{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:13:53Z","timestamp":1778080433682,"version":"3.51.4"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730092","type":"print"},{"value":"9783031730108","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73010-8_25","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:10:07Z","timestamp":1731157807000},"page":"425-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["ZeroI2V: Zero-Cost Adaptation of\u00a0Pre-trained Transformers from\u00a0Image to\u00a0Video"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0382-3985","authenticated-orcid":false,"given":"Xinhao","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1539-2609","authenticated-orcid":false,"given":"Yuhan","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: ViViT: a video vision transformer. In: International Conference on Computer Vision, pp. 6816\u20136826 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"25_CR2","unstructured":"Ba, L.J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"25_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: bert pre-training of image transformers. In: International Conference on Learning Representations (2022)"},{"key":"25_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, vol.\u00a0139, pp. 813\u2013824 (2021)"},{"key":"25_CR5","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. Adv. Neural Inform. Process. Syst. 33, 1877\u20131901 (2020)"},{"key":"25_CR6","unstructured":"Bulat, A., P\u00e9rez-R\u00faa, J., Sudhakaran, S., Mart\u00ednez, B., Tzimiropoulos, G.: Space-time mixing attention for video transformer. Adv. Neural Inform. Process. Syst. 19594\u201319607 (2021)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: International Conference on Computer Vision, pp. 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR9","unstructured":"Chen, S., et al.: Adaptformer: adapting vision transformers for scalable visual recognition. Adv. Neural Inform. Process. Syst. (2022)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. arXiv preprint arXiv:2212.07143 (2022)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"25_CR11","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"25_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: International Conference on Computer Vision (ICCV), pp. 6804\u20136815 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 200\u2013210 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: International Conference on Computer Vision (ICCV), pp. 6201\u20136210 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The something something video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5843\u20135851. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Gu, C., et\u00a0al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 15979\u201315988 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"25_CR20","unstructured":"He, X., Li, C., Zhang, P., Yang, J., Wang, X.E.: Parameter-efficient model adaptation for vision transformers. arXiv preprint arXiv:2203.16329 (2022)"},{"key":"25_CR21","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, vol.\u00a097, pp. 2790\u20132799 (2019)"},{"key":"25_CR22","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"25_CR24","doi-asserted-by":"publisher","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13695, pp. 105\u2013124. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_7","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: n 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"25_CR27","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (ICML), vol.\u00a0162, pp. 12888\u201312900 (2022)"},{"key":"25_CR28","unstructured":"Li, K., et al.: Uniformer: unified transformer for efficient spatial-temporal representation learning. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Uniformerv2: unlocking the potential of image vits for video understanding. In: International Conference on Computer Vision (ICCV), pp. 1632\u20131643 (2023)","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"25_CR30","unstructured":"Li, T., Wang, L.: Learning spatiotemporal features via video and text pair discrimination. arXiv preprint arXiv:2001.05691 (2020)"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4582\u20134597 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"25_CR32","unstructured":"Li, X., Huang, Z., Wang, J., Li, K., Wang, L.: Videoeval: comprehensive benchmark suite for low-cost evaluation of video foundation model. arXiv preprint arXiv:2407.06491 (2024)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: TEA: temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 906\u2013915 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134804 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: Resound: towards action recognition without representation bias. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 513\u2013528 (2018)","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"25_CR36","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. In: Adv. Neural Inform. Process. Syst. (2022)"},{"issue":"5","key":"25_CR37","first-page":"2760","volume":"44","author":"J Lin","year":"2022","unstructured":"Lin, J., Gan, C., Wang, K., Han, S.: TSM: temporal shift module for efficient and scalable video understanding on edge devices. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2760\u20132774 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR38","doi-asserted-by":"publisher","unstructured":"Lin, Z., et al.: Frozen CLIP models are efficient video learners. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13695, pp. 388\u2013404. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_23","DOI":"10.1007\/978-3-031-19833-5_23"},{"issue":"12","key":"25_CR39","doi-asserted-by":"publisher","first-page":"10270","DOI":"10.1109\/TPAMI.2021.3134200","volume":"44","author":"M Liu","year":"2022","unstructured":"Liu, M., Wang, Z., Ji, S.: Non-local graph neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 10270\u201310276 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11999\u201312009 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3192\u20133201 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: TAM: temporal adaptive module for video recognition. In: International Conference on Computer Vision, pp. 13688\u201313698 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"25_CR43","unstructured":"Lu, C., Jin, X., Huang, Z., Hou, Q., Cheng, M., Feng, J.: CMAE-V: contrastive masked autoencoders for video action recognition. arXiv preprint arXiv:2301.06018 (2023)"},{"key":"25_CR44","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? Adv. Neural Inf. Process. Syst. 14014\u201314024 (2019)"},{"key":"25_CR45","doi-asserted-by":"publisher","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13664, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_1","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"25_CR46","unstructured":"Nie, X., et al.: Pro-tuning: unified prompt tuning for vision tasks. arXiv preprint arXiv:2207.14381 (2022)"},{"key":"25_CR47","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"25_CR48","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: parameter-efficient image-to-video transfer learning. Adv. Neural Inf. Process. Syst. (2022)"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: Adapterfusion: non-destructive task composition for transfer learning. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 487\u2013503 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., et al.: Adapterhub: a framework for adapting transformers. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 46\u201354 (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"25_CR51","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"25_CR52","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI blog (2018)"},{"issue":"8","key":"25_CR53","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.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"25_CR54","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":"25_CR55","first-page":"15268","volume":"35","author":"J Tan","year":"2022","unstructured":"Tan, J., Zhao, X., Shi, X., Kang, B., Wang, L.: Pointtad: multi-label temporal action detection with learnable query points. NIPS 35, 15268\u201315280 (2022)","journal-title":"NIPS"},{"key":"25_CR56","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural Inf. Process. Syst. (2022)"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Tschannen, M., Mustafa, B., Houlsby, N.: Clippo: image-and-language understanding from pixels only. arXiv preprint arXiv:2212.08045 (2022)","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Tu, S., Dai, Q., Wu, Z., Cheng, Z., Hu, H., Jiang, Y.: Implicit temporal modeling with learnable alignment for video recognition. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"25_CR59","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Videomae V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"25_CR61","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. ECCV 2016. LNCS, vol.\u00a09912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"25_CR62","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: a new paradigm for video action recognition. arXiv preprint arXiv:2109.08472 (2021)"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BEVT: bert pretraining of video transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14713\u201314723 (2022)","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"25_CR64","unstructured":"Wang, Y., et\u00a0al.: Internvid: a large-scale video-text dataset for multimodal understanding and generation. In: ICLR (2024)"},{"key":"25_CR65","doi-asserted-by":"crossref","unstructured":"Wu, W., Sun, Z., Ouyang, W.: Revisiting classifier: transferring vision-language models for video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2847\u20132855 (2023)","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"25_CR66","doi-asserted-by":"publisher","unstructured":"Xiang, W., Li, C., Wang, B., Wei, X., Hua, X.S., Zhang, L.: Spatiotemporal self-attention modeling with temporal patch shift for action recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13663, pp. 627\u2013644. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_36","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: Progressive visual prompt learning with contrastive feature re-formation. arXiv preprint arXiv:2304.08386 (2023)","DOI":"10.1007\/s11263-024-02172-x"},{"key":"25_CR69","unstructured":"Xu, C., et al.: DPL: decoupled prompt learning for vision-language models. arXiv preprint arXiv:2308.10061 (2023)"},{"key":"25_CR70","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Multiview transformers for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3323\u20133333 (2022)","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"25_CR71","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: adapting image models for efficient video action recognition. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR72","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp.\u00a01\u20139 (2022)"},{"key":"25_CR73","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1204\u20131213 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"25_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhu, Y., Wang, H., Chen, Y., Wu, G., Wang, L.: Extracting motion and appearance via inter-frame attention for efficient video frame interpolation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"25_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.: Token shift transformer for video classification. In: ACM International Conference on Multimedia, pp. 917\u2013925 (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"25_CR76","unstructured":"Zhang, Y., Zhou, K., Liu, Z.: Neural prompt search. arXiv preprint arXiv:2206.04673 (2022)"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), vol. 11205, pp. 831\u2013846 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"25_CR78","unstructured":"Zhu, Y., Ji, Y., Zhao, Z., Wu, G., Wang, L.: AWT: transferring vision-language models via augmentation, weighting, and transportation. arXiv preprint arXiv:2407.04603 (2024)"},{"key":"25_CR79","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, G., Tan, J., Wu, G., Wang, L.: Dual detrs for multi-label temporal action detection. In: CVPR, pp. 18559\u201318569 (2024)","DOI":"10.1109\/CVPR52733.2024.01756"}],"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\/978-3-031-73010-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T14:07:48Z","timestamp":1731161268000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 November 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"}}]}}