{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T01:20:14Z","timestamp":1769476814592,"version":"3.49.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T00:00:00Z","timestamp":1765584000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T00:00:00Z","timestamp":1765584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00138-025-01774-w","type":"journal-article","created":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T12:14:24Z","timestamp":1765628064000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal adaptive fusion for enhanced long-term action anticipation"],"prefix":"10.1007","volume":"37","author":[{"given":"Yaoyao","family":"Jing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keming","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzhe","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,13]]},"reference":[{"issue":"11","key":"1774_CR1","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","volume":"43","author":"A Furnari","year":"2021","unstructured":"Furnari, A., Farinella, G.M.: Rolling-unrolling lstms for action anticipation from first-person video. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4021\u20134036 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"1774_CR2","doi-asserted-by":"publisher","first-page":"6688","DOI":"10.1109\/TPAMI.2020.3008558","volume":"45","author":"F Marchetti","year":"2023","unstructured":"Marchetti, F., Becattini, F., Seidenari, L., Bimbo, A.D.: Multiple trajectory prediction of moving agents with memory augmented networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6688\u20136702 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1774_CR3","doi-asserted-by":"crossref","unstructured":"Hawkins, K.P., Vo, N., Bansal, S., Bobick, A.F.: Probabilistic human action prediction and wait-sensitive planning for responsive human-robot collaboration. In 2013 13th IEEE-RAS international conference on humanoid robots (Humanoids), pp. 499\u2013506, (2013)","DOI":"10.1109\/HUMANOIDS.2013.7030020"},{"issue":"6","key":"1774_CR4","doi-asserted-by":"publisher","first-page":"6715","DOI":"10.1109\/TPAMI.2021.3059923","volume":"45","author":"Z Qi","year":"2023","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Self-regulated learning for egocentric video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6715\u20136730 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1774_CR5","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Richard, A., Gall, J.: When will you do what?\u2013anticipating temporal occurrences of activities. In 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, Computer Vision Foundation \/ IEEE Computer Society, 2018) June 18\u201322, pp. 5343\u20135352 (2018)","DOI":"10.1109\/CVPR.2018.00560"},{"key":"1774_CR6","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In 2021 IEEE\/CVF international conference on computer vision, ICCV 2021, IEEE. Montreal, QC, Canada, October 10\u201317, 2021, pp. 13485\u201313495 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"1774_CR7","doi-asserted-by":"crossref","unstructured":"Gong, D., Lee, J., Kim, M., Ha, S.J., Cho, M.: Future transformer for long-term action anticipation. In 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"1774_CR8","doi-asserted-by":"crossref","unstructured":"Nawhal, M., Jyothi, A.A., Mori, G.: Rethinking learning approaches for long-term action anticipation. In computer vision\u2013ECCV 2022, lecture notes in computer science, In 17th European conference on computer vision (ECCV 2022) Springer, Berlin, pp. 558\u2013576 (2022).","DOI":"10.1007\/978-3-031-19830-4_32"},{"key":"1774_CR9","doi-asserted-by":"crossref","unstructured":"Girase, H., Agarwal, N., Choi, C., Mangalam, K.: Latency matters: real-time action forecasting transformer. In IEEE\/CVF conference on computer vision and pattern recognition, CVPR 2023, Vancouver, IEEE. BC, Canada, June 17-24, 2023, pp. 18759\u201318769 (2023)","DOI":"10.1109\/CVPR52729.2023.01799"},{"key":"1774_CR10","doi-asserted-by":"crossref","unstructured":"Wang, B., Tian, Y., Wang, C., Yang, L.: Llmaction: Adapting large language model for long-term action anticipation. In Zhouchen Lin and et\u00a0al., editors, Pattern recognition and computer vision, volume 15040 of Lecture Notes in Computer Science, In 7th Chinese conference on pattern recognition and computer vision (PRCV 2024) pp. 269\u2013283. Springer, Singapore, (2025).","DOI":"10.1007\/978-981-97-8792-0_19"},{"key":"1774_CR11","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: Recovering the syntax and semantics of goal-directed human activities. In 2014 IEEE conference on computer vision and pattern recognition, pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"1774_CR12","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In Proceedings of the 2013 ACM international joint conference on pervasive and ubiquitous computing, UbiComp \u201913, ACM. pp. 729\u2013738 (2013)","DOI":"10.1145\/2493432.2493482"},{"issue":"1","key":"1774_CR13","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1007\/s10489-022-03470-y","volume":"53","author":"K Mao","year":"2023","unstructured":"Mao, K., Jin, P., Ping, Y., Tang, B.: Modeling multi-scale sub-group context for group activity recognition. Appl. Intell. 53(1), 1149\u20131161 (2023)","journal-title":"Appl. Intell."},{"key":"1774_CR14","doi-asserted-by":"publisher","first-page":"103443","DOI":"10.1109\/ACCESS.2020.2999503","volume":"8","author":"B Wang","year":"2020","unstructured":"Wang, B., Yu, J., Wang, K., Bao, X., Mao, K.: Fall detection based on dual-channel feature integration. IEEE Access 8, 103443\u2013103453 (2020)","journal-title":"IEEE Access"},{"key":"1774_CR15","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: Uncertainty-aware anticipation of activities. In 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW), pp. 1197\u20131204 (2019)","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"1774_CR16","doi-asserted-by":"crossref","unstructured":"Sener, F., Singhania, D., Yao, A.: Temporal aggregate representations for long-range video understanding. