{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:15:21Z","timestamp":1784888121391,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62202131"],"award-info":[{"award-number":["No.62202131"]}],"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":["No.62372145"],"award-info":[{"award-number":["No.62372145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10489-025-06636-6","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T08:57:29Z","timestamp":1750323449000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["IACFormer: a transformer framework with instantaneous average convolution for temporal action detection"],"prefix":"10.1007","volume":"55","author":[{"given":"Haiping","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixiang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liming","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0283-2407","authenticated-orcid":false,"given":"Wanjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"6636_CR1","doi-asserted-by":"crossref","unstructured":"Gao S, Wang H, Xu F, Song J, Jia K (2019) Real-time human action detection for elderly monitoring system. In: 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, pp 1191\u20131196","DOI":"10.1109\/CYBER46603.2019.9066751"},{"key":"6636_CR2","doi-asserted-by":"crossref","unstructured":"Liang J, Zhu H, Zhang E, Zhang J (2022) Stargazer: A transformer-based driver action detection system for intelligent transportation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3160\u20133167","DOI":"10.1109\/CVPRW56347.2022.00356"},{"key":"6636_CR3","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2014) Video action detection with relational dynamic-poselets. In: Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, pp 565\u2013580","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"6636_CR4","doi-asserted-by":"crossref","unstructured":"Li Y, Chen L, He R, Wang Z, Wu, Wang L (2021) Multisports: A multi-person video dataset of spatio-temporally localized sports actions. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13536\u201313545","DOI":"10.1109\/ICCV48922.2021.01328"},{"issue":"1","key":"6636_CR5","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/TMM.2004.840618","volume":"7","author":"A Hanjalic","year":"2005","unstructured":"Hanjalic A, Xu L-Q (2005) Affective video content representation and modeling. IEEE Trans Multimedia 7(1):143\u2013154","journal-title":"IEEE Trans Multimedia"},{"key":"6636_CR6","unstructured":"Kasteren TLM et al (2011) Activity recognition for health monitoring elderly using temporal probabilistic models. SCI"},{"issue":"3","key":"6636_CR7","first-page":"71","volume":"7","author":"J Choi","year":"2008","unstructured":"Choi J, Cho Y-I, Cho K, Bae S, Yang HS (2008) A view-based multiple objects tracking and human action recognition for interactive virtual environments. Int. J. Virtual Real. 7(3):71\u201376","journal-title":"Int. J. Virtual Real."},{"key":"6636_CR8","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong Z, Song Y, Wang J, Wang L (2022) Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv Neural Inf Process Syst 35:10078\u201310093","journal-title":"Adv Neural Inf Process Syst"},{"key":"6636_CR9","doi-asserted-by":"crossref","unstructured":"Chao Y-W, Vijayanarasimhan S, Seybold B, Ross DA, Deng J, Sukthankar R (2018) Rethinking the faster r-cnn architecture for temporal action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1130\u20131139","DOI":"10.1109\/CVPR.2018.00124"},{"key":"6636_CR10","doi-asserted-by":"crossref","unstructured":"Zhao C, Liu S, Mangalam K, Ghanem B (2023) Re2tal: Rewiring pretrained video backbones for reversible temporal action localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10637\u201310647","DOI":"10.1109\/CVPR52729.2023.01025"},{"key":"6636_CR11","doi-asserted-by":"publisher","first-page":"77658","DOI":"10.1109\/ACCESS.2022.3193158","volume":"10","author":"J Tong","year":"2022","unstructured":"Tong J, Li J, Zhang M, Zhang B (2022) Action localization using 2d-cnn and 3d-cnn collaboration. IEEE Access 10:77658\u201377667","journal-title":"IEEE Access"},{"key":"6636_CR12","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10044-019-00788-1","volume":"23","author":"A Zare","year":"2020","unstructured":"Zare A, Abrishami Moghaddam H, Sharifi A (2020) Video spatiotemporal mapping for human action recognition by convolutional neural network. Pattern Anal Appl 23:265\u2013279","journal-title":"Pattern Anal Appl"},{"key":"6636_CR13","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inform Process Syst 30"},{"key":"6636_CR14","unstructured":"Kenton JDM-WC, Toutanova LK (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol 1, p 