{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T05:42:42Z","timestamp":1785994962689,"version":"3.56.0"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733468","type":"print"},{"value":"9783031733475","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73347-5_14","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"237-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":288,"title":["VideoMamba: State Space Model for\u00a0Efficient Video Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-0341","authenticated-orcid":false,"given":"Kunchang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0382-3985","authenticated-orcid":false,"given":"Xinhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6200-9938","authenticated-orcid":false,"given":"Yinan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8415-790X","authenticated-orcid":false,"given":"Yali","family":"Wang","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"14_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML (2021)"},{"key":"14_CR5","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"14_CR6","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"14_CR7","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. ArXiv abs\/1808.01340 (2018)"},{"key":"14_CR8","unstructured":"Carreira, J., Noland, E., Hillier, C., Zisserman, A.: A short note on the kinetics-700 human action dataset. ArXiv abs\/1907.06987 (2019)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"14_CR10","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL (2011)"},{"key":"14_CR11","unstructured":"Chen, G., et al.: Video mamba suite: state space model as a versatile alternative for video understanding. ArXiv abs\/2403.09626 (2024)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Cho, J.H., Hariharan, B.: On the efficacy of knowledge distillation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00489"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J.: A thousand frames in just a few words: lingual description of videos through latent topics and sparse object stitching. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv abs\/1810.04805 (2018)"},{"key":"14_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"14_CR19","unstructured":"Feichtenhofer, C., Fan, H., Li, Y., He, K.: Masked autoencoders as spatiotemporal learners. In: NeurIPS (2022)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"14_CR21","unstructured":"Fu, D.Y., Dao, T., Saab, K.K., Thomas, A.W., Rudra, A., R\u00e9, C.: Hungry hungry hippos: Towards language modeling with state space models. In: ICLR (2023)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: Temporal activity localization via language query. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Ge, Y., et al.: Bridging video-text retrieval with multiple choice questions. In: CVP (2022)","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"14_CR25","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. ArXiv abs\/2312.00752 (2023)"},{"key":"14_CR26","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: ICLR (2022)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: Ava: A video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Guo, H., Li, J., Dai, T., Ouyang, Z., Ren, X., Xia, S.T.: MambaIR: a simple baseline for image restoration with state-space model. ArXiv abs\/2402.15648 (2024)","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"14_CR29","unstructured":"Han, T., Xie, W., Zisserman, A.: Turbo training with token dropout. In: BMVC (2022)"},{"key":"14_CR30","unstructured":"He, X., et al.: Pan-mamba: Effective pan-sharpening with state space model. ArXiv abs\/2402.12192 (2024)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Hu, V.T., et al.: ZigMa: a DiT-style zigzag mamba diffusion model. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.M.: Timeception for complex action recognition. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00034"},{"key":"14_CR34","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.M.: VideoGraph: recognizing minutes-long human activities in videos. ArXiv abs\/1905.05143 (2019)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild\u201d. Comput. Vis. Image Underst. 155, 1\u201323 (2017)","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Bertasius, G.: Long movie clip classification with state-space video models. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"14_CR37","unstructured":"Kay, W., et al.: The kinetics human action video dataset. ArXiv abs\/1705.06950 (2017)"},{"key":"14_CR38","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"14_CR39","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Revealing single frame bias for video-and-language learning. ArXiv abs\/2206.03428 (2022)"},{"key":"14_CR40","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS (2021)"},{"key":"14_CR41","unstructured":"Li, K., Li, X., Wang, Y., Wang, J., Qiao, Y.: CT-Net: channel tensorization network for video classification. In: ICLR (2020)"},{"key":"14_CR42","unstructured":"Li, K., et al.: UniFormerV2: spatiotemporal learning by arming image ViTs with video UniFormer. In: ICCV (2023)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Unmasked teacher: towards training-efficient video foundation models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"14_CR44","unstructured":"Li, K., et al.: UniFormer: unified transformer for efficient spatial-temporal representation learning. In: ICLR (2022)"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: Improved multiscale vision transformers for classification and detection. ArXiv abs\/2112.01526 (2021)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Liang, D., et al.: PointMamba: a simple state space model for point cloud analysis. ArXiv abs\/2402.10739 (2024)","DOI":"10.2139\/ssrn.5036327"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Lin, X., Petroni, F., Bertasius, G., Rohrbach, M., Chang, S.F., Torresani, L.: Learning to recognize procedural activities with distant supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"14_CR48","unstructured":"Liu, H., Yan, W., Zaharia, M., Abbeel, P.: World model on million-length video and language with ringattention. ArXiv abs\/2402.08268 (2024)"},{"key":"14_CR49","doi-asserted-by":"publisher","first-page":"6937","DOI":"10.1109\/TIP.2022.3217368","volume":"31","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, L., Wang, Y., Ma, X., Qiao, Y.: FineAction: a fine-grained video dataset for temporal action localization. Trans. Image Process. 