{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:36:04Z","timestamp":1743068164900,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755936"},{"type":"electronic","value":"9789819755943"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5594-3_27","type":"book-chapter","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T15:06:26Z","timestamp":1723561586000},"page":"323-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SPViM: Sparse Pyramid Video Representation Learning Framework for Fine-Grained Action Retrieval"],"prefix":"10.1007","author":[{"given":"Lutong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chenglei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hongqiu","family":"Luan","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Gai","sequence":"additional","affiliation":[]},{"given":"Wenxiu","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Yawen","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Moon, W., Hyun, S., Park, S., Park, D., Heo, J.P.: Query-dependent video representation for moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23023\u2013 23033 (2023)","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Wang, C.H., Tseng, Y.C., Chiang, T.H., Chen, Y.A.: Learning multi-scale representations with single-stream network for video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6165\u2013 6175 (2023)","DOI":"10.1109\/CVPRW59228.2023.00656"},{"key":"27_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108807","volume":"130","author":"TH Chiang","year":"2022","unstructured":"Chiang, T.H., Tseng, Y.C., Tseng, Y.C.: A multi-embedding neural model for incident video retrieval. Pattern Recogn. 130, 108807 (2022)","journal-title":"Pattern Recogn."},{"issue":"10","key":"27_CR4","doi-asserted-by":"publisher","first-page":"2385","DOI":"10.1007\/s11263-022-01651-3","volume":"130","author":"G Kordopatis-Zilos","year":"2022","unstructured":"Kordopatis-Zilos, G., Tzelepis, C., Papadopoulos, S., Kompatsiaris, I., Patras, I.: DNS: distill-and-select for efficient and accurate video indexing and retrieval. Int. J. Comput. Vision 130(10), 2385\u20132407 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Hadji, I., Derpanis, K.G., Jepson, A.D.: Representation learning via global temporal alignment and cycle-consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11068\u201311077 (2021)","DOI":"10.1109\/CVPR46437.2021.01092"},{"key":"27_CR6","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s11263-015-0851-8","volume":"119","author":"M Rohrbach","year":"2016","unstructured":"Rohrbach, M., et al.: Recognizing fine-grained and composite activities using hand-centric features and script data. Int. J. Comput. Vision 119, 346\u2013373 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Haresh, S., et al.: Learning by aligning videos in time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5548\u20135558 (2021)","DOI":"10.1109\/CVPR46437.2021.00550"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Temporal cycleconsistency learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1801\u20131810 (2019)","DOI":"10.1109\/CVPR.2019.00190"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"27_CR11","unstructured":"Xu, R., Niu, L., Zhang, J., Zhang, L.: A proposal-based approach for activity image-to-video retrieval (2019)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, Y.G., Jiang, Y., Wang, J.: VCDB: a large-scale database for partial copy detection in videos. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part IV 13, pp. 357\u2013371. Springer (2014)","DOI":"10.1007\/978-3-319-10593-2_24"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s11280-018-0536-7","volume":"22","author":"W Jing","year":"2019","unstructured":"Jing, W., Nie, X., Cui, C., Xi, X., Yang, G., Yin, Y.: Global-view hashing: harnessing global relations in near-duplicate video retrieval. World Wide Web 22, 771\u2013789 (2019)","journal-title":"World Wide Web"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., Kompatsiaris, Y.: Nearduplicate video retrieval by aggregating intermediate CNN layers. In: MultiMedia Modeling: 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4\u20136, 2017, Proceedings, Part I 23, pp. 251\u2013263. Springer (2017)","DOI":"10.1007\/978-3-319-51811-4_21"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Central similarity quantization for efficient image and video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3083\u2013 3092 (2020)","DOI":"10.1109\/CVPR42600.2020.00315"},{"issue":"1","key":"27_CR16","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/TBDATA.2016.2530714","volume":"2","author":"YG Jiang","year":"2016","unstructured":"Jiang, Y.G., Wang, J.: Partial copy detection in videos: a benchmark and an evaluation of popular methods. IEEE Trans. Big Data 2(1), 32\u201342 (2016)","journal-title":"IEEE Trans. Big Data"},{"key":"27_CR17","doi-asserted-by":"publisher","first-page":"24435","DOI":"10.1007\/s11042-016-4176-6","volume":"76","author":"H Liu","year":"2017","unstructured":"Liu, H., Zhao, Q., Wang, H., Lv, P., Chen, Y.: An image-based near-duplicate video retrieval and localization using improved edit distance. Multimed. Tools Appl. 76, 24435\u201324456 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S., Levine, S.: Time-contrastive networks: Self-supervised learning from video. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1134\u20131141 (2018). Author, F.: Article title. Journal 2(5), 99\u2013110 (2016)","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a largescale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE, New York (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR22","unstructured":"Zhou, J., Wang, P., Wang, F., Liu, Q., Li, H., Jin, R.: Elsa: enhanced local selfattention for vision transformer. arXiv preprint arXiv:2112.12786 (2021)"},{"key":"27_CR23","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Chen, M., Wei, F., Li, C., Cai, D.: Frame-wise action representations for long videos via sequence contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13801\u201313810 (2022)","DOI":"10.1109\/CVPR52688.2022.01343"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 527\u2013544. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Tekin, B., Coskun, H., Vineet, V., Fua, P., Pollefeys, M.: Learning to align sequential actions in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2181\u20132191 (2022)","DOI":"10.1109\/CVPR52688.2022.00222"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, D., Zheng, Q., Su, B.: Modeling video as stochastic processes for fine-grained video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2225\u20132234 (2023)","DOI":"10.1109\/CVPR52729.2023.00221"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5594-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T15:12:12Z","timestamp":1723561932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5594-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755936","9789819755943"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5594-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}