{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:50:05Z","timestamp":1743155405557,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781063"},{"type":"electronic","value":"9783031781070"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78107-0_9","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T19:31:58Z","timestamp":1733081518000},"page":"135-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AMC-OA: Adaptive Multi-Scale Convolutional Networks with\u00a0Optimized Attention for\u00a0Temporal Action Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7849-1407","authenticated-orcid":false,"given":"Rui","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1725\u20131732. IEEE, Columbus (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.223\u200b","DOI":"10.1109\/CVPR.2014.223"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: 2015 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4694\u20134702. IEEE, Boston (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7299101","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: 2016 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1933\u20131941. IEEE, Las Vegas (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.213\u200b","DOI":"10.1109\/CVPR.2016.213"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Shi, Y., Zhong, Q., Cao, L., Ma, J., Li, J., Tao, D.: TriDet: temporal action detection with relative boundary modeling (2023)","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, C., Luo, C., Tang, D., Chen, N., Codella, N., Zha, Z.-J.: Streaming video model (2023)","DOI":"10.1109\/CVPR52729.2023.01403"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y.-D., Zheng, Z., Chen, J., Wang, J., Lu, T.: ELAN: enhancing temporal action detection with location awareness (2023)","DOI":"10.1109\/ICME55011.2023.00179"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, S., Liu, K., Mangalam, K., Ghanem, B.: Re2TAL: rewiring pretrained video backbones for reversible temporal action localization (2022)","DOI":"10.1109\/CVPR52729.2023.01025"},{"key":"9_CR9","unstructured":"Underreview as a conference paper at ICLR 2023: T2D: Spatiotemporal Feature Learning Based on Triple 2D Decomposition"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Liu, Y., Liu, Z., Zhai, Y., Li, W., Doerman, D., Yuan, J.: STAT: towards generalizable temporal action localization. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Paris (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.13311","DOI":"10.48550\/arXiv.2404.13311"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Gupta, R., et al.: Class prototypes based contrastive learning for classifying multi-label and fine-grained educational videos. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1234\u20131242. IEEE, Vancouver (2023). https:\/\/doi.org\/10.1109\/CVPR.2023.01234","DOI":"10.1109\/CVPR.2023.01234"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR 2021), Vienna, Austria (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: MammalNet: a large-scale video benchmark for mammal recognition and behavior understanding. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13052\u201313061. IEEE, Vancouver (2023). https:\/\/doi.org\/10.1109\/CVPR.2023.13052","DOI":"10.1109\/CVPR.2023.13052"},{"key":"9_CR14","doi-asserted-by":"publisher","unstructured":"Heilbron, F.C., Barrios, W., Escorcia, V., Ghanem, B.: SCC: semantic context cascade for efficient action detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3175\u20133184. IEEE, Honolulu (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.337","DOI":"10.1109\/CVPR.2017.337"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2911\u20132920. IEEE, Honolulu (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.675","DOI":"10.1109\/CVPR.2017.675"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Chen, G., Zheng, Y.-D., Wang, L., Lu, T.: DCAN: improving temporal action detection via dual context aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 4181\u20134189. AAAI Press, Vancouver (2022). https:\/\/doi.org\/10.1609\/aaai.v36i4.20244","DOI":"10.1609\/aaai.v36i4.20244"},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"3857","DOI":"10.1109\/TMM.2021.3052338","volume":"23","author":"P Chen","year":"2021","unstructured":"Chen, P., Gan, C., Shen, G., Huang, W., Zeng, R., Tan, M.: Relation attention for temporal action localization. IEEE Trans. Multimedia 23, 3857\u20133869 (2021). https:\/\/doi.org\/10.1109\/TMM.2021.3052338","journal-title":"IEEE Trans. Multimedia"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Chang, S., et al.: Augmented transformer with adaptive graph for temporal action proposal generation. In: Proceedings of the 3rd International Workshop on Human-Centric Multimedia Analysis (HCMA@MM 2022), pp. 7-19. ACM, Lisboa (2022). https:\/\/doi.org\/10.1145\/3526128.3545365","DOI":"10.1145\/3526128.3545365"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Wang, J., Zeng, Z., Lan, T., Zhang, J., Tu, Z., Chang, S.-F.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9415\u20139424. IEEE, Seattle (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00944","DOI":"10.1109\/CVPR42600.2020.00944"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Tirupattur, P., Mazumdar, S., Kaushik, A., Ghanem, B., Davis, L.S.: Modeling multi-label action dependencies for temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13385\u201313394. IEEE, Nashville (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01318","DOI":"10.1109\/CVPR46437.2021.01318"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Kahatapitiya, K., Munasinghe, R., Fernando, B., Denman, S., Sridharan, S.: Coarse-Fine networks for temporal activity detection in videos. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15755\u201315765. IEEE, Nashville (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01575","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"9_CR22","unstructured":"Gupta, A., et al.: LoSA: long-short-range adapter for scaling end-to-end temporal action localization. arXiv preprint arXiv:2404.01282 (2024)"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Tan, J., Tang, J., Wang, L., Wu, G.: Relaxed transformer decoders for direct action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13506\u201313515. IEEE, Montreal (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01327","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"Liu, X., Hu, Y., Bai, S., Ding, F., Bai, X., Torr, P.H.S.: Multi-shot temporal event localization: a benchmark. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12596\u201312606. IEEE, Nashville (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01243","DOI":"10.1109\/CVPR46437.2021.01243"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Nawhal, M., Mori, G.: Activity graph transformer for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4647\u20134656. IEEE, Montreal (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00460","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7094\u20137103. IEEE, Seoul (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00704","DOI":"10.1109\/ICCV.2019.00704"},{"key":"9_CR27","doi-asserted-by":"publisher","unstructured":"Vaudaux-Ruth, G., Chan-Hon-Tong, A., and Achard, C.: SALAD: self-assessment learning for action detection. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1268\u20131277. IEEE, Snowmass Village (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00130","DOI":"10.1109\/WACV48630.2021.00130"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Liu, S., Zhao, X., Su, H., and Hu, Z.: TSI: temporal scale invariant network for action proposal generation. In: Computer Vision - ACCV 2020, pp. 530\u2013546. Springer, Kyoto (2020). https:\/\/doi.org\/10.1007\/978-3-030-69539-1_32","DOI":"10.1007\/978-3-030-69539-1_32"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78107-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T20:04:02Z","timestamp":1733083442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78107-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781063","9783031781070"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78107-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}