{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:22:49Z","timestamp":1783113769471,"version":"3.54.6"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L257022"],"award-info":[{"award-number":["L257022"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441232"],"award-info":[{"award-number":["62441232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.115128","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T06:46:54Z","timestamp":1779259614000},"page":"115128","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Progressive knowledge evolution under multi-granularity knowledge distillation for infrared action recognition"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4355-3169","authenticated-orcid":false,"given":"Xiaochen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7722-7172","authenticated-orcid":false,"given":"Dehui","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5583-8260","authenticated-orcid":false,"given":"Jinghua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7962-4091","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115128_b1","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1109\/TMM.2021.3050069","article-title":"Infrared action detection in the dark via cross-stream attention mechanism","volume":"24","author":"Chen","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115128_b2","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1109\/TMM.2024.3521718","article-title":"Vision-language meets the skeleton: Progressively distillation with cross-modal knowledge for 3D action representation learning","volume":"27","author":"Chen","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115128_b3","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"388","article-title":"TherISuRNet - a computationally efficient thermal image super-resolution network","author":"Chudasama","year":"2020"},{"key":"10.1016\/j.engappai.2026.115128_b4","first-page":"1","article-title":"Diffusion-based continuous feature representation for infrared small-dim target detection","volume":"62","author":"Fan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.engappai.2026.115128_b5","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4729","article-title":"3D CNNs with adaptive temporal feature resolutions","author":"Fayyaz","year":"2021"},{"issue":"6","key":"10.1016\/j.engappai.2026.115128_b6","doi-asserted-by":"crossref","first-page":"4377","DOI":"10.1109\/TPAMI.2025.3543211","article-title":"Shared growth of graph neural networks via prompted free-direction knowledge distillation","volume":"47","author":"Feng","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115128_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104469","article-title":"MDJ: A multi-scale difference joint keyframe extraction algorithm for infrared surveillance video action recognition","volume":"148","author":"Feng","year":"2024","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.engappai.2026.115128_b8","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.neucom.2016.05.094","article-title":"InfAR dataset: Infrared action recognition at different times","volume":"212","author":"Gao","year":"2016","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.engappai.2026.115128_b9","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1109\/TCDS.2022.3232569","article-title":"Channel-correlation-based selective knowledge distillation","volume":"15","author":"Gou","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.engappai.2026.115128_b10","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"5461","article-title":"Motion matters: Motion-guided modulation network for skeleton-based micro-action recognition","author":"Gu","year":"2025"},{"issue":"7","key":"10.1016\/j.engappai.2026.115128_b11","doi-asserted-by":"crossref","first-page":"6238","DOI":"10.1109\/TCSVT.2024.3358415","article-title":"Benchmarking micro-action recognition: Dataset, methods, and applications","volume":"34","author":"Guo","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.115128_b12","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11868","article-title":"Class attention transfer based knowledge distillation","author":"Guo","year":"2023"},{"key":"10.1016\/j.engappai.2026.115128_b13","series-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905) - Workshops","first-page":"17","article-title":"Human activity recognition in thermal infrared imagery","author":"Han","year":"2005"},{"key":"10.1016\/j.engappai.2026.115128_b14","unstructured":"Hinton, G., Vinyals, O., Dean, J., 2015. Distilling the Knowledge in a Neural Network. In: NIPS Deep Learning and Representation Learning Workshop."},{"key":"10.1016\/j.engappai.2026.115128_b15","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Cross modality knowledge distillation for robust pedestrian detection in low light and adverse weather conditions","author":"Hnewa","year":"2023"},{"issue":"3","key":"10.1016\/j.engappai.2026.115128_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104056","article-title":"Why logit distillation works: A novel knowledge distillation technique by deriving target augmentation and logits distortion","volume":"62","author":"Hossain","year":"2025","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.engappai.2026.115128_b17","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1007\/s11760-024-03796-9","article-title":"Tifar-net: Three-stream inception former-based action recognition network for infrared videos","volume":"19","author":"Imran","year":"2025","journal-title":"Signal, Image Video Process."