{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:16:24Z","timestamp":1770740184661,"version":"3.49.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007847","name":"Jilin Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["20250102241JC"],"award-info":[{"award-number":["20250102241JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.eswa.2025.130792","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T16:20:37Z","timestamp":1765556437000},"page":"130792","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mamba - CNN collaborative learning for panoramic semantic segmentation via online knowledge distillation"],"prefix":"10.1016","volume":"304","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0873-7192","authenticated-orcid":false,"given":"Chao","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1825-3345","authenticated-orcid":false,"given":"Jiayue","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3735-0162","authenticated-orcid":false,"given":"Cheng","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8566-1558","authenticated-orcid":false,"given":"Hua","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2025.130792_bib0001","doi-asserted-by":"crossref","unstructured":"Ai, H., Cao, Z., Zhu, J., Bai, H., Chen, Y., & Wang, L. (2022). Deep learning for omnidirectional vision: A survey and new perspectives. 10.48550\/arXiv.2205.10468.","DOI":"10.36227\/techrxiv.19807699"},{"key":"10.1016\/j.eswa.2025.130792_bib0002","unstructured":"Armeni, I., Sax, S., Zamir, A.R., & Savarese, S. (2017). Joint 2d-3d-semantic data for indoor scene understanding. 10.48550\/arxiv.1702.01105."},{"key":"10.1016\/j.eswa.2025.130792_bib0003","doi-asserted-by":"crossref","first-page":"26355","DOI":"10.52202\/079017-0830","article-title":"Geometric exploitation for indoor panoramic semantic segmentation","volume":"37","author":"Cao Dinh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0004","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niessner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017). Matterport3d: Learning from rgb-d data in indoor environments. 10.1109\/3dv.2017.00081.","DOI":"10.1109\/3DV.2017.00081"},{"issue":"5","key":"10.1016\/j.eswa.2025.130792_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2023.03.024","article-title":"3D Mesh classification and panoramic image segmentation using spherical vector networks with rotation-equivariant self-attention mechanism","volume":"35","author":"Chen","year":"2023","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"10.1016\/j.eswa.2025.130792_bib0006","article-title":"Rsmamba: Remote sensing image classification with state space model","author":"Chen","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.eswa.2025.130792_bib0007","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"10.1016\/j.eswa.2025.130792_bib0008","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.1016\/j.eswa.2025.130792_bib0009","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. 10.48550\/arxiv.2010.11929."},{"key":"10.1016\/j.eswa.2025.130792_bib0010","series-title":"Conference on robot learning","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"Dosovitskiy","year":"2017"},{"key":"10.1016\/j.eswa.2025.130792_bib0011","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. 10.48550\/arxiv.2312.00752."},{"key":"10.1016\/j.eswa.2025.130792_bib0012","unstructured":"Gu, A., Goel, K., & R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. 10.48550\/arxiv.2111.00396."},{"key":"10.1016\/j.eswa.2025.130792_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11020","article-title":"Online knowledge distillation via collaborative learning","author":"Guo","year":"2020"},{"key":"10.1016\/j.eswa.2025.130792_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111588","article-title":"Contrastive learning-based knowledge distillation for rgb-thermal urban scene semantic segmentation","volume":"292","author":"Guo","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0015","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"3222","article-title":"Single frame semantic segmentation using multi-modal spherical images","author":"Guttikonda","year":"2024"},{"key":"10.1016\/j.eswa.2025.130792_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6185","article-title":"Neighborhood attention transformer","author":"Hassani","year":"2023"},{"key":"10.1016\/j.eswa.2025.130792_bib0017","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.eswa.2025.130792_bib0018","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.eswa.2025.130792_bib0019","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. 10.48550\/arxiv.1503.02531."