2"},{"key":"6636_CR15","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. arXiv preprint arXiv:2010.11929"},{"key":"6636_CR16","doi-asserted-by":"crossref","unstructured":"Zhu H, Liang J, Lin C, Zhang J, Hu J (2022) A transformer-based system for action spotting in soccer videos. In: Proceedings of the 5th international ACM workshop on multimedia content analysis in sports, pp 103\u2013109","DOI":"10.1145\/3552437.3555693"},{"key":"6636_CR17","doi-asserted-by":"crossref","unstructured":"Shao J, Wang X, Quan R, Zheng J, Yang J, Yang Y (2023) Action sensitivity learning for temporal action localization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13457\u201313469","DOI":"10.1109\/ICCV51070.2023.01238"},{"key":"6636_CR18","doi-asserted-by":"crossref","unstructured":"Zhao J, Zhang Y, Li X, Chen H, Shuai B, Xu M, Liu C, Kundu K, Xiong Y, Modolo D et al (2022) Tuber: Tubelet transformer for video action detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13598\u201313607","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"6636_CR19","doi-asserted-by":"crossref","unstructured":"Li X, Lin T, Liu X, Zuo W, Li C, Long X, He D, Li F, Wen S, Gan C (2020) Deep concept-wise temporal convolutional networks for action localization. In: Proceedings of the 28th ACM international conference on multimedia, pp 4004\u20134012","DOI":"10.1145\/3394171.3413860"},{"key":"6636_CR20","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang S-F (2016) Temporal action localization in untrimmed videos via multi-stage cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"6636_CR21","doi-asserted-by":"crossref","unstructured":"Wei J, Wang H, Yi Y, Li Q, Huang D (2019) P3d-ctn: Pseudo-3d convolutional tube network for spatio-temporal action detection in videos. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE pp 300\u2013304","DOI":"10.1109\/ICIP.2019.8802979"},{"key":"6636_CR22","doi-asserted-by":"crossref","unstructured":"Xu H, Das A, Saenko K (2017) R-c3d: Region convolutional 3d network for temporal activity detection. In: Proceedings of the IEEE international conference on computer vision, pp 5783\u20135792","DOI":"10.1109\/ICCV.2017.617"},{"key":"6636_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103692","volume":"232","author":"M Yang","year":"2023","unstructured":"Yang M, Chen G, Zheng Y-D, Lu T, Wang L (2023) Basictad: an astounding rgb-only baseline for temporal action detection. Comput Vis Image Underst 232:103692","journal-title":"Comput Vis Image Underst"},{"key":"6636_CR24","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S (2019) Bmn: Boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3889\u20133898","DOI":"10.1109\/ICCV.2019.00399"},{"issue":"12","key":"6636_CR25","doi-asserted-by":"publisher","first-page":"16041","DOI":"10.1007\/s10489-022-04342-1","volume":"53","author":"S Zhang","year":"2023","unstructured":"Zhang S, Wei H-L, Ding J (2023) An effective zero-shot learning approach for intelligent fault detection using 1d cnn. Appl Intell 53(12):16041\u201316058","journal-title":"Appl Intell"},{"issue":"3","key":"6636_CR26","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1007\/s10044-023-01161-z","volume":"26","author":"A Zou","year":"2023","unstructured":"Zou A, Hao W, Chen G, Jin D (2023) Dec-transformer: deep embedded clustering with transformer on chinese long text. Pattern Anal Appl 26(3):1349\u20131362","journal-title":"Pattern Anal Appl"},{"key":"6636_CR27","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu X, Wang Q, Hu Y, Tang X, Zhang S, Bai S, Bai X (2022) End-to-end temporal action detection with transformer. IEEE Trans Image Process 31:5427\u20135441","journal-title":"IEEE Trans Image Process"},{"key":"6636_CR28","doi-asserted-by":"crossref","unstructured":"Shi D, Zhong Y, Cao Q, Zhang J, Ma L, Li J, Tao D (2022) React: Temporal action detection with relational queries. In: European conference on computer vision. Springer, pp 105\u2013121","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"6636_CR29","doi-asserted-by":"crossref","unstructured":"Zhang C-L, Wu J, Li Y (2022) Actionformer: Localizing moments of actions with transformers. In: European conference on computer vision. Springer, pp 492\u2013510","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"6636_CR30","doi-asserted-by":"crossref","unstructured":"Korban M, Youngs P, Acton ST (2024) A semantic and motion-aware spatiotemporal transformer network for action detection. IEEE Transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2024.3377192"},{"key":"6636_CR31","doi-asserted-by":"crossref","unstructured":"Babavalian MR, Kiani K (2024) Video captioning using transformer-based gan. Multimed Tool Appl pp 