},{"key":"10.1016\/j.engappai.2026.115128_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.infrared.2019.103014","article-title":"Deep residual infrared action recognition by integrating local and global spatio-temporal cues","volume":"102","author":"Imran","year":"2019","journal-title":"Infrared Phys. Technol."},{"key":"10.1016\/j.engappai.2026.115128_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118406","article-title":"Representation for action recognition with motion vector termed as: SDQIO","volume":"212","author":"Islam","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.115128_b20","first-page":"1","article-title":"Prompting-to-distill semantic knowledge for few-shot learning","volume":"21","author":"Ji","year":"2024","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.engappai.2026.115128_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107957","article-title":"Lighter and faster: A multi-scale adaptive graph convolutional network for skeleton-based action recognition","volume":"132","author":"Jiang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115128_b22","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"309","article-title":"Learning spatiotemporal features for infrared action recognition with 3D convolutional neural networks","author":"Jiang","year":"2017"},{"key":"10.1016\/j.engappai.2026.115128_b23","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"398","article-title":"ActAR: Actor-driven pose embeddings for video action recognition","author":"Lamghari","year":"2022"},{"key":"10.1016\/j.engappai.2026.115128_b24","series-title":"Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence","article-title":"Prototypical calibrating ambiguous samples for micro-action recognition","author":"Li","year":"2025"},{"key":"10.1016\/j.engappai.2026.115128_b25","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"9516","article-title":"Data augmentation for human behavior analysis in multi-person conversations","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.115128_b26","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.1109\/TMM.2025.3535385","article-title":"Repetitive action counting with hybrid temporal relation modeling","volume":"27","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115128_b27","series-title":"Network and Parallel Computing","first-page":"117","article-title":"Deep visible and thermal image fusion with cross-modality feature selection for pedestrian detection","author":"Li","year":"2021"},{"key":"10.1016\/j.engappai.2026.115128_b28","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12458","article-title":"Correlation-decoupled knowledge distillation for multimodal sentiment analysis with incomplete modalities","author":"Li","year":"2024"},{"issue":"2","key":"10.1016\/j.engappai.2026.115128_b29","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.2024.3429387","article-title":"Human-centric transformer for domain adaptive action recognition","volume":"47","author":"Lin","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"10.1016\/j.engappai.2026.115128_b30","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1109\/LSP.2018.2823910","article-title":"Global temporal representation based CNNs for infrared action recognition","volume":"25","author":"Liu","year":"2018","journal-title":"IEEE Signal Process. Lett."},{"issue":"4","key":"10.1016\/j.engappai.2026.115128_b31","doi-asserted-by":"crossref","DOI":"10.1007\/s00138-024-01550-2","article-title":"Thermal infrared action recognition with two-stream shift graph convolutional network","volume":"35","author":"Liu","year":"2024","journal-title":"Mach. Vis. Appl."},{"key":"10.1016\/j.engappai.2026.115128_b32","doi-asserted-by":"crossref","first-page":"4944","DOI":"10.1007\/s11263-025-02415-5","article-title":"I2MD: 3D action representation learning with inter- and intra-modal mutual distillation","volume":"133","author":"Mao","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.engappai.2026.115128_b33","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/TMM.2024.3521772","article-title":"Progressive knowledge distillation from different levels of teachers for online action detection","volume":"27","author":"Moniruzzaman","year":"2025","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.engappai.2026.115128_b34","article-title":"Attention-based deep learning framework for action recognition in a dark environment","volume":"14","author":"Munsif","year":"2024","journal-title":"Human-Centric Comput. Inf. Sci."