},{"key":"10.1016\/j.eswa.2025.130792_bib0020","series-title":"European conference on computer vision","first-page":"148","article-title":"Zigma: A dit-style zigzag mamba diffusion model","author":"Hu","year":"2024"},{"key":"10.1016\/j.eswa.2025.130792_bib0021","series-title":"European conference on computer vision","first-page":"12","article-title":"Localmamba: Visual state space model with windowed selective scan","author":"Huang","year":"2025"},{"key":"10.1016\/j.eswa.2025.130792_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10664","article-title":"Refine myself by teaching myself: Feature refinement via self-knowledge distillation","author":"Ji","year":"2021"},{"key":"10.1016\/j.eswa.2025.130792_bib0023","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.patrec.2024.02.027","article-title":"Channel-spatial knowledge distillation for efficient semantic segmentation","volume":"180","author":"Karine","year":"2024","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.eswa.2025.130792_bib0024","series-title":"2020 25th International conference on pattern recognition (ICPR)","first-page":"4619","article-title":"Feature fusion for online mutual knowledge distillation","author":"Kim","year":"2021"},{"key":"10.1016\/j.eswa.2025.130792_bib0025","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5432","article-title":"Knowledge distillation for efficient instance semantic segmentation with transformers","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2025.130792_bib0026","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, T., Qi, Z., Wang, G., Shan, Y., & Li, X. (2023). Sgat4pass: Spherical geometry-aware transformer for panoramic semantic segmentation. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (pp. 1125\u20131133). 10.24963\/ijcai.2023\/125.","DOI":"10.24963\/ijcai.2023\/125"},{"key":"10.1016\/j.eswa.2025.130792_bib0027","unstructured":"Li, Y., Yang, W., & Fei, B. (2024b). 3dmambacomplete: Exploring structured state space model for point cloud completion. 10.48550\/arxiv.2404.07106."},{"key":"10.1016\/j.eswa.2025.130792_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111956","article-title":"Reliable hybrid knowledge distillation for multi-source domain adaptive object detection","volume":"297","author":"Li","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0029","unstructured":"Liang, D., Zhou, X., Xu, W., Zhu, X., Zou, Z., Ye, X., Tan, X., & Bai, X. (2024). Pointmamba: A simple state space model for point cloud analysis. 10.48550\/arXiv.2402.10739."},{"key":"10.1016\/j.eswa.2025.130792_bib0030","unstructured":"Liao, W., Zhu, Y., Wang, X., Pan, C., Wang, Y., & Ma, L. (2024). Lightm-unet: Mamba assists in lightweight unet for medical image segmentation. 10.48550\/arxiv.2403.05246."},{"key":"10.1016\/j.eswa.2025.130792_bib0031","unstructured":"Liu, J., Yu, R., Wang, Y., Zheng, Y., Deng, T., Ye, W., & Wang, H. (2024a). Point mamba: A novel point cloud backbone based on state space model with octree-based ordering strategy. arXiv: 2403.06467."},{"key":"10.1016\/j.eswa.2025.130792_bib0032","article-title":"TransKD: Transformer knowledge distillation for efficient semantic segmentation","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0033","first-page":"103031","article-title":"Vmamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0034","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.eswa.2025.130792_bib0035","unstructured":"Ma, J., Li, F., & Wang, B. (2024a). U-mamba: Enhancing long-range dependency for biomedical image segmentation. 10.48550\/arxiv.2401.04722."},{"key":"10.1016\/j.eswa.2025.130792_bib0036","article-title":"Rs 3 mamba: Visual state space model for remote sensing image semantic segmentation","author":"Ma","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.eswa.2025.130792_bib0037","doi-asserted-by":"crossref","unstructured":"Ruan, J., Li, J., & Xiang, S. (2024a). Vm-unet: Vision mamba unet for medical image segmentation. 10.48550\/arxiv.2402.02491.","DOI":"10.1145\/3767748"},{"key":"10.1016\/j.eswa.2025.130792_bib0038","doi-asserted-by":"crossref","unstructured":"Ruan, J., Li, J., & Xiang, S. (2024b). Vm-unet: Vision mamba unet for medical image segmentation. 10.48550\/arxiv.2402.02491.","DOI":"10.1145\/3767748"},{"key":"10.1016\/j.eswa.2025.130792_bib0039","series-title":"European conference on computer vision","first-page":"195","article-title":"Panoformer: Panorama transformer for indoor 360\u2218 depth estimation","author":"Shen","year":"2022"},{"key":"10.1016\/j.eswa.2025.130792_bib0040","unstructured":"Smith, J.T.H., Warrington, A., & Linderman, S.W. (2022). Simplified state space layers for sequence modeling. 10.48550\/arxiv.2208.04933."