{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:04:40Z","timestamp":1783969480496,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233991","type":"print"},{"value":"9789819234004","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3400-4_33","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:15:53Z","timestamp":1783966553000},"page":"399-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Task Decoupling for Temporal Action Localization"],"prefix":"10.1007","author":[{"given":"Hui","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6022-5837","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4955-8582","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"33_CR1","first-page":"492","volume-title":"European Conference on Computer Vision","author":"CL Zhang","year":"2022","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: European Conference on Computer Vision, pp. 492\u2013510. Springer (2022)"},{"key":"33_CR2","unstructured":"Tang, T.N., Kim, K., Sohn, K.: TemporalMaxer: maximize temporal context with only max pooling for temporal action localization. arXiv preprint https:\/\/arxiv.org\/abs\/2303.09055 (2023)"},{"key":"33_CR3","first-page":"18857","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D Shi","year":"2023","unstructured":"Shi, D., Zhong, Y., Cao, Q., Ma, L., Li, J., Tao, D.: TriDet: temporal action detection with relative boundary modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18857\u201318866 (2023)"},{"key":"33_CR4","first-page":"4878","volume":"39","author":"Q Li","year":"2025","unstructured":"Li, Q., Liu, D., Kong, J., Li, S., Xu, H., Wang, J.: Temporal action localization with cross layer task decoupling and refinement. Proc. AAAI Conf. Artif. Intell. 39, 4878\u20134886 (2025)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"33_CR5","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"33_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","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)","journal-title":"Comput. Vis. Image Underst."},{"key":"33_CR7","first-page":"961","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"F Caba Heilbron","year":"2015","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)"},{"key":"33_CR8","first-page":"8668","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"H Zhao","year":"2019","unstructured":"Zhao, H., Torralba, A., Torresani, L., Yan, Z.: HACS: human action clips and segments dataset for recognition and temporal localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8668\u20138678 (2019)"},{"key":"33_CR9","first-page":"6299","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Carreira","year":"2017","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, pp. 6299\u20136308 (2017)"},{"key":"33_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103484","volume":"222","author":"D Wei","year":"2022","unstructured":"Wei, D., et al.: Efficient dual attention slowfast networks for video action recognition. Comput. Vis. Image Underst. 222, 103484 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"33_CR11","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"E Perez","year":"2018","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, (2018)"},{"key":"33_CR12","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"33_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint https:\/\/arxiv.org\/abs\/1711.05101 (2017)"},{"key":"33_CR14","first-page":"14549","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Wang","year":"2023","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)"},{"issue":"6","key":"33_CR15","doi-asserted-by":"publisher","first-page":"4625","DOI":"10.1109\/TCSVT.2023.3326692","volume":"34","author":"J Yang","year":"2023","unstructured":"Yang, J., Wei, P., Zheng, N.: Cross time-frequency transformer for temporal action localization. IEEE Trans. Circuits Syst. Video Technol. 34(6), 4625\u20134638 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"33_CR16","doi-asserted-by":"publisher","first-page":"5705","DOI":"10.1109\/TMM.2023.3338082","volume":"26","author":"J Yang","year":"2023","unstructured":"Yang, J., Wei, P., Ren, Z., Zheng, N.: Gated multi-scale transformer for temporal action localization. IEEE Trans. Multimed. 26, 5705\u20135717 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Nag, S., Zhu, X., Deng, J., Song, Y.Z., Xiang, T.: DiffTAD: temporal action detection with proposal denoising diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10362\u201310374 (2023)","DOI":"10.1109\/ICCV51070.2023.00951"},{"key":"33_CR18","first-page":"503","volume-title":"European Conference on Computer Vision","author":"F Cheng","year":"2022","unstructured":"Cheng, F., Bertasius, G.: TALLformer: temporal action localization with a longmemory transformer. In: European Conference on Computer Vision, pp. 503\u2013521. Springer (2022)"},{"key":"33_CR19","first-page":"485","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Qing","year":"2021","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 485\u2013494 (2021)"},{"key":"33_CR20","first-page":"20610","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"C Su","year":"2025","unstructured":"Su, C., Zheng, H., Peng, D., Wang, X.: DiCA: disambiguated contrastive alignment for cross-modal retrieval with partial labels. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 20610\u201320618 (2025)"},{"key":"33_CR21","first-page":"3612","volume":"38","author":"H Liu","year":"2024","unstructured":"Liu, H., Ma, Y., Yan, M., Chen, Y., Peng, D., Wang, X.: DiDA: disambiguated domain alignment for cross-domain retrieval with partial labels. Proc. AAAI Conf. Artif. Intell. 38, 3612\u20133620 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"37","key":"33_CR22","first-page":"31689","volume":"40","author":"Q Li","year":"2026","unstructured":"Li, Q., et al.: Learning beyond domains: misleading prompts and pseudo-label contrast for text domain generalization. Proc. AAAI Conf. Artif. Intell. 40(37), 31689\u201331697 (2026)","journal-title":"Proc. AAAI Conf. Artif. Intell."}],"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\/978-981-92-3400-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:15:56Z","timestamp":1783966556000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3400-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819233991","9789819234004"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3400-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","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":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}