{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:05:41Z","timestamp":1780445141199,"version":"3.54.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"vor","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Manipal University Jaipur"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"DOI":"10.1007\/s44163-026-00919-8","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T16:50:11Z","timestamp":1775753411000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TSM-Transformer: a hybrid EfficientNetV2-Lite and temporal shift model for facial expression recognition in videos"],"prefix":"10.1007","volume":"6","author":[{"given":"Rahul","family":"Saraswat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveen Kumar","family":"Mannepalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep Singh","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manish","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"919_CR1","doi-asserted-by":"crossref","unstructured":"Gaya-Morey FX, Manresa-Yee C, Martinie C, Buades-Rubio JM. Evaluating facial expression recognition datasets for deep learning: a benchmark study with novel similarity metrics,\u201d pp. 1\u201312, 2025.","DOI":"10.1109\/TAFFC.2026.3693316"},{"key":"919_CR2","doi-asserted-by":"publisher","first-page":"3732","DOI":"10.1109\/TIP.2023.3290520","volume":"32","author":"T Liu","year":"2023","unstructured":"Liu T, Li J, Wu J, Du B, Chang J, Liu Y. Facial expression recognition on the high aggregation subgraphs. IEEE Trans Image Process. 2023;32:3732\u201345. https:\/\/doi.org\/10.1109\/TIP.2023.3290520.","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"919_CR3","doi-asserted-by":"publisher","first-page":"9946","DOI":"10.1109\/TNNLS.2025.3548669","volume":"36","author":"B Pan","year":"2025","unstructured":"Pan B, Hirota K, Dai Y, Jia Z, Shao S, She J. Learning sequential variation information for dynamic facial expression recognition. IEEE Trans Neural Networks Learn Syst. 2025;36(6):9946\u201360. https:\/\/doi.org\/10.1109\/TNNLS.2025.3548669.","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"issue":"1","key":"919_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-87688-z","volume":"15","author":"H Arabian","year":"2025","unstructured":"Arabian H, et al. Feasibility study of emotion mimicry analysis in human\u2013machine interaction. Sci Rep. 2025;15(1):3859. https:\/\/doi.org\/10.1038\/s41598-025-87688-z.","journal-title":"Sci Rep"},{"key":"919_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121658","volume":"692","author":"MR Manavand","year":"2025","unstructured":"Manavand MR, Salarifar MH, Ghavami M, Taghipour-Gorjikolaie M. Driver\u2019s facial expression recognition by using deep local and global features. Inf Sci. 2025;692:121658. https:\/\/doi.org\/10.1016\/j.ins.2024.121658.","journal-title":"Inf Sci"},{"key":"919_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130020","volume":"636","author":"Y L\u00fc","year":"2025","unstructured":"L\u00fc Y, Zhang F, Ma Z, Zheng B, Nan Z. Dynamic facial expression recognition in the wild via multi-snippet spatiotemporal learning. Neurocomputing. 2025;636:130020. https:\/\/doi.org\/10.1016\/j.neucom.2025.130020.","journal-title":"Neurocomputing"},{"key":"919_CR7","doi-asserted-by":"publisher","unstructured":"Suma KG, Balasm Z, Sasirekha N, VM P, Sandhya K. Emotion recognition in visual art on color and texture analysis using improved vision transformer. In: 2025 international conference on intelligent systems and computational networks (ICISCN), 2025, pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICISCN64258.2025.10934620.","DOI":"10.1109\/ICISCN64258.2025.10934620"},{"key":"919_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-00930-6","author":"M Pradeepa","year":"2025","unstructured":"Pradeepa M, Sharmila B, Nirmala M. A hybrid deep learning model EfficientNet with GRU for breast cancer detection from histopathology images. Sci Rep. 2025. https:\/\/doi.org\/10.1038\/s41598-025-00930-6.","journal-title":"Sci Rep"},{"key":"919_CR9","doi-asserted-by":"publisher","unstructured":"Lin J, Gan C, Han S. TSM: temporal shift module for efficient video understanding. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 7082\u20137092, 2019. https:\/\/doi.org\/10.1109\/ICCV.2019.00718.","DOI":"10.1109\/ICCV.2019.00718"},{"key":"919_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2025.04.007","author":"MM Alam","year":"2025","unstructured":"Alam MM, Dini MA, Kim D-S, Jun T. TMNet: Transformer-fused multimodal framework for emotion recognition via EEG and speech. ICT Express. 2025. https:\/\/doi.org\/10.1016\/j.icte.2025.04.007.","journal-title":"ICT Express"},{"key":"919_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2025.105470","volume":"168","author":"T Han","year":"2026","unstructured":"Han T, Dou S, Zhang W, Liu R. Enhanced dynamic temporal feature extraction with static expression insights for dynamic facial expression recognition. Dig Signal Process. 2026;168:105470. https:\/\/doi.org\/10.1016\/j.dsp.2025.105470.","journal-title":"Dig Signal Process"},{"key":"919_CR12","doi-asserted-by":"publisher","unstructured":"Kumar R, Corvisieri G, Fici TF, Hussain SI, Tegolo D, Valenti C. Transfer learning for facial expression recognition. 2025. https:\/\/doi.org\/10.3390\/info16040320.","DOI":"10.3390\/info16040320"},{"key":"919_CR13","doi-asserted-by":"crossref","unstructured":"Li M, Zhang X, Liao T, Lin S, Xiao G. Pth-net: dynamic facial expression recognition without face detection and alignment. In: IEEE Trans. Image Process., 2024.","DOI":"10.36227\/techrxiv.170630113.31834403\/v1"},{"key":"919_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424777","author":"H Zhou","year":"2024","unstructured":"Zhou H, Huang S, Zhang F, Xu C. Ceprompt: cross-modal emotion-aware prompting for facial expression recognition. IEEE Trans Circuits Syst Video Technol. 2024. https:\/\/doi.org\/10.1109\/TCSVT.2024.3424777.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"919_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129261","volume":"621","author":"H Zhou","year":"2025","unstructured":"Zhou H, Huang S, Xu Y. UA-FER: Uncertainty-aware representation learning for facial expression recognition. Neurocomputing. 2025;621:129261.","journal-title":"Neurocomputing"},{"key":"919_CR16","doi-asserted-by":"publisher","unstructured":"Sumon RI, Ali H, Akter S, Uddin SM, Mozumder MA, Kim H-C. A deep learning-based approach for precise emotion recognition in domestic animals using EfficientNetB5 architecture, 2025. https:\/\/doi.org\/10.3390\/eng6010009.","DOI":"10.3390\/eng6010009"},{"key":"919_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102735","volume":"115","author":"F Zhang","year":"2025","unstructured":"Zhang F, et al. Towards facial micro-expression detection and classification using modified multimodal ensemble learning approach. Inf Fusion. 2025;115:102735. https:\/\/doi.org\/10.1016\/j.inffus.2024.102735.","journal-title":"Inf Fusion"},{"issue":"9","key":"919_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10091036","volume":"10","author":"MAH Akhand","year":"2021","unstructured":"Akhand MAH, Roy S, Siddique N, Kamal MAS, Shimamura T. Facial emotion recognition using transfer learning in the deep CNN. Electronics. 2021;10(9):1036.","journal-title":"Electronics"},{"key":"919_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124763","volume":"255","author":"D Li","year":"2024","unstructured":"Li D, Qiao N, Liu Y. Micro-expression recognition based on a novel GCN-transformer cooperation model for IoT-eHealth. Expert Syst Appl. 2024;255:124763. https:\/\/doi.org\/10.1016\/j.eswa.2024.124763.","journal-title":"Expert Syst Appl"},{"key":"919_CR20","doi-asserted-by":"publisher","unstructured":"Tagmatova Z, Umirzakova S, Kutlimuratov A, Abdusalomov A, Im Cho Y. A hyper-attentive multimodal transformer for real-time and robust facial expression recognition, 2025. https:\/\/doi.org\/10.3390\/app15137100.","DOI":"10.3390\/app15137100"},{"issue":"1","key":"919_CR21","doi-asserted-by":"publisher","first-page":"13711","DOI":"10.1038\/s41598-025-98610-y","volume":"15","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Lin W, Zhang Y, Xu J, Xu Y. Leveraging vision transformers and entropy-based attention for accurate micro-expression recognition. Sci Rep. 2025;15(1):13711. https:\/\/doi.org\/10.1038\/s41598-025-98610-y.","journal-title":"Sci Rep"},{"issue":"6","key":"919_CR22","doi-asserted-by":"publisher","first-page":"3863","DOI":"10.1007\/s00530-023-01164-0","volume":"29","author":"H Zhou","year":"2023","unstructured":"Zhou H, Huang S, Xu Y. Inceptr: micro-expression recognition integrating inception-CBAM and vision transformer. Multimedia Syst. 2023;29(6):3863\u201376.","journal-title":"Multimedia Syst"},{"key":"919_CR23","doi-asserted-by":"publisher","first-page":"41557","DOI":"10.1109\/ACCESS.2024.3377235","volume":"12","author":"JH Kim","year":"2024","unstructured":"Kim JH, Poulose A, Han DS. CVGG-19: customized visual geometry group deep learning architecture for facial emotion recognition. IEEE Access. 