{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:21:03Z","timestamp":1783146063581,"version":"3.54.6"},"reference-count":44,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371084"],"award-info":[{"award-number":["62371084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371083"],"award-info":[{"award-number":["62371083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476033"],"award-info":[{"award-number":["62476033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371076"],"award-info":[{"award-number":["62371076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007957","name":"Chongqing Municipal Education Commission","doi-asserted-by":"publisher","award":["KJQN202500623"],"award-info":[{"award-number":["KJQN202500623"]}],"id":[{"id":"10.13039\/501100007957","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2025NSCQ-GPX1312"],"award-info":[{"award-number":["CSTB2025NSCQ-GPX1312"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2025NSCQ-GPX1282"],"award-info":[{"award-number":["CSTB2025NSCQ-GPX1282"]}],"id":[{"id":"10.13039\/501100005230","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.2026.114745","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:06:06Z","timestamp":1776668766000},"page":"114745","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Ground-to-Aerial Scene Adaptation: Unsupervised drone video action recognition via domain adaptation"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0413-8640","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4718-9900","authenticated-orcid":false,"given":"Zhijia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-0775","authenticated-orcid":false,"given":"Fulin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anyong","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1264-2812","authenticated-orcid":false,"given":"Tiecheng","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenqiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114745_b1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A., 2017. Quo vadis, action recognition? a new model and the kinetics dataset. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.engappai.2026.114745_b2","doi-asserted-by":"crossref","unstructured":"Chen, P., Gao, Y., Ma, A.J., 2022. Multi-level attentive adversarial learning with temporal dilation for unsupervised video domain adaptation. In: Proc. Winter Conf. Applications of Comp. Vis.. pp. 1259\u20131268.","DOI":"10.1109\/WACV51458.2022.00085"},{"key":"10.1016\/j.engappai.2026.114745_b3","doi-asserted-by":"crossref","unstructured":"Chen, M.-H., Kira, Z., AlRegib, G., Yoo, J., Chen, R., Zheng, J., 2019. Temporal attentive alignment for large-scale video domain adaptation. In: Proc. IEEE Int. Conf. Comp. Vis.. pp. 6321\u20136330.","DOI":"10.1109\/ICCV.2019.00642"},{"key":"10.1016\/j.engappai.2026.114745_b4","doi-asserted-by":"crossref","unstructured":"Chen, M., Zheng, Z., Yang, Y., Chua, T.-S., 2023. Pipa: Pixel-and patch-wise self-supervised learning for domain adaptative semantic segmentation. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 1905\u20131914.","DOI":"10.1145\/3581783.3611708"},{"key":"10.1016\/j.engappai.2026.114745_b5","doi-asserted-by":"crossref","unstructured":"Choi, J., Sharma, G., Chandraker, M., Huang, J.-B., 2020a. Unsupervised and semi-supervised domain adaptation for action recognition from drones. In: Proc. Winter Conf. Applications of Comp. Vis.. pp. 1717\u20131726.","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"10.1016\/j.engappai.2026.114745_b6","doi-asserted-by":"crossref","unstructured":"Choi, J., Sharma, G., Schulter, S., Huang, J.-B., 2020b. Shuffle and attend: Video domain adaptation. In: Proc. Eur. Conf. Comp. Vis.. pp. 678\u2013695.","DOI":"10.1007\/978-3-030-58610-2_40"},{"key":"10.1016\/j.engappai.2026.114745_b7","unstructured":"da Costa, V.G.T., Zara, G., Rota, P., Oliveira-Santos, T., Sebe, N., Murino, V., Ricci, E., 2022a. Dual-head contrastive domain adaptation for video action recognition. In: Proc. Winter Conf. Applications of Comp. Vis.. pp. 1181\u20131190."},{"key":"10.1016\/j.engappai.2026.114745_b8","doi-asserted-by":"crossref","unstructured":"da Costa, V.G.T., Zara, G., Rota, P., Oliveira-Santos, T., Sebe, N., Murino, V., Ricci, E., 2022b. Unsupervised domain adaptation for video transformers in action recognition. In: Proc. Int. Conf. Patt. Recogn.. pp. 1258\u20131265.","DOI":"10.1109\/ICPR56361.2022.9956679"},{"key":"10.1016\/j.engappai.2026.114745_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111328","article-title":"Source-free video domain adaptation by learning from noisy labels","volume":"161","author":"Dasgupta","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2026.114745_b10","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. In: Proc. Int. Conf. Learn. Representations."},{"key":"10.1016\/j.engappai.2026.114745_b11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A., 2016. Convolutional two-stream network fusion for video action recognition. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 1933\u20131941.","DOI":"10.1109\/CVPR.2016.213"},{"key":"10.1016\/j.engappai.2026.114745_b12","unstructured":"Ganin, Y., Lempitsky, V., 2015. Unsupervised domain adaptation by backpropagation. In: Proc. Int. Conf. Mach. Learn.. pp. 1180\u20131189."},{"issue":"59","key":"10.1016\/j.engappai.2026.114745_b13","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114745_b14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R., 2020. Momentum contrast for unsupervised visual representation learning. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.engappai.2026.114745_b15","first-page":"1","article-title":"FuTH-Net: Fusing temporal relations and holistic features for aerial video classification","volume":"60","author":"Jin","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.engappai.2026.114745_b16","doi-asserted-by":"crossref","unstructured":"Kothandaraman, D., Guan, T., Wang, X., Hu, S., Lin, M., Manocha, D., 2022. Far: Fourier aerial video recognition. In: Proc. Eur. Conf. Comp. Vis.. pp. 657\u2013676.","DOI":"10.1007\/978-3-031-19836-6_37"},{"key":"10.1016\/j.engappai.2026.114745_b17","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T., 2011. HMDB: a large video database for human motion recognition. In: Proc. IEEE Int. Conf. Comp. Vis.. pp. 2556\u20132563.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"10.1016\/j.engappai.2026.114745_b18","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L., 2020. Tea: Temporal excitation and aggregation for action recognition. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 909\u2013918.","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"10.1016\/j.engappai.2026.114745_b19","doi-asserted-by":"crossref","unstructured":"Li, T., Liu, J., Zhang, W., Ni, Y., Wang, W., Li, Z., 2021. Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 16266\u201316275.","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"10.1016\/j.engappai.2026.114745_b20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T., 2021. Tam: Temporal adaptive module for video recognition. In: Proc. IEEE Int. Conf. Comp. Vis.. pp. 13708\u201313718.","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"10.1016\/j.engappai.2026.114745_b21","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M., 2015. Learning transferable features with deep adaptation networks. In: Proc. Int. Conf. Mach. Learn.. pp. 97\u2013105."},{"key":"10.1016\/j.engappai.2026.114745_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107140","article-title":"Human activity recognition from UAV-captured video sequences","volume":"100","author":"Mliki","year":"2020","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.engappai.2026.114745_b23","first-page":"11815","article-title":"Adversarial cross-domain action recognition with co-attention","volume":"Vol. 34","author":"Pan","year":"2020"},{"key":"10.1016\/j.engappai.2026.114745_b24","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.engappai.2026.114745_b25","doi-asserted-by":"crossref","first-page":"82","DOI":"10.3390\/drones3040082","article-title":"Drone-action: An outdoor recorded drone video dataset for action recognition","volume":"3","author":"Perera","year":"2019","journal-title":"Drones"},{"key":"10.1016\/j.engappai.2026.114745_b26","series-title":"Synthetic-to-real domain adaptation for action recognition: A dataset and baseline performances","author":"Reddy","year":"2023"},{"key":"10.1016\/j.engappai.2026.114745_b27","first-page":"23386","article-title":"Contrast and mix: Temporal contrastive video domain adaptation with background mixing","volume":"34","author":"Sahoo","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114745_b28","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., Harada, T., 2018. Maximum classifier discrepancy for unsupervised domain adaptation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 3723\u20133732.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"10.1016\/j.engappai.2026.114745_b29","series-title":"An image is worth 16x16 words, what is a video worth?","author":"Sharir","year":"2021"},{"key":"10.1016\/j.engappai.2026.114745_b30","series-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"10.1016\/j.engappai.2026.114745_b31","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M., 2018. Learning to compare: Relation network for few-shot learning. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 1199\u20131208.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"10.1016\/j.engappai.2026.114745_b32","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1007\/BF01016429","article-title":"Possible generalization of Boltzmann-Gibbs statistics","volume":"52","author":"Tsallis","year":"1988","journal-title":"J. Stat. Phys."},{"key":"10.1016\/j.engappai.2026.114745_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106505","article-title":"Video domain adaptation for semantic segmentation using perceptual consistency matching","volume":"179","author":"Ullah","year":"2024","journal-title":"Neural Netw."},{"issue":"11","key":"10.1016\/j.engappai.2026.114745_b34","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114745_b35","series-title":"Aztr: Aerial video action recognition with auto zoom and temporal reasoning","author":"Wang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114745_b36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yue, Y., Lin, Y., Jiang, H., Lai, Z., Kulikov, V., Orlov, N., Shi, H., Huang, G., 2022. Adafocus v2: End-to-end training of spatial dynamic networks for video recognition. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn.. pp. 20030\u201320040.","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"10.1016\/j.engappai.2026.114745_b37","article-title":"Unsupervised video domain adaptation for action recognition: A disentanglement perspective","volume":"36","author":"Wei","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114745_b38","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.neunet.2022.12.005","article-title":"DroneAttention: Sparse weighted temporal attention for drone-camera based activity recognition","volume":"159","author":"Yadav","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.engappai.2026.114745_b39","article-title":"Aerial video classification with window semantic enhanced video transformers","author":"Yang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114745_b40","series-title":"Transformer-based source-free domain adaptation","author":"Yang","year":"2021"},{"issue":"5","key":"10.1016\/j.engappai.2026.114745_b41","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1109\/TIP.2018.2886807","article-title":"Learning the synthesizability of dynamic texture samples","volume":"28","author":"Yang","year":"2018","journal-title":"IEEE Trans. Image Process"},{"key":"10.1016\/j.engappai.2026.114745_b42","article-title":"Aerial video classification by integrating global-local semantics in ConvNets","author":"Yang","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.engappai.2026.114745_b43","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S., 2021. Barlow twins: Self-supervised learning via redundancy reduction. In: Proc. Int. Conf. Mach. Learn.. pp. 12310\u201312320."},{"key":"10.1016\/j.engappai.2026.114745_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106497","article-title":"Unsupervised and semi-supervised domain adaptation networks considering both global knowledge and prototype-based local class information for motor imagery classification","volume":"179","author":"Zhang","year":"2024","journal-title":"Neural Netw."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010274?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010274?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:04:43Z","timestamp":1783145083000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626010274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S0952197626010274"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114745","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":"Ground-to-Aerial Scene Adaptation: Unsupervised drone video action recognition via domain adaptation","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114745","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":"114745"}}