{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:43:24Z","timestamp":1782953004906,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698554","type":"print"},{"value":"9789819698561","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9856-1_18","type":"book-chapter","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T12:39:35Z","timestamp":1753187975000},"page":"205-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6955-6238","authenticated-orcid":false,"given":"Xinnan","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5432-6784","authenticated-orcid":false,"given":"Yicheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5179-4530","authenticated-orcid":false,"given":"Tixin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7352-7997","authenticated-orcid":false,"given":"Wentao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8302-1338","authenticated-orcid":false,"given":"Yuanjie","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: Video Mamba Suite: State space model as a versatile alternative for video understanding. arXiv, unpublished (2024)","DOI":"10.1007\/s11263-025-02597-y"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, F., Bertasius, G.: TALLFormer: temporal action localization with a long-memory transformer. In: ECCV, pp. 503\u2013521 (2022)","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"18_CR4","unstructured":"Dao, T., Gu, A.: Transformers are SSMs: generalized models and efficient algorithms through structured state space duality. In: ICML (2024)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"18_CR6","unstructured":"Gu, A., Goel, K., Re, C.: Efficiently modeling long sequences with structured state spaces. In: ICLR (2022)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"He, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: The Thumos challenge on action recognition for videos \u201cin the wild\u201d. In: CVIU, pp. 1\u201323 (2017)","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: CVPR, pp. 3320\u20133329 (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: BMN: boundary-matching network for temporal action proposal generation. In: ICCV, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2999\u20133007 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: End-to-end temporal action detection with 1B parameters across 1000 frames. In: CVPR, pp. 18591\u201318601 (2024)","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"18_CR13","unstructured":"Liu, S., et al.: ETAD: training action detection end to end on a laptop. In: CVPR, pp. 4524\u20134533 (2024)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 5427\u20135441 (2022)","DOI":"10.1109\/TIP.2022.3195321"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: CVPR, pp. 485\u2013494 (2021)","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Shi, D., et al.: TriDet: temporal action detection with relative boundary modeling. In: CVPR, pp. 18857\u201318866 (2023)","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Tan, J., Tang, J., Wang, L., Wu, G.: Relaxed transformer decoders for direct action proposal generation. In: ICCV, pp. 13526\u201313535 (2021)","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"18_CR19","unstructured":"Tang, T.N., Kim, K., Sohn, K.: TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization. arXiv, unpublished (2023)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: CVPR, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: ECCV (2016). https:\/\/api.semanticscholar.org\/CorpusID:5711057","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: InternVideo2: scaling foundation models for multimodal video understanding. In: ECCV, pp. 396\u2013416 (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-TAD: sub-graph localization for temporal action detection. In: CVPR, pp. 10156\u201310165 (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"ang, L., et al.: DyFADet: dynamic feature aggregation for temporal action detection. In: ECCV, pp. 305\u2013322. Springer (2025)","DOI":"10.1007\/978-3-031-72952-2_18"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: ECCV, pp. 492\u2013510 (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, C., Thabet, A.K., Ghanem, B.: Video self-stitching graph network for temporal action localization. In: ICCV, pp. 13658\u201313667 (2021)","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, H., Torralba, A., Torresani, L., Yan, Z.: HACS: human action clips and segments dataset for recognition and temporal localization. In: ICCV, pp. 8668\u20138678 (2019)","DOI":"10.1109\/ICCV.2019.00876"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et al.: Distance-IoU loss: faster and better learning for bounding box regression. In: AAAI, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: 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","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9856-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:44:09Z","timestamp":1782949449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9856-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698554","9789819698561"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9856-1_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 July 2025","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":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}