},{"key":"10.1016\/j.eswa.2025.130792_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2573","article-title":"Hohonet: 360 Indoor holistic understanding with latent horizontal features","author":"Sun","year":"2021"},{"key":"10.1016\/j.eswa.2025.130792_bib0042","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"707","article-title":"Distortion-aware convolutional filters for dense prediction in panoramic images","author":"Tateno","year":"2018"},{"key":"10.1016\/j.eswa.2025.130792_bib0043","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"373","article-title":"360Bev: Panoramic semantic mapping for indoor bird\u2019s-eye view","author":"Teng","year":"2024"},{"key":"10.1016\/j.eswa.2025.130792_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16520","article-title":"CrossKD: Cross-head knowledge distillation for object detection","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2025.130792_bib0045","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, J.Q., Zhang, Y., Cui, G., & Li, L. (2024b). Mamba-unet: Unet-like pure visual mamba for medical image segmentation. 10.48550\/arxiv.2402.05079.","DOI":"10.2139\/ssrn.5097998"},{"key":"10.1016\/j.eswa.2025.130792_bib0046","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2025.130792_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102428","article-title":"Compressing convolutional neural networks with cheap convolutions and online distillation","volume":"78","author":"Xie","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.eswa.2025.130792_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1376","article-title":"Capturing omni-range context for omnidirectional segmentation","author":"Yang","year":"2021"},{"key":"10.1016\/j.eswa.2025.130792_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127206","article-title":"Kd-scfnet: Towards more accurate and lightweight salient object detection via knowledge distillation","volume":"572","author":"Zhang","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2025.130792_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16917","article-title":"Bending reality: Distortion-aware transformers for adapting to panoramic semantic segmentation","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2025.130792_bib0051","article-title":"Behind every domain there is a shift: Adapting distortion-aware vision transformers for panoramic semantic segmentation","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2025.130792_bib0052","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10121","article-title":"Point cloud mamba: Point cloud learning via state space model","volume":"39","author":"Zhang","year":"2025"},{"key":"10.1016\/j.eswa.2025.130792_bib0053","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, part VI 13","first-page":"668","article-title":"Panocontext: A whole-room 3d context model for panoramic scene understanding","author":"Zhang","year":"2014"},{"key":"10.1016\/j.eswa.2025.130792_bib0054","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. (pp. 2881\u20132890). 10.1109\/cvpr.2017.660.","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.eswa.2025.130792_bib0055","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"4501","article-title":"Complementary bi-directional feature compression for indoor 360deg semantic segmentation with self-distillation","author":"Zheng","year":"2023"},{"key":"10.1016\/j.eswa.2025.130792_bib0056","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"4501","article-title":"Complementary bi-directional feature compression for indoor 360deg semantic segmentation with self-distillation","author":"Zheng","year":"2023"},{"key":"10.1016\/j.eswa.2025.130792_bib0057","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024a). Vision mamba: Efficient visual representation learning with bidirectional state space model. 10.48550\/arxiv.2401.09417."},{"issue":"19","key":"10.1016\/j.eswa.2025.130792_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e38495","article-title":"Samba: Semantic segmentation of remotely sensed images with state space model","volume":"10","author":"Zhu","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.eswa.2025.130792_bib0059","article-title":"Knowledge distillation by on-the-fly native ensemble","volume":"31","author":"Zhu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425044070?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417425044070?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T03:21:10Z","timestamp":1770088870000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417425044070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":59,"alternative-id":["S0957417425044070"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2025.130792","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mamba - CNN collaborative learning for panoramic semantic segmentation via online knowledge distillation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2025.130792","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"130792"}}