shimada","year":"2023"},{"key":"10.1016\/j.neunet.2026.109431_bib0036","article-title":"The nerc-slip system for sound event localization and detection of dcase2022 challenge","author":"Wang","year":"2022","journal-title":"DCASE2022 Challenge, Technical Report"},{"key":"10.1016\/j.neunet.2026.109431_bib0037","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1109\/TASLP.2023.3256088","article-title":"A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detection","volume":"31","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neunet.2026.109431_bib0038","series-title":"Communications and networking","first-page":"364","article-title":"Audio-visual sound event localization and detection based on CRNN using depth-wise separable convolution","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0039","series-title":"Communications and networking","first-page":"364","article-title":"Audio-visual sound event localization and detection based on CRNN using depth-wise separable convolution","author":"Wang","year":"2024"},{"issue":"37","key":"10.1016\/j.neunet.2026.109431_bib0040","article-title":"Fusionmamba: Dynamic feature enhancement for multimodal image fusion with mamba","volume":"2","author":"Xie","year":"2024","journal-title":"Visual Intelligence"},{"key":"10.1016\/j.neunet.2026.109431_bib0041","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"1","article-title":"Depmamba: Progressive fusion mamba for multimodal depression detection","author":"Ye","year":"2025"},{"key":"10.1016\/j.neunet.2026.109431_bib0042","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"241","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","author":"Yu","year":"2017"},{"key":"10.1016\/j.neunet.2026.109431_bib0043","unstructured":"Yue, Y., & Li, Z. (2024). Medmamba: Vision mamba for medical image classification. arXiv preprint arXiv: 2403.03849."},{"key":"10.1016\/j.neunet.2026.109431_bib0044","first-page":"1","article-title":"Audio-visual segmentation with semantics","author":"Zhou","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109431_bib0045","series-title":"European Conference on Computer Vision","article-title":"Audio-visual segmentation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neunet.2026.109431_bib0046","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109431_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107152","article-title":"Endpoint-aware audio-visual speech enhancement utilizing dynamic weight modulation based on SNR estimation","volume":"185","author":"Zhu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109431_bib0048","doi-asserted-by":"crossref","unstructured":"Zou, J., Liu, L., Chen, Q., Wang, S., Hu, Z., Xing, X., & Qin, J. (2024). Mmr-mamba: Multi-modal mri reconstruction with mamba and spatial-frequency information fusion. arXiv preprint arXiv: 2406.18950.","DOI":"10.1016\/j.media.2025.103549"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008890?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008890?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:30:50Z","timestamp":1791685850000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":48,"alternative-id":["S0893608026008890"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109431","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DSF-Net: Dual-strategy fusion for efficient audio-visual sound event localization and detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109431","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109431"}}