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, editors, Computer Vision\u2013ECCV 2020\u201316th European conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XVI, volume 12361 of Lecture Notes in Computer Science, pages 154\u2013171. Springer, (2020)","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"1774_CR17","doi-asserted-by":"crossref","unstructured":"Furnari, A., Farinella, G.: What would you expect? anticipating egocentric actions with rolling-unrolling lstms and modality attention. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pages 6251\u20136260, (2019)","DOI":"10.1109\/ICCV.2019.00635"},{"key":"1774_CR18","doi-asserted-by":"crossref","unstructured":"Mascar\u00f3, E.V., Ahn, H., Lee, D.: Intention-conditioned long-term human egocentric action anticipation. In 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pages 6037\u20136046, (2023)","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"1774_CR19","doi-asserted-by":"crossref","unstructured":"Roy, D., Fernando, B.: Action anticipation using latent goal learning. In 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pages 808\u2013816, (2022)","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"1774_CR20","doi-asserted-by":"crossref","unstructured":"Roy, D., Fernando, B.: Predicting the next action by modeling the abstract goal. In Apostolos Antonacopoulos, Swapan Chaudhuri, Rama Chellappa, Cheng-Lin Liu, Subhasish Bhattacharya, and Umapada Pal, editors, Pattern Recognition, volume 15315 of Lecture Notes in Computer Science, page 162\u2013177, Cham, (2025). Springer. 26th International Conference on Pattern Recognition (ICPR 2024)","DOI":"10.1007\/978-3-031-78354-8_11"},{"key":"1774_CR21","doi-asserted-by":"crossref","unstructured":"Jain, A., Singh, A., Koppula, H.S., Soh, S., Saxena, A.: Recurrent neural networks for driver activity anticipation via sensory-fusion architecture. In 2016 IEEE International Conference on Robotics and Automation (ICRA), pages 3118\u20133125, (2016)","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"1774_CR22","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Schneider, D., Voit, M., Stiefelhagen, R., Beyerer, J.: Anticipative feature fusion transformer for multi-modal action anticipation. In 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pages 6057\u20136066, (2023)","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"1774_CR23","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research, pages 8748\u20138763. PMLR, (2021)"},{"key":"1774_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103633","volume":"126","author":"M Xing","year":"2026","unstructured":"Xing, M., Feng, Z., Zhu, S., Su, Y., Gribova, V.V., Filaretoy, V.F., Huang, D.: Unbiased spatial-temporal atomic fusion-based zero-shot action recognition. Inf. Fusion 126, 103633 (2026)","journal-title":"Inf. Fusion"},{"key":"1774_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2020.102380","volume":"113","author":"Y Su","year":"2021","unstructured":"Su, Y., Xing, M., An, S., Peng, W., Feng, Z.: VDARN: video disentangling attentive relation network for few-shot and zero-shot action recognition. Ad Hoc Netw. 113, 102380 (2021)","journal-title":"Ad Hoc Netw."},{"key":"1774_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110898","volume":"157","author":"Y Su","year":"2025","unstructured":"Su, Y., Tan, Y., An, S., Xing, M., Feng, Z.: Semantic-driven dual consistency learning for weakly supervised video anomaly detection. Pattern Recognit. 157, 110898 (2025)","journal-title":"Pattern Recognit."},{"key":"1774_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna\u00a0M. Wallach, Rob Fergus, S.\u00a0V.\u00a0N. Vishwanathan, and Roman Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 5998\u20136008, (2017)"},{"key":"1774_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-3-030-71278-5_12","volume-title":"Pattern Recognition","author":"YA Farha","year":"2021","unstructured":"Farha, Y.A., Ke, Q., Schiele, B., Gall, J.: Long-term anticipation of activities with cycle consistency. In: Akata, Z., Geiger, A., Sattler, T. (eds.) Pattern Recognition. Lecture Notes in Computer Science, vol. 12544, pp. 159\u2013173. Springer, Cham (2021)"},{"key":"1774_CR29","doi-asserted-by":"crossref","unstructured":"Gong, D., Lee, J., Kim, M., Ha, S.J., Cho, M.: Future transformer for long-term action anticipation. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3042\u20133051, (2022)","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"1774_CR30","unstructured":"Gupta, A., Liu, J., Bo, L., Roy-Chowdhury, A.K., Mei, T.: A-act: Action anticipation through cycle transformations, (2022)"},{"key":"1774_CR31","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: Uncertainty-aware anticipation of activities. In 2019 IEEE\/CVF International Conference on Computer Vision Workshops, ICCV Workshops 2019, Seoul, Korea (South), October 27-28, 2019, pages 1197\u20131204. IEEE, (2019)","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"1774_CR32","doi-asserted-by":"crossref","unstructured":"Ke, Q., Fritz, M., Schiele, B.: Time-conditioned action anticipation in one shot. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 9925\u20139934. Computer Vision Foundation \/ IEEE, (2019)","DOI":"10.1109\/CVPR.2019.01016"},{"key":"1774_CR33","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Ke, Q., Schiele, B., Gall, J.: Long-term anticipation of activities with cycle consistency. In Zeynep Akata, Andreas Geiger, and Torsten Sattler, editors, Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, T\u00fcbingen, Germany, September 28 - October 1, 2020, Proceedings, volume 12544 of Lecture Notes in Computer Science, pages 159\u2013173. Springer, (2020)","DOI":"10.1007\/978-3-030-71278-5_12"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01774-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-025-01774-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01774-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T15:08:00Z","timestamp":1769440080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-025-01774-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,13]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["1774"],"URL":"https:\/\/doi.org\/10.1007\/s00138-025-01774-w","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,13]]},"assertion":[{"value":"31 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"15"}}