1\u201323","DOI":"10.2139\/ssrn.4511115"},{"issue":"3","key":"6636_CR32","doi-asserted-by":"publisher","first-page":"3444","DOI":"10.1007\/s10489-022-03728-5","volume":"53","author":"X Wu","year":"2023","unstructured":"Wu X, Tang B, Zhao M, Wang J, Guo Y (2023) Str transformer: a cross-domain transformer for scene text recognition. Appl Intell 53(3):3444\u20133458","journal-title":"Appl Intell"},{"key":"6636_CR33","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhou F, Wang D, Zhang X, Yu D, Guan L (2024) Lgaformer: transformer with local and global attention for action detection. J Supercomput pp 1\u201328","DOI":"10.1007\/s11227-024-06138-1"},{"issue":"3","key":"6636_CR34","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1049\/cvi2.12163","volume":"17","author":"H Zhang","year":"2023","unstructured":"Zhang H, Ma C, Yu D, Guan L, Wang D, Hu Z, Liu X (2023) Mtscanet: Multi temporal resolution temporal semantic context aggregation network. IET Comput Vision 17(3):366\u2013378","journal-title":"IET Comput Vision"},{"key":"6636_CR35","doi-asserted-by":"crossref","unstructured":"Dai R, Minciullo L, Garattoni L, Francesca G, Bremond F (2019) Self-attention temporal convolutional network for long-term daily living activity detection. In: 2019 16th IEEE International conference on advanced video and signal based surveillance (AVSS). IEEE, pp 1\u20137","DOI":"10.1109\/AVSS.2019.8909841"},{"key":"6636_CR36","doi-asserted-by":"crossref","unstructured":"Dai R, Das S, Kahatapitiya K, Ryoo MS, Br\u00e9mond F (2022) Ms-tct: Multi-scale temporal convtransformer for action detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 20041\u201320051","DOI":"10.1109\/CVPR52688.2022.01941"},{"issue":"1","key":"6636_CR37","doi-asserted-by":"publisher","first-page":"15333","DOI":"10.1038\/s41598-023-41561-z","volume":"13","author":"S Zhang","year":"2023","unstructured":"Zhang S, Zhao L, Hu K, Feng S, Fan E, Zhao L (2023) Deep guided transformer dehazing network. Sci Rep 13(1):15333","journal-title":"Sci Rep"},{"issue":"5","key":"6636_CR38","doi-asserted-by":"publisher","first-page":"2290","DOI":"10.1007\/s10278-023-00842-9","volume":"36","author":"J Yuan","year":"2023","unstructured":"Yuan J, Zhou F, Guo Z, Li X, Yu H (2023) Hcformer: hybrid cnn-transformer for ldct image denoising. J Digit Imaging 36(5):2290\u20132305","journal-title":"J Digit Imaging"},{"issue":"6","key":"6636_CR39","doi-asserted-by":"publisher","first-page":"3819","DOI":"10.1007\/s00530-023-01184-w","volume":"29","author":"F Xiao","year":"2023","unstructured":"Xiao F, Zhang Z, Yao Y (2023) Ctnet: hybrid architecture based on cnn and transformer for image inpainting detection. Multimedia Syst 29(6):3819\u20133832","journal-title":"Multimedia Syst"},{"key":"6636_CR40","unstructured":"Wu T, Ge S, Qin J, Wu G, Wang L (2024) Open-vocabulary spatio-temporal action detection. arXiv preprint arXiv:2405.10832"},{"issue":"10","key":"6636_CR41","doi-asserted-by":"publisher","first-page":"12472","DOI":"10.1007\/s10489-022-04122-x","volume":"53","author":"J Liu","year":"2023","unstructured":"Liu J, Kang Y, Li H, Wang H, Yang X (2023) Stghtn: Spatial-temporal gated hybrid transformer network for traffic flow forecasting. Appl Intell 53(10):12472\u201312488","journal-title":"Appl Intell"},{"issue":"6","key":"6636_CR42","doi-asserted-by":"publisher","first-page":"6753","DOI":"10.1007\/s10489-022-03785-w","volume":"53","author":"T Xue","year":"2023","unstructured":"Xue T, Ma P (2023) Tc-net: transformer combined with cnn for image denoising. Appl Intell 53(6):6753\u20136762","journal-title":"Appl Intell"},{"key":"6636_CR43","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122"},{"key":"6636_CR44","doi-asserted-by":"crossref","unstructured":"Zhang X, Hamann B, Wang D, Wang H, Wang Y, Yin Y, Gao H (2024) Fmgdn: Flexible multi-grained dilation network empowered multimedia image inpainting for electronic consumer. IEEE Trans Consum Electron","DOI":"10.1109\/TCE.2024.3386773"},{"key":"6636_CR45","unstructured":"Jayakumar SM, Czarnecki WM, Menick J, Schwarz J, Rae J, Osindero S, Teh YW, Harley T, Pascanu R (2020) Multiplicative interactions and where to find them. In: International conference on learning representations"},{"key":"6636_CR46","unstructured":"Wu Y, Zhang S, Zhang Y, Bengio Y, Salakhutdinov RR (2016) On multiplicative integration with recurrent neural networks. Adv Neural Inform Process Syst 29"},{"key":"6636_CR47","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"6636_CR48","doi-asserted-by":"crossref","unstructured":"Xue W, Li T (2018) Aspect based sentiment analysis with gated convolutional networks. arXiv preprint arXiv:1805.07043","DOI":"10.18653\/v1\/P18-1234"},{"key":"6636_CR49","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"6636_CR50","doi-asserted-by":"crossref","unstructured":"Shi