{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:32:27Z","timestamp":1773887547287,"version":"3.50.1"},"reference-count":76,"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\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T022205\/1"],"award-info":[{"award-number":["EP\/T022205\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V002856\/1"],"award-info":[{"award-number":["EP\/V002856\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1105102"],"award-info":[{"award-number":["2023YFF1105102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0116300"],"award-info":[{"award-number":["2023YFE0116300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1105105"],"award-info":[{"award-number":["2023YFF1105105"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771721"],"award-info":[{"award-number":["2025M771721"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106089"],"award-info":[{"award-number":["62106089"]}],"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":["62332008"],"award-info":[{"award-number":["62332008"]}],"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":["62336004"],"award-info":[{"award-number":["62336004"]}],"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":["U1836218"],"award-info":[{"award-number":["U1836218"]}],"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":["62020106012"],"award-info":[{"award-number":["62020106012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JUSRP202501040"],"award-info":[{"award-number":["JUSRP202501040"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People&apos;s Republic of China","doi-asserted-by":"publisher","award":["B12018"],"award-info":[{"award-number":["B12018"]}],"id":[{"id":"10.13039\/501100002338","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":[[2026,4]]},"DOI":"10.1016\/j.neunet.2025.108354","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T16:03:11Z","timestamp":1764086591000},"page":"108354","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Interactive image-to-video transfer learning"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9555-9445","authenticated-orcid":false,"given":"Cong","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9015-3128","authenticated-orcid":false,"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-9205","authenticated-orcid":false,"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108354_bib0001","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6836","article-title":"Vivit: A video vision transformer","author":"Arnab","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2025.108354_bib0002","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.patcog.2013.06.020","article-title":"Ongoing human action recognition with motion capture","volume":"47","author":"Barnachon","year":"2014","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108354_bib0003","series-title":"Icml","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"vol. 2","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.neunet.2025.108354_bib0004","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume":"34","author":"Bulat","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0005","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"9038","article-title":"Task-adapter: Task-specific adaptation of image models for few-shot action recognition","author":"Cao","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0006","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6299","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.neunet.2025.108354_bib0007","series-title":"16th Asian conference on machine learning","article-title":"Motion meets attention: Video motion prompts","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18688","article-title":"Align before adapt: Leveraging entity-to-region alignments for generalizable video action recognition","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0009","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7024","article-title":"Potion: Pose motion representation for action recognition","author":"Choutas","year":"2018"},{"key":"10.1016\/j.neunet.2025.108354_bib0010","series-title":"2009 IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2025.108354_bib0011","series-title":"International conference on machine learning","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"Donahue","year":"2014"},{"key":"10.1016\/j.neunet.2025.108354_bib0012","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2758","article-title":"Flownet: Learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.neunet.2025.108354_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6824","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"10.1016\/j.neunet.2025.108354_bib0014","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107114","article-title":"A discriminative multi-modal adaptation neural network model for video action recognition","volume":"185","author":"Gao","year":"2025","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.neunet.2025.108354_bib0016","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2net: A new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108354_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16102","article-title":"Omnivore: A single model for many visual modalities","author":"Girdhar","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0018","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.neunet.2025.108354_bib0019","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"5842","article-title":"The \u201csomething something\u201d video database for learning and evaluating visual common sense","author":"Goyal","year":"2017"},{"key":"10.1016\/j.neunet.2025.108354_bib0020","unstructured":"Han, Z., Gao, C., Liu, J., Zhang, J., & Zhang, S. Q. (2024). Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv: 2403.14608."