},{"issue":"12","key":"10.1016\/j.engappai.2026.115128_b35","doi-asserted-by":"crossref","first-page":"13676","DOI":"10.1109\/TII.2024.3431070","article-title":"Darkness-adaptive action recognition: Leveraging efficient tubelet slow-fast network for industrial applications","volume":"20","author":"Munsif","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.engappai.2026.115128_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111996","article-title":"Action understanding in low-light and pitch-dark conditions: A comprehensive survey","volume":"161","author":"Munsif","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115128_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112480","article-title":"Contextual visual and motion salient fusion framework for action recognition in dark environments","volume":"304","author":"Munsif","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.115128_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104144","article-title":"Multi-modal transformer with language modality distillation for early pedestrian action anticipation","volume":"249","author":"Osman","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.engappai.2026.115128_b39","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/TMM.2023.3263288","article-title":"MAR: Masked autoencoders for efficient action recognition","volume":"26","author":"Qing","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115128_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103853","article-title":"ARCTIC: A knowledge distillation approach via attention-based relation matching and activation region constraint for RGB-to-infrared videos action recognition","volume":"237","author":"Quan","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.engappai.2026.115128_b41","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"5190","article-title":"Multimodal distillation for egocentric action recognition","author":"Radevski","year":"2023"},{"key":"10.1016\/j.engappai.2026.115128_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109569","article-title":"Kinematic matrix: One-shot human action recognition using kinematic data structure","volume":"139","author":"Ranjbar","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115128_b43","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1010","article-title":"NTU rgb+d: A large scale dataset for 3D human activity analysis","author":"Shahroudy","year":"2016"},{"key":"10.1016\/j.engappai.2026.115128_b44","series-title":"2020 IEEE Winter Conference on Applications of Computer Vision","first-page":"614","article-title":"D3D: Distilled 3D networks for video action recognition","author":"Stroud","year":"2020"},{"key":"10.1016\/j.engappai.2026.115128_b45","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"2663","article-title":"TIRDet: Mono-modality thermal InfraRed object detection based on prior thermal-to-visible translation","author":"Wang","year":"2023"},{"issue":"10","key":"10.1016\/j.engappai.2026.115128_b46","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115128_b47","series-title":"Proceedings of the Thirty-Eighth Association for the Advancement of Artificial Intelligence(AAAI) Conference","article-title":"Generative model-based feature knowledge distillation for action recognition","author":"Wang","year":"2024"},{"key":"10.1016\/j.engappai.2026.115128_b48","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20039","article-title":"MMANet: Margin-aware distillation and modality-aware regularization for incomplete multimodal learning","author":"Wei","year":"2023"},{"issue":"4","key":"10.1016\/j.engappai.2026.115128_b49","doi-asserted-by":"crossref","DOI":"10.1145\/3700878","article-title":"Joint mixing data augmentation for skeleton-based action recognition","volume":"21","author":"Xiang","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.engappai.2026.115128_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130541","article-title":"Few-shot action recognition with temporal feature enhancement in fine-tuning","volume":"647","author":"Xie","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.115128_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113262","article-title":"SCDFuse: A semantic complementary distillation framework for joint infrared and visible image fusion and denoising","volume":"315","author":"Xie","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.115128_b52","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"2409","article-title":"UniRGB-IR: A unified framework for visible-infrared semantic tasks via adapter tuning","author":"Yuan","year":"2025"},{"key":"10.1016\/j.engappai.2026.115128_b53","first-page":"1","article-title":"Detail-aware network for infrared image enhancement","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.engappai.2026.115128_b54","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"431","article-title":"Photometric correction for infrared sensors","author":"Zhang","year":"2023"},{"key":"10.1016\/j.engappai.2026.115128_b55","doi-asserted-by":"crossref","unstructured":"Zhao, T., Liu, B., Gao, Y., Sun, Y., Yuan, M., Wei, X., 2025. Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 6364\u20136373.","DOI":"10.1109\/ICCV51701.2025.00600"},{"key":"10.1016\/j.engappai.2026.115128_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111319","article-title":"Region-aware mutual relational knowledge distillation for semantic segmentation","volume":"161","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014119?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014119?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:51:48Z","timestamp":1783111908000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626014119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"alternative-id":["S0952197626014119"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115128","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Progressive knowledge evolution under multi-granularity knowledge distillation for infrared action recognition","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115128","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":"115128"}}