{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:03:37Z","timestamp":1784203417648,"version":"3.55.0"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005230","name":"Chongqing Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012546","name":"Chongqing Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012546","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":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109050","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:29:08Z","timestamp":1777559348000},"page":"109050","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Non-target divergence hypothesis: Toward understanding modality differences in cross-modal knowledge distillation"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3649-3519","authenticated-orcid":false,"given":"Yilong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1443-0776","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109050_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111854","article-title":"Multi-teacher cross-modal distillation with cooperative deep supervision fusion learning for unimodal segmentation","volume":"297","author":"Ahmad","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109050_bib0002","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9297","article-title":"Semantickitti: A dataset for semantic scene understanding of lidar sequences","author":"Behley","year":"2019"},{"key":"10.1016\/j.neunet.2026.109050_bib0003","series-title":"ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP)","first-page":"721","article-title":"Vggsound: A large-scale audio-visual dataset","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109050_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11766","article-title":"Enhanced multimodal representation learning with cross-modal kd","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109050_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108205","article-title":"Remote sensing object detection through hierarchical feature mining and multivariate head collaboration with knowledge distillation","volume":"195","author":"Chen","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109050_bib0006","unstructured":"Chen, Y., Xu, Z., Zhang, R., Jiang, X., Gao, X. et al. (2024). Foundation model assisted weakly supervised liDAR semantic segmentation. arXiv preprint arXiv: 2404.12861."},{"key":"10.1016\/j.neunet.2026.109050_bib0007","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., & Zhao, F. (2022). Bevdistill: Cross-modal bev distillation for multi-view 3d object detection. arXiv preprint arXiv: 2211.09386."},{"key":"10.1016\/j.neunet.2026.109050_bib0008","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4794","article-title":"On the efficacy of knowledge distillation","author":"Cho","year":"2019"},{"key":"10.1016\/j.neunet.2026.109050_bib0009","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"13053","article-title":"Learning an augmented rgb representation with cross-modal knowledge distillation for action detection","author":"Dai","year":"2021"},{"issue":"2","key":"10.1016\/j.neunet.2026.109050_bib0010","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.1109\/TNNLS.2022.3190166","article-title":"Dual-level knowledge distillation via knowledge alignment and correlation","volume":"35","author":"Ding","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.109050_bib0011","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1109\/LRA.2023.3247175","article-title":"Cekd: Cross-modal edge-privileged knowledge distillation for semantic scene understanding using only thermal images","volume":"8","author":"Feng","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109050_bib0012","series-title":"International conference on machine learning","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"Ganin","year":"2015"},{"key":"10.1016\/j.neunet.2026.109050_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106587","article-title":"Cross-modal knowledge distillation for continuous sign language recognition","volume":"179","author":"Gao","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109050_bib0014","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109050_bib0015","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv: 1503.02531."},{"key":"10.1016\/j.neunet.2026.109050_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16006","article-title":"C2KD: Bridging the modality gap for cross-modal knowledge distillation","author":"Huo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109050_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12977","article-title":"Cross-modal distillation for speaker recognition","volume":"Vol. 37","author":"Jin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109050_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111544","article-title":"Multi-modal hypergraph contrastive learning for medical image segmentation","volume":"165","author":"Jing","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109050_bib0019","series-title":"Rank correlation methods","author":"Kendall","year":"1948"},{"key":"10.1016\/j.neunet.2026.109050_bib0020","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, Y., Hwang, S., Jeong, H., & Kum, D. (2024). Labeldistill: Label-guided cross-modal knowledge distillation for camera-based 3d object detection. arXiv preprint arXiv: 2407.10164.","DOI":"10.1007\/978-3-031-72992-8_2"},{"issue":"1","key":"10.1016\/j.neunet.2026.109050_bib0021","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"The Annals of Mathematical Statistics"},{"issue":"11","key":"10.1016\/j.neunet.2026.109050_bib0022","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.109050_bib0023","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2373","article-title":"Decomposed cross-modal distillation for rgb-based temporal action detection","author":"Lee","year":"2023"},{"key":"10.1016\/j.neunet.2026.109050_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106360","article-title":"Efficient thermal infrared tracking with cross-modal compress distillation","volume":"123","author":"Li","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109050_bib0025","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3351","article-title":"Anisotropic convolutional networks for 3d semantic scene completion","author":"Li","year":"2020"},{"issue":"6","key":"10.1016\/j.neunet.2026.109050_bib0026","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/s00530-025-02061-4","article-title":"Mdikd: Multi-dimensional integration knowledge distillation","volume":"31","author":"Li","year":"2025","journal-title":"Multimedia Systems"},{"issue":"5","key":"10.1016\/j.neunet.2026.109050_bib0027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196391","article-title":"The ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American english","volume":"13","author":"Livingstone","year":"2018","journal-title":"PloS One"},{"issue":"10","key":"10.1016\/j.neunet.2026.109050_bib0028","doi-asserted-by":"crossref","first-page":"5486","DOI":"10.1109\/TCSVT.2023.3257193","article-title":"Using multimodal contrastive knowledge distillation for video-text retrieval","volume":"33","author":"Ma","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109050_bib0029","series-title":"Proceedings eighth IEEE international conference on computer vision. ICCV 