},{"key":"10.1016\/j.neunet.2025.108354_bib0021","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.2025.108354_bib0022","series-title":"International conference on machine learning","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","author":"Hendrycks","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0023","series-title":"International conference on machine learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0024","series-title":"International conference on learning representations","article-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition","author":"Huang","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0025","unstructured":"Huh, M., Agrawal, P., & Efros, A. A. (2016). What makes imagenet good for transfer learning?arXiv preprint arXiv: 1608.08614."},{"key":"10.1016\/j.neunet.2025.108354_bib0026","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.patcog.2016.01.012","article-title":"Human action recognition using genetic algorithms and convolutional neural networks","volume":"59","author":"Ijjina","year":"2016","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108354_bib0027","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"3192","article-title":"Towards understanding action recognition","author":"Jhuang","year":"2013"},{"issue":"1","key":"10.1016\/j.neunet.2025.108354_bib0028","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108354_bib0029","series-title":"European conference on computer vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0030","series-title":"Bmvc","first-page":"2","article-title":"Human activity recognition using a dynamic texture based method","volume":"vol. 1","author":"Kellokumpu","year":"2008"},{"key":"10.1016\/j.neunet.2025.108354_bib0031","series-title":"European conference on computer vision","first-page":"345","article-title":"Motionsqueeze: Neural motion feature learning for video understanding","author":"Kwon","year":"2020"},{"key":"10.1016\/j.neunet.2025.108354_bib0032","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv: 2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"issue":"10","key":"10.1016\/j.neunet.2025.108354_bib0033","doi-asserted-by":"crossref","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","article-title":"Uniformer: Unifying convolution and self-attention for visual recognition","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108354_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104150","article-title":"M-adapter: Multi-level image-to-video adaptation for video action recognition","volume":"249","author":"Li","year":"2024","journal-title":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.neunet.2025.108354_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"909","article-title":"Tea: Temporal excitation and aggregation for action recognition","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2025.108354_bib0036","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"513","article-title":"Resound: Towards action recognition without representation bias","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2025.108354_bib0037","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7083","article-title":"Tsm: Temporal shift module for efficient video understanding","author":"Lin","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0038","series-title":"Computer vision\u2013ECCV 2022: 17th european conference, tel aviv, israel, october 23\u201327, 2022, proceedings, part XXXV","first-page":"388","article-title":"Frozen clip models are efficient video learners","author":"Lin","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Sparse deep transfer learning for convolutional neural network","volume":"vol. 31","author":"Liu","year":"2017"},{"key":"10.1016\/j.neunet.2025.108354_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3202","article-title":"Video swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0041","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv: 1711.05101."},{"key":"10.1016\/j.neunet.2025.108354_bib0042","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5512","article-title":"Grouped spatial-temporal aggregation for efficient action recognition","author":"Luo","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109905","article-title":"Relative-position embedding based spatially and temporally decoupled transformer for action recognition","volume":"145","author":"Ma","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108354_bib0044","series-title":"European conference on computer vision","first-page":"1","article-title":"Expanding language-image pretrained models for general video recognition","author":"Ni","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0045","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106326","article-title":"Tfrs: A task-level feature rectification and separation method for few-shot video action recognition","volume":"176","author":"Qin","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108354_bib0047","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2025.108354_bib0048","series-title":"Proceedings of the 15th ACM international conference on multimedia","first-page":"357","article-title":"A 3-dimensional sift descriptor and its application to action recognition","author":"Scovanner","year":"2007"},{"key":"10.1016\/j.neunet.2025.108354_bib0049","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"10.1016\/j.neunet.2025.108354_bib0050","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0051","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0052","series-title":"Handbook of research on machine learning applications and trends: Algorithms, methods, and techniques","first-page":"242","article-title":"Transfer learning","author":"Torrey","year":"2010"},{"key":"10.1016\/j.neunet.2025.108354_bib0053","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5552","article-title":"Video classification with channel-separated convolutional networks","author":"Tran","year":"2019"},{"key":"10.1016\/j.neunet.2025.108354_bib0054","unstructured":"Wang, B., & Wang, W. (2024). Tds-clip: Temporal difference side network for image-to-video transfer learning. arXiv preprint arXiv: 2408.10688."