{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:22Z","timestamp":1784300122594,"version":"3.55.0"},"reference-count":131,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11263-025-02597-y","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T17:42:58Z","timestamp":1766770978000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding"],"prefix":"10.1007","volume":"134","author":[{"given":"Guo","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoqi","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,26]]},"reference":[{"key":"2597_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J. B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022). Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems, 35, 23716\u201323736.","journal-title":"Advances in neural information processing systems"},{"key":"2597_CR2","first-page":"20014","volume":"34","author":"A Ali","year":"2021","unstructured":"Ali, A., Touvron, H., Caron, M., Bojanowski, P., Douze, M., Joulin, A., Laptev, I., Neverova, N., Synnaeve, G., Verbeek, J., & J\u00e9gou, H. (2021). Xcit:Cross-covariance image transformers., 34, 20014\u201320027.","journal-title":"Xcit:Cross-covariance image transformers."},{"key":"2597_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C. (2021) Vivit: A video vision transformer. In: ICCV, pp 6816\u20136826","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"2597_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A. (2021) Frozen in time: A joint video and image encoder for end-to-end retrieval. In: ICCV, pp 1708\u20131718","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"2597_CR5","unstructured":"Banerjee, S., Lavie, A. (2005) Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372"},{"key":"2597_CR6","unstructured":"Bao, H., Dong, L., Piao, S., & Wei, F. (2022) Beit: BERT pre-training of image transformers. In: ICLR"},{"key":"2597_CR7","unstructured":"Bertasius, G., Wang, H., & Torresani, L. (2021) Is space-time attention all you need for video understanding? Vol. 2, No. 3."},{"key":"2597_CR8","unstructured":"Blakeman, A., Basant, A., Khattar, A., Renduchintala, A., Bercovich, A., Ficek, A., Bjorlin, A., Taghibakhshi, A., Deshmukh, AS., Mahabaleshwarkar, AS et\u00a0al. (2025) Nemotron-h: A family of accurate and efficient hybrid mamba-transformer models. arXiv preprint arXiv:2504.03624"},{"key":"2597_CR9","doi-asserted-by":"crossref","unstructured":"Brill, E., & Moore, RC (2000) An improved error model for noisy channel spelling correction. In: 38th Annual Meeting of the Association for Computational Linguistics, Hong Kong, China, October 1-8, 2000, ACL, pp 286\u2013293","DOI":"10.3115\/1075218.1075255"},{"key":"2597_CR10","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners"},{"key":"2597_CR11","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman, A. (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp 4724\u20134733","DOI":"10.1109\/CVPR.2017.502"},{"key":"2597_CR12","doi-asserted-by":"crossref","unstructured":"Chen, G., Zheng, Y., Wang, L., Lu, T. (2022) DCAN: improving temporal action detection via dual context aggregation. In: AAAI, pp 248\u2013257","DOI":"10.1609\/aaai.v36i1.19900"},{"key":"2597_CR13","unstructured":"Chen, G., Zheng, YD., Wang, J., Xu, J., Huang, Y., Pan, J., Wang, Y., Wang, Y., Qiao, Y., Lu, T et\u00a0al. (2023a) Videollm: Modeling video sequence with large language models. arXiv preprint arXiv:2305.13292"},{"key":"2597_CR14","unstructured":"Chen, G., Li, Z., Wang, S., Jiang, J., Liu, Y., Lu, L., Huang, DA., Byeon, W., Le, M., & Rintamaki, T, et\u00a0al. (2025) Eagle 2.5: Boosting long-context post-training for frontier vision-language models. arXiv preprint arXiv:2504.15271"},{"key":"2597_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wu, J., Wang, W., Su, W., Chen, G., Xing, S., Muyan, Z., Zhang, Q., Zhu, X., Lu, L. et\u00a0al. (2023b) Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14238","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"2597_CR16","unstructured":"Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L et\u00a0al. (2020) Rethinking attention with performers. arXiv preprint arXiv:2009.14794"},{"issue":"1","key":"2597_CR17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., & Wray, M. (2022). Rescaling egocentric vision: Collection, pipeline and challenges for EPIC-KITCHENS-100. IJCV, 130(1), 33\u201355.","journal-title":"IJCV"},{"key":"2597_CR18","unstructured":"Dao, T. (2023) Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691"},{"key":"2597_CR19","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L. (2009) Imagenet: A large-scale hierarchical image database. In: CVPR, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2597_CR20","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, pp 4171\u20134186","DOI":"10.18653\/v1\/N19-1423"},{"key":"2597_CR21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X,. Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR"},{"key":"2597_CR22","unstructured":"Dou, ZY., Yang, X., Nagarajan, T., Wang, H., Huang, J., Peng, N., Kitani, K., & Chu, FJ, (2024) Unlocking exocentric video-language data for egocentric video representation learning. arXiv preprint arXiv:2408.03567"},{"key":"2597_CR23","unstructured":"Duan, Y., Wang, W., Chen, Z., Zhu, X., Lu, L., Lu, T., Qiao, Y., Li, H., Dai, J., & Wang, W. (2024) Vision-rwkv: Efficient and scalable visual perception with rwkv-like architectures. arXiv preprint arXiv:TODO"},{"key":"2597_CR24","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li ,Y., Yan, Z., Malik, J., Feichtenhofer C (2021) Multiscale vision transformers. In: ICCV, pp 6804\u20136815","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"2597_CR25","doi-asserted-by":"crossref","unstructured":"Farha, YA., & Gall, J. (2019) Ms-tcn: Multi-stage temporal convolutional network for action segmentation. In: CVPR, pp 3575\u20133584","DOI":"10.1109\/CVPR.2019.00369"},{"key":"2597_CR26","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., & Rehg, JM. (2011) Learning to recognize objects in egocentric activities. In: CVPR 2011, IEEE, pp 3281\u20133288","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"2597_CR27","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C (2020) X3d: Expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 203\u2013213","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2597_CR28","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: ICCV, pp 6201\u20136210","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2597_CR29","unstructured":"Feichtenhofer C, Fan H, Li Y, He K (2022) Masked autoencoders as spatiotemporal learners"},{"key":"2597_CR30","unstructured":"Fu DY, Dao T, Saab KK, Thomas AW, Rudra A, R\u00e9 C (2022) Hungry hungry hippos: Towards language modeling with state space models. arXiv preprint arXiv:2212.14052"},{"key":"2597_CR31","unstructured":"Fu TJ, Li L, Gan Z, Lin K, Wang WY, Wang L, Liu Z (2021) Violet: End-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681"},{"key":"2597_CR32","doi-asserted-by":"crossref","unstructured":"Fujita S, Hirao T, Kamigaito H, Okumura M, Nagata M (2020) Soda: Story oriented dense video captioning evaluation framework. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI 16, Springer, pp 517\u2013531","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"2597_CR33","doi-asserted-by":"crossref","unstructured":"Furnari A, Farinella GM (2019) What would you expect? anticipating egocentric actions with rolling-unrolling lstms and modality attention. In: ICCV","DOI":"10.1109\/ICCV.2019.00635"},{"key":"2597_CR34","doi-asserted-by":"crossref","unstructured":"Gao J, Sun C, Yang Z, Nevatia R (2017) Tall: Temporal activity localization via language query. In: Proceedings of the IEEE international conference on computer vision, pp 5267\u20135275","DOI":"10.1109\/ICCV.2017.563"},{"key":"2597_CR35","doi-asserted-by":"crossref","unstructured":"Grauman K, Westbury A, Byrne E, Chavis Z, Furnari A, Girdhar R, Hamburger J, Jiang H, Liu M, Liu X, et\u00a0al. (2022) Ego4d: Around the world in 3,000 hours of egocentric video. In: CVPR, pp 18995\u201319012","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"2597_CR36","unstructured":"Gu A, Dao T (2023) Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752"},{"key":"2597_CR37","unstructured":"Gu A, Goel K, R\u00e9 C (2021a) Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396"},{"key":"2597_CR38","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., Saab, K., Dao, T., Rudra, A., & R\u00e9, C. (2021). Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems, 34, 572\u2013585.","journal-title":"Advances in neural information processing systems"},{"key":"2597_CR39","first-page":"35971","volume":"35","author":"A Gu","year":"2022","unstructured":"Gu, A., Goel, K., Gupta, A., & R\u00e9, C. (2022). On the parameterization and initialization of diagonal state space models. Advances in Neural Information Processing Systems, 35, 35971\u201335983.