{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:57:37Z","timestamp":1742983057770,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":92,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609079"},{"type":"electronic","value":"9789819609086"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0908-6_1","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:26:42Z","timestamp":1733513202000},"page":"3-24","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LocoMotion: Learning Motion-Focused Video-Language Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3670-3897","authenticated-orcid":false,"given":"Hazel","family":"Doughty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2517-0220","authenticated-orcid":false,"given":"Fida Mohammad","family":"Thoker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9092-1556","authenticated-orcid":false,"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"1_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: Proceedings of the IEEE International Conference on Computer Vision (ICCV). pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bagad, P., Tapaswi, M., Snoek, C.G.M.: Test of time: Instilling video-language models with a sense of time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2503\u20132516 (2023)","DOI":"10.1109\/CVPR52729.2023.00247"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Brown, A., Zisserman, A.: Condensed movies: Story based retrieval with contextual embeddings. In: Proceedings of the Asian Conference on Computer Vision (ACCV) (2020)","DOI":"10.1007\/978-3-030-69541-5_28"},{"key":"1_CR4","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR). pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"1_CR5","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Buch, S., Eyzaguirre, C., Gaidon, A., Wu, J., Fei-Fei, L., Niebles, J.C.: Revisiting the\" video\" in video-language understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2917\u20132927 (2022)","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, J.: Activitynet: A large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"1_CR8","unstructured":"Chen, S., Li, H., Wang, Q., Zhao, Z., Sun, M., Zhu, X., Liu, J.: Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., Yu, G.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, F., Wang, X., Lei, J., Crandall, D., Bansal, M., Bertasius, G.: Vindlu: A recipe for effective video-and-language pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10739\u201310750 (2023)","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Damen, D., Doughty, H., Farinella, G.M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et\u00a0al.: Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100. International Journal of Computer Vision (IJCV) pp. 1\u201323 (2022)","DOI":"10.1007\/s11263-021-01531-2"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Dave, I., Gupta, R., Rizve, M.N., Shah, M.: Tclr: Temporal contrastive learning for video representation. Computer Vision and Image Understanding (CVIU) 219, 103406 (2022)","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"1_CR13","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2019)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Ding, S., Li, M., Yang, T., Qian, R., Xu, H., Chen, Q., Wang, J., Xiong, H.: Motion-aware contrastive video representation learning via foreground-background merging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Doughty, H., Laptev, I., Mayol-Cuevas, W., Damen, D.: Action modifiers: Learning from adverbs in instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00095"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Doughty, H., Snoek, C.G.M.: How do you do it? fine-grained action understanding with pseudo-adverbs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01346"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"1_CR19","unstructured":"Feichtenhofer, C., Fan, H., Li, Y., He, K.: Masked autoencoders as spatiotemporal learners. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Jain, M., Karmanov, I., Snoek, C.G.M.: Motion-augmented self-training for video recognition at smaller scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01026"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR). pp. 1396\u20131406 (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Goyal, R., Ebrahimi\u00a0Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et\u00a0al.: The \u201csomething something\" video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: A dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"1_CR27","unstructured":"Han, T., Xie, W., Zisserman, A.: Self-supervised co-training for video representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Hong, J., Fisher, M., Gharbi, M., Fatahalian, K.: Video pose distillation for few-shot, fine-grained sports action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00912"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Hu, H., Dong, S., Zhao, Y., Lian, D., Li, Z., Gao, S.: Transrac: Encoding multi-scale temporal correlation with transformers for repetitive action counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Huang, D., Wu, W., Hu, W., Liu, X., He, D., Wu, Z., Wu, X., Tan, M., Ding, E.: Ascnet: Self-supervised video representation learning with appearance-speed consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00799"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, S., Jiang, J., Tang, M., Jin, R., Ang, M.H.: Self-supervised motion learning from static images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00133"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: Tgif-qa: Toward spatio-temporal reasoning in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Jenni, S., Jin, H.: Time-equivariant contrastive video representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00982"},{"key":"1_CR34","unstructured":"Kim, M., Kwon, H., Wang, C., Kwak, S., Cho, M.: Relational self-attention: What\u2019s missing in attention for video understanding. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: Learning self-similarity in space and time as generalized motion for video action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01282"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Revealing single frame bias for video-and-language learning. In: Proceedings of the Annual Meeting for the Association of Computational Linguistics (ACL) (2023)","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T.L., Bansal, M., Liu, J.: Less is more: Clipbert for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: Tvqa: Localized, compositional video question answering. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Li, H., Niebles, J.C., Hoi, S.C.: Align and prompt: Video-and-language pre-training with entity prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4953\u20134963 (2022)","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"1_CR41","unstructured":"Li, K., He, Y., Wang, Y., Li, Y., Wang, W., Luo, P., Wang, Y., Wang, L., Qiao, Y.: Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., Liu, J.: Hero: Hierarchical encoder for video+ language omni-representation pre-training. Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Lin, K., Lin, C.C., Liu, Z., Liu, C., Wang, L.: Lavender: Unifying video-language understanding as masked language modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 23119\u201323129 (2023)","DOI":"10.1109\/CVPR52729.2023.02214"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Li, T., Foo, L.G., Ke, Q., Rahmani, H., Wang, A., Wang, J., Liu, J.: Dynamic spatio-temporal specialization learning for fine-grained action recognition. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"1_CR46","unstructured":"Lin, Z., Qi, S., Zhengyang, S., Changhu, W.: Inter-intra variant dual representations for self-supervised video recognition. In: British Machine Vision Conference (BMVC) (2021)"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Zeng, A., Zhou, Z., You, Y., Lu, C.: Bridging the gap between human motion and action semantics via kinematic phrases. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73242-3_13"},{"key":"1_CR48","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., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Mac, K.N.C., Joshi, D., Yeh, R.A., Xiong, J., Feris, R.S., Do, M.N.: Learning motion in feature space: Locally-consistent deformable convolution networks for fine-grained action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00638"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Mavroudi, E., Bhaskara, D., Sefati, S., Ali, H., Vidal, R.: End-to-end fine-grained action segmentation and recognition using conditional random field models and discriminative sparse coding. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00174"},{"key":"1_CR51","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Moltisanti, D., Keller, F., Bilen, H., Sevilla-Lara, L.: Learning action changes by measuring verb-adverb textual relationships. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 23110\u201323118 (2023)","DOI":"10.1109\/CVPR52729.2023.02213"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Ni, B., Paramathayalan, V.R., Moulin, P.: Multiple granularity analysis for fine-grained action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.102"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Ni, J., Zhou, N., Qin, J., Wu, Q., Liu, J., Li, B., Huang, D.: Motion sensitive contrastive learning for self-supervised video representation. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19833-5_27"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: Contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"1_CR56","unstructured":"Peihao, C., Deng, H., Dongliang, H., Xiang, L., Runhao, Z., Shilei, W., Mingkui, T., Chuang, G.: Rspnet: Relative speed perception for unsupervised video representation learning. In: The AAAI Conference on Artificial Intelligence (AAAI) (2021)"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: Generating diverse human motions from textual descriptions. In: European Conference on Computer Vision (ECCV). pp. 480\u2013497. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Tmr: Text-to-motion retrieval using contrastive 3d human motion synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Ryoo, M.S.: Fine-grained activity recognition in baseball videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2018)","DOI":"10.1109\/CVPRW.2018.00226"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Qian, R., Meng, T., Gong, B., Yang, M.H., Wang, H., Belongie, S., Cui, Y.: Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"1_CR61","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML). pp. 8748\u20138763 (2021)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Intra-and inter-action understanding via temporal action parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"1_CR66","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Sun, B., Ye, X., Yan, T., Wang, Z., Li, H., Wang, Z.: Fine-grained action recognition with robust motion representation decoupling and concentration. In: Proceedings of the ACM International Conference on Multimedia (ACMMM) (2022)","DOI":"10.1145\/3503161.3548046"},{"key":"1_CR68","unstructured":"Tao, L., Wang, X., Yamasaki, T.: Pretext-contrastive learning: Toward good practices in self-supervised video representation leaning. arXiv preprint arXiv:2010.15464 (2021)"},{"key":"1_CR69","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Bagad, P., Snoek, C.G.M.: How severe is benchmark-sensitivity in video self-supervised learning? In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19830-4_36"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.G.M.: Tubelet-contrastive self-supervision for video-efficient generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 13812\u201313823 (2023)","DOI":"10.1109\/ICCV51070.2023.01270"},{"key":"1_CR72","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhou, Y., Luo, C., Xie, W., Zeng, W., Xiong, Z.: Unsupervised visual representation learning by tracking patches in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00259"},{"key":"1_CR74","doi-asserted-by":"crossref","unstructured":"Wang, J., Gao, Y., Li, K., Lin, Y., Ma, A.J., Cheng, H., Peng, P., Huang, F., Ji, R., Sun, X.: Removing the background by adding the background: Towards background robust self-supervised video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"1_CR75","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: Vatex: A large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"1_CR76","unstructured":"Wang, Y., He, Y., Li, Y., Li, K., Yu, J., Ma, X., Li, X., Chen, G., Chen, X., Wang, Y., et\u00a0al.: Internvid: A large-scale video-text dataset for multimodal understanding and generation. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"1_CR77","unstructured":"Wang, Z., Blume, A., Li, S., Liu, G., Cho, J., Tang, Z., Bansal, M., Ji, H.: Paxion: Patching action knowledge in video-language foundation models. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"1_CR78","doi-asserted-by":"crossref","unstructured":"Xiao, F., Tighe, J., Modolo, D.: Maclr: Motion-aware contrastive learning of representations for videos. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19833-5_21"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhao, Z., Xiao, J., Wu, F., Zhang, H., He, X., Zhuang, Y.: Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the ACM International Conference on Multimedia (ACMMM). pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"1_CR80","doi-asserted-by":"crossref","unstructured":"Xu, H., Ghosh, G., Huang, P.Y., Okhonko, D., Aghajanyan, A., Metze, F., Zettlemoyer, L., Feichtenhofer, C.: Videoclip: Contrastive pre-training for zero-shot video-text understanding. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"1_CR81","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"1_CR82","unstructured":"Xue, H., Sun, Y., Liu, B., Fu, J., Song, R., Li, H., Luo, J.: Clip-vip: Adapting pre-trained image-text model to video-language representation alignment. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"1_CR84","unstructured":"Zellers, R., Lu, X., Hessel, J., Yu, Y., Park, J.S., Cao, J., Farhadi, A., Choi, Y.: Merlot: Multimodal neural script knowledge models. In: Advances in Neural Information Processing Systems (NeurIPS). pp. 23634\u201323651 (2021)"},{"key":"1_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"1_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, X., Han, G., He, S.: Context-aware and scale-insensitive temporal repetition counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"1_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., Huang, S., Zhang, Y., Zhao, H., Lu, H., Shen, X.: T2m-gpt: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"1_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Shao, L., Snoek, C.G.M.: Repetitive activity counting by sight and sound. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01385"},{"key":"1_CR89","unstructured":"Zhao, H., Sheng, D., Bao, J., Chen, D., Chen, D., Wen, F., Yuan, L., Liu, C., Zhou, W., Chu, Q., et\u00a0al.: X-paste: Revisiting scalable copy-paste for instance segmentation using clip and stablediffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"1_CR90","unstructured":"Zhao, L., Gundavarapu, N.B., Yuan, L., Zhou, H., Yan, S., Sun, J.J., Friedman, L., Qian, R., Weyand, T., Zhao, Y., et\u00a0al.: Videoprism: A foundational visual encoder for video understanding. International Conference on Machine Learning (ICML) (2024)"},{"key":"1_CR91","unstructured":"Zheng, L., Chiang, W.L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., Zhang, H., Gonzalez, J.E., Stoica, I.: Judging llm-as-a-judge with mt-bench and chatbot arena. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"1_CR92","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: Actbert: Learning global-local video-text representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 8746\u20138755 (2020)","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:08:54Z","timestamp":1733515734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}