},{"key":"10.1016\/j.neunet.2025.108354_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111770","article-title":"Vlpa-clip: Video language prompting and adapting clip for efficient video action recognition","volume":"168","author":"Wang","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108354_bib0056","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"Wang","year":"2013"},{"key":"10.1016\/j.neunet.2025.108354_bib0057","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1895","article-title":"Tdn: Temporal difference networks for efficient action recognition","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2025.108354_bib0058","series-title":"European conference on computer vision","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"Wang","year":"2016"},{"key":"10.1016\/j.neunet.2025.108354_bib0059","unstructured":"Wang, L., Yuan, X., Gedeon, T., & Zheng, L. (2024a). Taylor videos for action recognition. arXiv preprint arXiv: 2402.03019."},{"key":"10.1016\/j.neunet.2025.108354_bib0060","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5517","article-title":"A multimodal, multi-task adapting framework for video action recognition","volume":"vol. 38","author":"Wang","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2025.108354_bib0061","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1109\/TNNLS.2023.3331841","article-title":"Actionclip: Adapting language-image pretrained models for video action recognition","volume":"36","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0062","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2019.09.029","article-title":"Multi-label zero-shot human action recognition via joint latent ranking embedding","volume":"122","author":"Wang","year":"2020","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108354_bib0063","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"5339","article-title":"Seeing in flowing: Adapting clip for action recognition with motion prompts learning","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108354_bib0064","unstructured":"Wang, Y., Li, K., Li, Y., He, Y., Huang, B., Zhao, Z., Zhang, H., Xu, J., Liu, Y., Wang, Z. et al. (2022). Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv: 2212.03191."},{"key":"10.1016\/j.neunet.2025.108354_bib0065","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14668","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"Wei","year":"2022"},{"issue":"4","key":"10.1016\/j.neunet.2025.108354_bib0066","doi-asserted-by":"crossref","first-page":"2120","DOI":"10.1109\/TCSVT.2021.3085959","article-title":"Graph2net: Perceptually-enriched graph learning for skeleton-based action recognition","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.108354_bib0067","series-title":"European conference on computer vision","first-page":"38","article-title":"Efficient few-shot action recognition via multi-level post-reasoning","author":"Wu","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0068","series-title":"European conference on computer vision","first-page":"627","article-title":"Spatiotemporal self-attention modeling with temporal patch shift for action recognition","author":"Xiang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0069","first-page":"80522","article-title":"V-petl bench: A unified visual parameter-efficient transfer learning benchmark","volume":"37","author":"Xin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108354_bib0070","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3333","article-title":"Multiview transformers for video recognition","author":"Yan","year":"2022"},{"key":"10.1016\/j.neunet.2025.108354_bib0071","series-title":"International conference on learning representations","article-title":"Aim: Adapting image models for efficient video understanding","author":"Yang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108354_bib0072","series-title":"Computer vision\u2013ECCV 2014: 13th european conference, zurich, switzerland, september 6\u201312, 2014, proceedings, part i 13","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"},{"key":"10.1016\/j.neunet.2025.108354_bib0073","unstructured":"Zhang, D., Feng, T., Xue, L., Wang, Y., Dong, Y., & Tang, J. (2025). Parameter-efficient fine-tuning for foundation models. arXiv preprint arXiv: 2501.13787."},{"key":"10.1016\/j.neunet.2025.108354_bib0074","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18504","article-title":"Enhanced motion-text alignment for image-to-video transfer learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2025.108354_bib0075","unstructured":"Zhao, L., Gundavarapu, N. B., Yuan, L., Zhou, H., Yan, S., Sun, J. J., Friedman, L., Qian, R., Weyand, T., Zhao, Y. et al. (2024). Videoprism: A foundational visual encoder for video understanding. arXiv preprint arXiv: 2402.13217."},{"key":"10.1016\/j.neunet.2025.108354_bib0076","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1016\/j.neunet.2023.09.031","article-title":"A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition","volume":"168","author":"Zhou","year":"2023","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012353?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012353?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:52:12Z","timestamp":1773870732000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025012353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":76,"alternative-id":["S0893608025012353"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108354","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Interactive image-to-video transfer learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108354","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108354"}}