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2597_CR40","unstructured":"Guo Y, Liu J, Li M, Liu Q, Chen X, Tang X (2024) Trace: Temporal grounding video llm via causal event modeling. arXiv preprint arXiv:2410.05643"},{"key":"2597_CR41","doi-asserted-by":"publisher","first-page":"3302","DOI":"10.1609\/aaai.v39i3.32341","volume":"39","author":"Y Guo","year":"2025","unstructured":"Guo, Y., Liu, J., Li, M., Cheng, D., Tang, X., Sui, D., Liu, Q., Chen, X., & Zhao, K. (2025). Vtg-llm: Integrating timestamp knowledge into video llms for enhanced video temporal grounding. Proceedings of the AAAI Conference on Artificial Intelligence, 39, 3302\u20133310.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2597_CR42","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Kautz J (2025) Mambavision: A hybrid mamba-transformer vision backbone. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp 25261\u201325270","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"2597_CR43","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2597_CR44","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick RB (2022) Masked autoencoders are scalable vision learners. In: CVPR, pp 15979\u201315988","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2597_CR45","doi-asserted-by":"crossref","unstructured":"Heilbron FC, Escorcia V, Ghanem B, Niebles JC (2015) Activitynet: A large-scale video benchmark for human activity understanding. In: CVPR, pp 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"issue":"8","key":"2597_CR46","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Comput, 9(8), 1735\u20131780.","journal-title":"Neural Comput"},{"key":"2597_CR47","first-page":"9099","volume":"162","author":"W Hua","year":"2022","unstructured":"Hua, W., Dai, Z., Liu, H., & Le, Q. V. (2022). Transformer quality in linear time., 162, 9099\u20139117.","journal-title":"Transformer quality in linear time."},{"key":"2597_CR48","doi-asserted-by":"crossref","unstructured":"Huang Y, Cai M, Li Z, Sato Y (2018) Predicting gaze in egocentric video by learning task-dependent attention transition. In: Proceedings of the European conference on computer vision (ECCV), pp 754\u2013769","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"2597_CR49","doi-asserted-by":"publisher","first-page":"7795","DOI":"10.1109\/TIP.2020.3007841","volume":"29","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Cai, M., Li, Z., Lu, F., & Sato, Y. (2020). Mutual context network for jointly estimating egocentric gaze and action. IEEE Transactions on Image Processing, 29, 7795\u20137806.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2597_CR50","doi-asserted-by":"crossref","unstructured":"Huang Y, Sugano Y, Sato Y (2020b) Improving action segmentation via graph-based temporal reasoning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14024\u201314034","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"2597_CR51","doi-asserted-by":"crossref","unstructured":"Huang Y, Yang L, Sato Y (2023) Weakly supervised temporal sentence grounding with uncertainty-guided self-training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18908\u201318918","DOI":"10.1109\/CVPR52729.2023.01813"},{"issue":"9","key":"2597_CR52","doi-asserted-by":"publisher","first-page":"3977","DOI":"10.1007\/s11263-024-02017-7","volume":"132","author":"Y Huang","year":"2024","unstructured":"Huang, Y., Yang, L., Chen, G., Zhang, H., Lu, F., & Sato, Y. (2024). Matching compound prototypes for few-shot action recognition. International Journal of Computer Vision, 132(9), 3977\u20134002.","journal-title":"International Journal of Computer Vision"},{"key":"2597_CR53","first-page":"448","volume":"37","author":"S Ioffe","year":"2015","unstructured":"Ioffe, S. (2015). Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift., 37, 448\u2013456.","journal-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift."},{"key":"2597_CR54","doi-asserted-by":"crossref","unstructured":"Islam MM, Bertasius G (2022) Long movie clip classification with state-space video models. In: European Conference on Computer Vision, Springer, pp 87\u2013104","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"2597_CR55","unstructured":"Jia C, Yang Y, Xia Y, Chen YT, Parekh Z, Pham H, Le Q, Sung YH, Li Z, Duerig T (2021) Scaling up visual and vision-language representation learning with noisy text supervision. In: International conference on machine learning, PMLR, pp 4904\u20134916"},{"key":"2597_CR56","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev P, Suleyman M, Zisserman A (2017) The kinetics human action video dataset. CoRR abs\/1705.06950"},{"key":"2597_CR57","doi-asserted-by":"crossref","unstructured":"Kuehne H, Arslan A, Serre T (2014) The language of actions: Recovering the syntax and semantics of goal-directed human activities. In: CVPR, pp 780\u2013787","DOI":"10.1109\/CVPR.2014.105"},{"key":"2597_CR58","unstructured":"Lei J, Berg TL, Bansal M (2021) Detecting moments and highlights in videos via natural language queries. pp 11846\u201311858"},{"key":"2597_CR59","unstructured":"Li K, Wang Y, Gao P, Song G, Liu Y, Li H, Qiao Y (2023a) Uniformer: Unified transformer for efficient spatiotemporal representation learning. IEEE TPAMI"},{"key":"2597_CR60","doi-asserted-by":"crossref","unstructured":"Li K, Wang Y, Li Y, Wang Y, He Y, Wang L, Qiao Y (2023b) Unmasked teacher: Towards training-efficient video foundation models. CoRR abs\/2303.16058","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"2597_CR61","doi-asserted-by":"crossref","unstructured":"Li K, Wang Y, Li Y, Wang Y, He Y, Wang L, Qiao Y (2023c) Unmasked teacher: Towards training-efficient video foundation models. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 19948\u201319960","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"2597_CR62","unstructured":"Lieber O, Lenz B, Bata H, Cohen G, Osin J, Dalmedigos I, Safahi E, Meirom S, Belinkov Y, Shalev-Shwartz S, et\u00a0al. (2024) Jamba: A hybrid transformer-mamba language model. arXiv preprint arXiv:2403.19887"},{"key":"2597_CR63","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"},{"key":"2597_CR64","doi-asserted-by":"crossref","unstructured":"Lin J, Gan C, Han S (2019) TSM: temporal shift module for efficient video understanding. In: ICCV, pp 7082\u20137092","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2597_CR65","unstructured":"Lin KQ, Wang J, Soldan M, Wray M, Yan R, Xu EZ, Gao D, Tu R, Zhao W, Kong W, Cai C, Wang H, Damen D, Ghanem B, Liu W, Shou MZ (2022) Egocentric video-language pretraining"},{"key":"2597_CR66","doi-asserted-by":"crossref","unstructured":"Lin KQ, Zhang P, Chen J, Pramanick S, Gao D, Wang AJ, Yan R, Shou MZ (2023) Univtg: Towards unified video-language temporal grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2794\u20132804","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"2597_CR67","first-page":"3","volume":"11208","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., & Yang, M. (2018). BSN: boundary sensitive network for temporal action proposal generation. ECCV, 11208, 3\u201321.","journal-title":"ECCV"},{"key":"2597_CR68","doi-asserted-by":"crossref","unstructured":"Liu Y, Li S, Wu Y, Chen CW, Shan Y, Qie X (2022a) Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection. In: CVPR, pp 3042\u20133051","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"2597_CR69","unstructured":"Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Liu Y (2024) Vmamba: Visual state space model. arXiv preprint arXiv:2401.10166"},{"key":"2597_CR70","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp 9992\u201310002","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2597_CR71","doi-asserted-by":"crossref","unstructured":"Liu Z, Ning J, Cao Y, Wei Y, Zhang Z, Lin S, Hu H (2022b) Video swin transformer. In: CVPR, pp 3192\u20133201","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2597_CR72","unstructured":"Luo H, Ji L, Shi B, Huang H, Duan N, Li T, Li J, Bharti T, Zhou M (2020) Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353"},{"key":"2597_CR73","unstructured":"Mangalam K, Akshulakov R, Malik J (2024) Egoschema: A diagnostic benchmark for very long-form video language understanding. Advances in Neural Information Processing Systems 36"},{"key":"2597_CR74","unstructured":"Mehta H, Gupta A, Cutkosky A, Neyshabur B (2022) Long range language modeling via gated state spaces. arXiv preprint arXiv:2206.13947"},{"key":"2597_CR75","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"2597_CR76","unstructured":"Pei B, Huang Y, Xu J, Chen G, He Y, Yang L, Wang Y, Xie W, Qiao Y, Wu F, et\u00a0al. (2025) Modeling fine-grained hand-object dynamics for egocentric video representation learning. arXiv