31, 6937\u20136950 (2022)","journal-title":"Trans. Image Process."},{"key":"14_CR50","unstructured":"Liu, Y., et al.: VMamba: visual state space model. ArXiv abs\/2401.10166 (2024)"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"14_CR53","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"14_CR54","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. NeurIPS (2019)"},{"key":"14_CR55","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"14_CR56","unstructured":"Ma, J., Li, F., Wang, B.: U-Mamba: enhancing long-range dependency for biomedical image segmentation. ArXiv abs\/2401.04722 (2024)"},{"key":"14_CR57","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. ArXiv abs\/2206.13947 (2022)"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"14_CR59","unstructured":"Nguyen, E., et al.: S4ND: modeling images and videos as multidimensional signals with state spaces. In: NeurIPS (2022)"},{"key":"14_CR60","unstructured":"Patrick, M., et al.: Keeping your eye on the ball: trajectory attention in video transformers. In: NeurIPS (2021)"},{"key":"14_CR61","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"issue":"1","key":"14_CR62","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11263-016-0987-1","volume":"123","author":"A Rohrbach","year":"2017","unstructured":"Rohrbach, A., et al.: Movie description. Int. J. Comput. Vis. 123(1), 94\u2013120 (2017). https:\/\/doi.org\/10.1007\/s11263-016-0987-1","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR63","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"14_CR64","unstructured":"Sharir, G., Noy, A., Zelnik-Manor, L.: An image is worth 16$$\\times $$16 words, what is a video worth? ArXiv abs\/2103.13915 (2021)"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"14_CR66","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. NeurIPS (2014)"},{"key":"14_CR67","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. In: ICLR (2023)"},{"key":"14_CR68","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"14_CR69","unstructured":"Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. ArXiv abs\/2104.09864 (2021)"},{"key":"14_CR70","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"14_CR71","unstructured":"Sun, Y., et al.: Retentive network: a successor to transformer for large language models. ArXiv abs\/2307.08621 (2023)"},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: COIN: a large-scale dataset for comprehensive instructional video analysis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00130"},{"key":"14_CR73","unstructured":"Team, G.: Gemini: A family of highly capable multimodal models. ArXiv abs\/2312.11805 (2023)"},{"key":"14_CR74","unstructured":"Team, R.: RWKV: Reinventing RNNs for the transformer era. In: EMNLP (2023)"},{"key":"14_CR75","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)"},{"key":"14_CR76","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u2019egou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"14_CR77","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"14_CR78","doi-asserted-by":"crossref","unstructured":"Tran, D., xiu Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"14_CR79","unstructured":"Wang, C., Tsepa, O., Ma, J., Wang, B.: Graph-Mamba: towards long-range graph sequence modeling with selective state spaces. ArXiv abs\/2402.00789 (2024)"},{"key":"14_CR80","unstructured":"Wang, J., Yan, J.N., Gu, A., Rush, A.M.: Pretraining without attention. ArXiv abs\/2212.10544 (2022)"},{"key":"14_CR81","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"14_CR82","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"14_CR83","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BEVT: BERT pretraining of video transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"14_CR84","unstructured":"Wang, Y., et al.: InternVid: a large-scale video-text dataset for multimodal understanding and generation. In: ICLR (2024)"},{"key":"14_CR85","unstructured":"Wang, Y., et al.: InternVideo: general video foundation models via generative and discriminative learning. ArXiv abs\/2212.03191 (2022)"},{"key":"14_CR86","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Krahenbuhl, P.: Towards long-form video understanding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"14_CR87","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"14_CR88","unstructured":"Yang, Y., Xing, Z., Zhu, L.: Vivim: a video vision mamba for medical video object segmentation. ArXiv abs\/2401.14168 (2024)"},{"key":"14_CR89","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: ActivityNet-QA: a dataset for understanding complex web videos via question answering. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"14_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: MorphMLP: an efficient MLP-like backbone for spatial-temporal representation learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_14"},{"key":"14_CR91","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: Efficient visual representation learning with bidirectional state space model. ArXiv abs\/2401.09417 (2024)"},{"key":"14_CR92","doi-asserted-by":"crossref","unstructured":"Zhuang, S., et al.: Vlogger: Make your dream a vlog. ArXiv abs\/2401.09414 (2024)","DOI":"10.1109\/CVPR52733.2024.00841"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73347-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:32:35Z","timestamp":1732962755000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}