2024;12:41557\u201378. https:\/\/doi.org\/10.1109\/ACCESS.2024.3377235.","journal-title":"IEEE Access"},{"key":"919_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3578178","volume":"74","author":"C-S Jiang","year":"2025","unstructured":"Jiang C-S, Liu Z-T, Fukushima EF, She J. Motion semantic enhancement and autonomous information mining for static-dynamic visual emotion recognition in human\u2013robot interaction. IEEE Trans Instrum Meas. 2025;74:1\u201315. https:\/\/doi.org\/10.1109\/TIM.2025.3578178.","journal-title":"IEEE Trans Instrum Meas"},{"issue":"9","key":"919_CR25","doi-asserted-by":"publisher","first-page":"9943","DOI":"10.1109\/TII.2022.3233650","volume":"19","author":"C-S Jiang","year":"2023","unstructured":"Jiang C-S, Liu Z-T, Wu M, She J, Cao W-H. Efficient facial expression recognition with representation reinforcement network and transfer self-training for human\u2013machine interaction. IEEE Trans Ind Inform. 2023;19(9):9943\u201352. https:\/\/doi.org\/10.1109\/TII.2022.3233650.","journal-title":"IEEE Trans Ind Inform"},{"key":"919_CR26","doi-asserted-by":"publisher","unstructured":"Jiang C-S, Liu Z-T. Facial expression recognition based on multi-scale convolutional vision transformer. In: 2022 13th Asian control conference (ASCC), 2022, pp. 1084\u20131089. https:\/\/doi.org\/10.23919\/ASCC56756.2022.9828211.","DOI":"10.23919\/ASCC56756.2022.9828211"},{"key":"919_CR27","doi-asserted-by":"publisher","DOI":"10.3390\/s25041224","author":"S Muksimova","year":"2025","unstructured":"Muksimova S, Valikhujaev Y, Umirzakova S, Baltayev J, Cho YI. GazeCapsNet: a lightweight gaze estimation framework. Sensors. 2025. https:\/\/doi.org\/10.3390\/s25041224.","journal-title":"Sensors"},{"key":"919_CR28","unstructured":"Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer, 2021. arXiv Prepr. arXiv2110.02178."},{"key":"919_CR29","doi-asserted-by":"crossref","unstructured":"Wu K et al. Tinyvit: fast pretraining distillation for small vision transformers. In: European conference on computer vision, Springer, 2022, pp. 68\u201385.","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"919_CR30","doi-asserted-by":"crossref","unstructured":"Jiang X et al. Dfew: a large-scale database for recognizing dynamic facial expressions in the wild. In: Proceedings of the 28th ACM international conference on multimedia, 2020, pp. 2881\u20132889.","DOI":"10.1145\/3394171.3413620"},{"key":"919_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/tbiom.2025.3546279","author":"F Liu","year":"2025","unstructured":"Liu F, Wang H, Shen S. Robust dynamic facial expression recognition. IEEE Trans Biometrics Behav Identity Sci. 2025. https:\/\/doi.org\/10.1109\/tbiom.2025.3546279.","journal-title":"IEEE Trans Biometrics Behav Identity Sci"},{"key":"919_CR32","doi-asserted-by":"publisher","unstructured":"Mehta S. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer, 2022; 3. https:\/\/doi.org\/10.48550\/arXiv.2110.02178.","DOI":"10.48550\/arXiv.2110.02178"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-026-00919-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-00919-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-00919-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:53:52Z","timestamp":1780444432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-026-00919-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["919"],"URL":"https:\/\/doi.org\/10.1007\/s44163-026-00919-8","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,9]]},"assertion":[{"value":"13 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not Applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"500"}}