preprint arXiv:2503.00986"},{"key":"2597_CR77","doi-asserted-by":"crossref","unstructured":"Peng B, Alcaide E, Anthony Q, Albalak A, Arcadinho S, Cao H, Cheng X, Chung M, Grella M, GV KK, et\u00a0al. (2023) Rwkv: Reinventing rnns for the transformer era. arXiv preprint arXiv:2305.13048","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"2597_CR78","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3d residual networks. In: ICCV, pp 5534\u20135542","DOI":"10.1109\/ICCV.2017.590"},{"issue":"8","key":"2597_CR79","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.","journal-title":"OpenAI blog"},{"key":"2597_CR80","first-page":"8748","volume":"139","author":"A Radford","year":"2021","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., & Krueger, G. (2021). Sutskever I. Learning transferable visual models from natural language supervision., 139, 8748\u20138763.","journal-title":"Learning transferable visual models from natural language supervision."},{"key":"2597_CR81","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:140:1\u2013140:67"},{"key":"2597_CR82","doi-asserted-by":"crossref","unstructured":"Ren S, Yao L, Li S, Sun X, Hou L (2024) Timechat: A time-sensitive multimodal large language model for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14313\u201314323","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"2597_CR83","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"2597_CR84","unstructured":"Sharir G, Noy A, Zelnik-Manor L (2021) An image is worth 16x16 words, what is a video worth? arXiv preprint arXiv:2103.13915"},{"key":"2597_CR85","unstructured":"Smith JT, Warrington A, Linderman SW (2022) Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933"},{"key":"2597_CR86","doi-asserted-by":"crossref","unstructured":"Sun C, Myers A, Vondrick C, Murphy K, Schmid C (2019) Videobert: A joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7464\u20137473","DOI":"10.1109\/ICCV.2019.00756"},{"key":"2597_CR87","unstructured":"Sun Y, Dong L, Huang S, Ma S, Xia Y, Xue J, Wang J, Wei F (2023) Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621"},{"issue":"12","key":"2597_CR88","doi-asserted-by":"publisher","first-page":"8238","DOI":"10.1109\/TCSVT.2021.3085907","volume":"32","author":"Z Tang","year":"2021","unstructured":"Tang, Z., Liao, Y., Liu, S., Li, G., Jin, X., Jiang, H., Yu, Q., & Xu, D. (2021). Human-centric spatio-temporal video grounding with visual transformers. IEEE Transactions on Circuits and Systems for Video Technology, 32(12), 8238\u20138249.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2597_CR89","unstructured":"Tong Z, Song Y, Wang J, Wang L (2022) Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS"},{"key":"2597_CR90","first-page":"10347","volume":"139","author":"H Touvron","year":"2021","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., & Sablayrolles, A. (2021). J\u00e9gou H. Training data-efficient image transformers & distillation through attention., 139, 10347\u201310357.","journal-title":"Training data-efficient image transformers & distillation through attention."},{"key":"2597_CR91","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A, Grave E, Lample G (2023a) Llama: Open and efficient foundation language models. CoRR abs\/2302.13971"},{"key":"2597_CR92","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, et\u00a0al. (2023b) Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"2597_CR93","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, et\u00a0al. (2023c) Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"2597_CR94","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev LD, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"2597_CR95","unstructured":"Tran D, Ray J, Shou Z, Chang S, Paluri M (2017) Convnet architecture search for spatiotemporal feature learning. CoRR abs\/1708.05038"},{"key":"2597_CR96","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2597_CR97","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Feiszli M, Torresani L (2019) Video classification with channel-separated convolutional networks. In: ICCV, pp 5551\u20135560","DOI":"10.1109\/ICCV.2019.00565"},{"key":"2597_CR98","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1109\/ACCESS.2017.2778011","volume":"6","author":"A Ullah","year":"2017","unstructured":"Ullah, A., Ahmad, J., Muhammad, K., Sajjad, M., & Baik, S. W. (2017). Action recognition in video sequences using deep bi-directional