2001","first-page":"416","article-title":"A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics","volume":"Vol. 2","author":"Martin","year":"2001"},{"key":"10.1016\/j.neunet.2026.109050_bib0030","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5191","article-title":"Improved knowledge distillation via teacher assistant","volume":"Vol. 34","author":"Mirzadeh","year":"2020"},{"key":"10.1016\/j.neunet.2026.109050_bib0031","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"595","article-title":"Let me show you how it\u2019s done-cross-modal knowledge distillation as pretext task for semantic segmentation","author":"Nair","year":"2024"},{"key":"10.1016\/j.neunet.2026.109050_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3967","article-title":"Relational knowledge distillation","author":"Park","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2026.109050_bib0033","first-page":"5","article-title":"Probabilistic knowledge transfer for deep representation learning","volume":"1","author":"Passalis","year":"2018","journal-title":"CoRR, abs\/1803.10837"},{"key":"10.1016\/j.neunet.2026.109050_bib0034","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109050_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16773","article-title":"Co-advise: Cross inductive bias distillation","author":"Ren","year":"2022"},{"key":"10.1016\/j.neunet.2026.109050_bib0036","unstructured":"Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014). Fitnets: Hints for thin deep nets. arXiv preprint arXiv: 1412.6550."},{"key":"10.1016\/j.neunet.2026.109050_bib0037","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"14875","article-title":"Xkd: Cross-modal knowledge distillation with domain alignment for video representation learning","volume":"Vol. 38","author":"Sarkar","year":"2024"},{"key":"10.1016\/j.neunet.2026.109050_bib0038","series-title":"Computer vision\u2013ECCV 2012: 12th European conference on computer vision, Florence, Italy, October 7\u201313, 2012, Proceedings, Part V 12","first-page":"746","article-title":"Indoor segmentation and support inference from rgbd images","author":"Silberman","year":"2012"},{"issue":"12","key":"10.1016\/j.neunet.2026.109050_bib0039","doi-asserted-by":"crossref","first-page":"11059","DOI":"10.1109\/TPAMI.2024.3451658","article-title":"Uni-to-multi modal knowledge distillation for bidirectional liDAR-camera semantic segmentation","volume":"46","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109050_bib0040","unstructured":"Tang, J., Shivanna, R., Zhao, Z., Lin, D., Singh, A., Chi, E. H., & Jain, S. (2020). Understanding and improving knowledge distillation. arXiv preprint arXiv: 2002.03532."},{"key":"10.1016\/j.neunet.2026.109050_bib0041","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2019). Contrastive representation distillation. arXiv preprint arXiv: 1910.10699."},{"key":"10.1016\/j.neunet.2026.109050_bib0042","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1365","article-title":"Similarity-preserving knowledge distillation","author":"Tung","year":"2019"},{"issue":"5","key":"10.1016\/j.neunet.2026.109050_bib0043","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1109\/72.788640","article-title":"An overview of statistical learning theory","volume":"10","author":"Vapnik","year":"1999","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/j.neunet.2026.109050_bib0044","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"216","article-title":"Learnable cross-modal knowledge distillation for multi-modal learning with missing modality","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109050_bib0045","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10377","article-title":"DistilVPR: Cross-modal knowledge distillation for visual place recognition","volume":"vol. 38","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109050_bib0046","first-page":"1","article-title":"Cross-modal graph knowledge representation and distillation learning for land cover classification","volume":"61","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109050_bib0047","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.1109\/TCSS.2024.3402270","article-title":"Zero-shot cross-lingual knowledge transfer in VQA via multimodal distillation","volume":"12","author":"Weng","year":"2025","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"10.1016\/j.neunet.2026.109050_bib0048","first-page":"5105","article-title":"Feature importance ranking for deep learning","volume":"33","author":"Wojtas","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109050_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108180","article-title":"A multi-level teacher assistant-based knowledge distillation framework with dynamic feedback for motor imagery EEG decoding","volume":"194","author":"Wu","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109050_bib0050","series-title":"ICLR","article-title":"The modality focusing hypothesis: Towards understanding crossmodal knowledge distillation","author":"Xue","year":"2023"},{"key":"10.1016\/j.neunet.2026.109050_bib0051","series-title":"European conference on computer vision","first-page":"677","article-title":"2dpass: 2d priors assisted semantic segmentation on lidar point clouds","author":"Yan","year":"2022"},{"key":"10.1016\/j.neunet.2026.109050_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103841","article-title":"Saliency-aware multi-resolution graph fusion via self-supervised contrastive learning for robust ultrasound endometrial cancer diagnosis","volume":"127","author":"Yang","year":"2026","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109050_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111351","article-title":"Cross-modal knowledge transfer for 3d point clouds via graph offset prediction","volume":"162","author":"Zhang","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109050_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107838","article-title":"ShiftKD: Benchmarking knowledge distillation under distribution shift","volume":"192","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109050_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108833","article-title":"Visual-to-EEG cross-modal knowledge distillation for continuous emotion recognition","volume":"130","author":"Zhang","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109050_bib0056","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11953","article-title":"Decoupled knowledge distillation","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109050_bib0057","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"16280","article-title":"Perception-aware multi-sensor fusion for 3d lidar semantic segmentation","author":"Zhuang","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005101?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005101?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:10:13Z","timestamp":1784200213000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":57,"alternative-id":["S0893608026005101"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109050","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Non-target divergence hypothesis: Toward understanding modality differences in cross-modal knowledge distillation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109050","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":"109050"}}