D, Zhong Y, Cao Q, Ma L, Li J, Tao D (2023) Tridet: Temporal action detection with relative boundary modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18857\u201318866","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"6636_CR51","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"issue":"11","key":"6636_CR52","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2018) Temporal segment networks for action recognition in videos. IEEE Trans Pattern Anal Mach Intell 41(11):2740\u20132755","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6636_CR53","doi-asserted-by":"crossref","unstructured":"Weng Y, Pan Z, Han M, Chang X, Zhuang B (2022) An efficient spatio-temporal pyramid transformer for action detection. In: European conference on computer vision. Springer, pp 358\u2013375","DOI":"10.1007\/978-3-031-19830-4_21"},{"key":"6636_CR54","doi-asserted-by":"crossref","unstructured":"Zhao C, Thabet AK, Ghanem B (2021) Video self-stitching graph network for temporal action localization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13658\u201313667","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"6636_CR55","doi-asserted-by":"crossref","unstructured":"Chen G, Zheng Y-D, Wang L, Lu T (2022) Dcan: improving temporal action detection via dual context aggregation. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 248\u2013257","DOI":"10.1609\/aaai.v36i1.19900"},{"key":"6636_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109560","volume":"140","author":"Q Liu","year":"2023","unstructured":"Liu Q, Wang Z, Rong S (2023) Improve temporal action proposals using hierarchical context. Pattern Recogn 140:109560","journal-title":"Pattern Recogn"},{"key":"6636_CR57","doi-asserted-by":"crossref","unstructured":"Cheng F, Bertasius G (2022) Tallformer: Temporal action localization with a long-memory transformer. In: European conference on computer vision. Springer, pp 503\u2013521","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"6636_CR58","doi-asserted-by":"crossref","unstructured":"Alwassel H, Giancola S, Ghanem B (2021) Tsp: Temporally-sensitive pretraining of video encoders for localization tasks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3173\u20133183","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"6636_CR59","doi-asserted-by":"crossref","unstructured":"Qing Z, Su H, Gan W, Wang D, Wu W, Wang X, Qiao Y, Yan J, Gao C, Sang N (2021) Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 485\u2013494","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"6636_CR60","doi-asserted-by":"crossref","unstructured":"Wang L, Huang B, Zhao Z, Tong Z, He Y, Wang Y, Wang Y, Qiao Y (2023) Videomae v2: Scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14549\u201314560","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"6636_CR61","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2704\u20132713","DOI":"10.1109\/CVPR.2018.00286"},{"key":"6636_CR62","first-page":"6666","volume":"35","author":"D Zheng","year":"2022","unstructured":"Zheng D, Liu Y, Li L et al (2022) Leveraging inter-layer dependency for post-training quantization. Adv Neural Inf Process Syst 35:6666\u20136679","journal-title":"Adv Neural Inf Process Syst"},{"key":"6636_CR63","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhu J, Wang D, Wang Y, Liang T, Wang H, Yin Y (2024) A gradual self distillation network with adaptive channel attention for facial expression recognition. Appl Soft Comput, p 111762","DOI":"10.1016\/j.asoc.2024.111762"},{"key":"6636_CR64","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. PMLR, pp 1126\u20131135"},{"key":"6636_CR65","doi-asserted-by":"crossref","unstructured":"Wei G, Lan C, Zeng W, Chen Z (2021) Metaalign: Coordinating domain alignment and classification for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16643\u201316653","DOI":"10.1109\/CVPR46437.2021.01637"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06636-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06636-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06636-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T13:38:37Z","timestamp":1758289117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06636-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":65,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6636"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06636-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,19]]},"assertion":[{"value":"11 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This research did not involve human participants or animal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}}],"article-number":"801"}}