lstm with cnn features. IEEE access, 6, 1155\u20131166.","journal-title":"IEEE access"},{"key":"2597_CR99","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NeurIPS, pp 5998\u20136008"},{"key":"2597_CR100","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence\u00a0Zitnick C, Parikh D (2015) Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2597_CR101","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Rohrbach M, Donahue J, Mooney R, Darrell T, Saenko K (2015) Sequence to sequence-video to text. In: Proceedings of the IEEE international conference on computer vision, pp 4534\u20134542","DOI":"10.1109\/ICCV.2015.515"},{"key":"2597_CR102","doi-asserted-by":"crossref","unstructured":"Wang J, Chen G, Huang Y, Wang L, Lu T (2023a) Memory-and-anticipation transformer for online action understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 13824\u201313835","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"2597_CR103","doi-asserted-by":"crossref","unstructured":"Wang, J., Ge, Y., Yan, R., Ge, Y., Lin, KQ., Tsutsui, S., Lin, X., Cai, G., Wu, J., Shan, Y., Qie, X., Shou, MZ. (2023b) All in one: Exploring unified video-language pre-training. In: CVPR, pp 6598\u20136608","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"2597_CR104","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhu, W., Wang, P., Yu, X., Liu, L., Omar, M., Hamid, R. (2023c) Selective structured state-spaces for long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6387\u20136397","DOI":"10.1109\/CVPR52729.2023.00618"},{"issue":"11","key":"2597_CR105","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L. V. (2019). Temporal segment networks for action recognition in videos. IEEE TPAMI, 41(11), 2740\u20132755.","journal-title":"IEEE TPAMI"},{"key":"2597_CR106","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G. (2021a) TDN: temporal difference networks for efficient action recognition. In: CVPR, pp 1895\u20131904","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"2597_CR107","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., Qiao, Y. (2023d) VideoMAE V2: scaling video masked autoencoders with dual masking. In: CVPR, pp 14549\u201314560","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"2597_CR108","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, R., Lu, Z., Zheng, F., Cheng, R., Luo, P. (2021b) End-to-end dense video captioning with parallel decoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6847\u20136857","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"2597_CR109","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, DP., Song, K., Liang, D., Lu, T., Luo, P., Shao, L. (2021c) Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: ICCV, pp 568\u2013578","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2597_CR110","unstructured":"Wang, Y., Li, K., Li, Y., He, Y., Huang, B., Zhao, Z., Zhang, H., Xu, J., Liu, Y., Wang, Z., Xing, S., Chen, G., Pan, J., Yu, J., Wang, Y., Wang, L., & Qiao, Y. (2022) Internvideo: General video foundation models via generative and discriminative learning. CoRR abs\/2212.03191"},{"key":"2597_CR111","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, K., Li, X., Yu, J., He, Y., Chen, G., Pei, B., Zheng, R., Wang, Z., Shi, Y., et\u00a0al. (2024) Internvideo2: Scaling foundation models for multimodal video understanding. In: European Conference on Computer Vision, Springer, pp 396\u2013416","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"2597_CR112","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, S., Stengel-Eskin, E., Yoon, J., Cheng, F., Bertasius, G., & Bansal, M. (2025) Videotree: Adaptive tree-based video representation for llm reasoning on long videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp 3272\u20133283","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"2597_CR113","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, CY., & Yuille, A., Feichtenhofer, C. (2022) Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14668\u201314678","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"2597_CR114","doi-asserted-by":"crossref","unstructured":"Wu, CY., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., & Girshick, R. (2019) Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 284\u2013293","DOI":"10.1109\/CVPR.2019.00037"},{"key":"2597_CR115","doi-asserted-by":"crossref","unstructured":"Wu,CY., Li, Y., Mangalam, K., Fan, H., Xiong, B., Malik, J., & Feichtenhofer, C. (2022) Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13587\u201313597","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"2597_CR116","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, RB., Doll\u00e1r P, Tu Z., & He, K. (2017) Aggregated residual transformations for deep neural networks. In: CVPR, pp 5987\u20135995","DOI":"10.1109\/CVPR.2017.634"},{"key":"2597_CR117","first-page":"318","volume":"11219","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018). Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. ECCV, 11219, 318\u2013335.","journal-title":"ECCV"},{"key":"2597_CR118","first-page":"124","volume":"35","author":"A Yang","year":"2022","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., & Schmid, C. (2022). Zero-shot video question answering via frozen bidirectional language models. Advances in Neural Information Processing Systems, 35, 124\u2013141.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2597_CR119","doi-asserted-by":"crossref","unstructured":"Yang, A., Nagrani, A., Seo, PH., Miech, A., Pont-Tuset, J., Laptev, I., Sivic, J., & Schmid, C. (2023) Vid2seq: Large-scale pretraining of a visual language model for dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10714\u201310726","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"2597_CR120","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xing, Z., Yu, L., Huang, C., Fu, H., & Zhu, L. (2024) Vivim: A video vision mamba for medical video segmentation. arXiv preprint arXiv:2401.14168","DOI":"10.1109\/TCSVT.2025.3563411"},{"key":"2597_CR121","doi-asserted-by":"crossref","unstructured":"Yi, F., Wen, H., & Jiang, T. (2021) Asformer: Transformer for action segmentation. In: BMVC, p 236","DOI":"10.5244\/C.35.49"},{"key":"2597_CR122","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wu, J., & Li, Y. (2022) Actionformer: Localizing moments of actions with transformers. In: Avidan S, Brostow GJ, Ciss\u00e9 M, Farinella GM, Hassner T (eds) ECCV, vol 13664, pp 492\u2013510","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"2597_CR123","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., & Zhou, JT. (2020) Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"2597_CR124","unstructured":"Zhang, Y., Wu, J., Li, W., Li, B., Ma, Z., Liu, Z., Li, C. (2024) Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713"},{"key":"2597_CR125","doi-asserted-by":"crossref","unstructured":"Zhao, H., Torralba, A., Torresani, L., Yan, Z. (2019) HACS: human action clips and segments dataset for recognition and temporal localization. In: ICCV, IEEE, pp 8667\u20138677","DOI":"10.1109\/ICCV.2019.00876"},{"key":"2597_CR126","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P. (2022) Real-time online video detection with temporal smoothing transformers. In: ECCV, Springer, pp 485\u2013502","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"2597_CR127","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P. (2023) Training a large video model on a single machine in a day. arXiv preprint arXiv:2309.16669"},{"key":"2597_CR128","doi-asserted-by":"crossref","unstructured":"Zhao Y, Misra I, Kr\u00e4henb\u00fchl P, Girdhar R (2023) Learning video representations from large language models. In: CVPR, IEEE, pp 6586\u20136597","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"2597_CR129","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., & Corso, J. (2018) Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol\u00a032","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"2597_CR130","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024) Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417"},{"key":"2597_CR131","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2021) Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02597-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02597-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02597-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:43:53Z","timestamp":1771602233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02597-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,26]]},"references-count":131,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2597"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02597-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,26]]},"assertion":[{"value":"30 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"20"}}