{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T20:57:49Z","timestamp":1774990669528,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784972","type":"print"},{"value":"9783031784989","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78498-9_18","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T09:27:55Z","timestamp":1733218075000},"page":"260-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Full-Frequency Dynamic Convolution: A\u00a0Physical Frequency-Dependent Convolution for\u00a0Sound Event Detection"],"prefix":"10.1007","author":[{"given":"Haobo","family":"Yue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqin","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Bello, J., Mydlarz, C., Salamon, J.: Sound analysis in smart cities. In: Virtanen, T., Plumbley, M., Ellis, D. (eds.) Computational Analysis of Sound Scenes and Events, pp. 373\u2013397. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-63450-0_13","DOI":"10.1007\/978-3-319-63450-0_13"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, \u00c7., Ferroni, G., Tuveri, F., Azcarreta, J., Krstulovi\u0107, S.: A framework for the robust evaluation of sound event detection. In: ICASSP, pp. 61\u201365 (2020)","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chen, K., Du, X., Zhu, B., Ma, Z., Berg-Kirkpatrick, T., Dubnov, S.: HTS-AT: a hierarchical token-semantic audio transformer for sound classification and detection. In: ICASSP, pp. 646\u2013650 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"18_CR4","unstructured":"Chen, S., et al.: BEATs: audio pre-training with acoustic tokenizers. In: ICML, pp. 5178\u20135193 (2023)"},{"issue":"2","key":"18_CR5","first-page":"81","volume":"33","author":"C Debes","year":"2016","unstructured":"Debes, C., Merentitis, A., Sukhanov, S., Niessen, M., Frangiadakis, N., Bauer, A.: Monitoring activities of daily living in smart homes: understanding human behavior. IEEE SPM 33(2), 81\u201394 (2016)","journal-title":"IEEE SPM"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: INTERSPEECH, pp. 571\u2013575 (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"18_CR8","unstructured":"Jia, X., De\u00a0Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: NEURIPS (2016)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Jin, Q., Schulam, P., Rawat, S., Burger, S., Ding, D., Metze, F.: Event-based video retrieval using audio. In: INTERSPEECH, pp. 2085\u20132088 (2012)","DOI":"10.21437\/Interspeech.2012-556"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Li, K., Song, Y., Dai, L.R., McLoughlin, I., Fang, X., Liu, L.: AST-SED: an effective sound event detection method based on audio spectrogram transformer. In: ICASSP, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096853"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Li, K., Song, Y., McLoughlin, I., Liu, L., Li, J., Dai, L.R.: Fine-tuning audio spectrogram transformer with task-aware adapters for sound event detection. In: INTERSPEECH, pp. 291\u2013295 (2023)","DOI":"10.21437\/Interspeech.2023-1174"},{"key":"18_CR12","first-page":"1336","volume":"32","author":"X Li","year":"2024","unstructured":"Li, X., Shao, N., Li, X.: Self-supervised audio teacher-student transformer for both clip-level and frame-level tasks. IEEE\/ACM TASLP 32, 1336\u20131351 (2024)","journal-title":"IEEE\/ACM TASLP"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: CVPR, pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"18_CR14","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_CR15","doi-asserted-by":"crossref","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: Metrics for polyphonic sound event detection. AS 6(6) (2016)","DOI":"10.3390\/app6060162"},{"key":"18_CR16","unstructured":"Na, T., Zhang, Q.: Convolutional network with conformer for semi-supervised sound event detection. Technical report, DCASE2021 Challenge (2021)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, S.H., Ko, B.Y., Park, Y.H.: Frequency dynamic convolution: frequency-adaptive pattern recognition for sound event detection. In: INTERSPEECH, pp. 2763\u20132767 (2022)","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, S.H., Park, Y.H.: FilterAugment: an acoustic environmental data augmentation method. In: ICASSP, pp. 4308\u20134312 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Park, D.S., : SpecAugment: a simple data augmentation method for automatic speech recognition. In: INTERSPEECH, pp. 2613\u20132617 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"issue":"1","key":"18_CR20","first-page":"199","volume":"19","author":"J Rouat","year":"2008","unstructured":"Rouat, J.: Computational auditory scene analysis: principles, algorithms, and applications. IEEE TNN 19(1), 199\u2013199 (2008)","journal-title":"IEEE TNN"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Shao, N., Li, X., Li, X.: Fine-tune the pretrained ATST model for sound event detection. arxiv preprint (2023)","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Sun, J., Li, Y., Lu, H., Kamiya, T., Serikawa, S.: Deep learning for visual segmentation: a review. In: COMPSAC, pp. 1256\u20131260 (2020)","DOI":"10.1109\/COMPSAC48688.2020.00-84"},{"key":"18_CR23","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NEURIPS (2017)"},{"key":"18_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-58452-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 282\u2013298. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_17"},{"key":"18_CR25","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: SOLOv2: dynamic and fast instance segmentation. In: NEURIPS, pp. 17721\u201317732 (2020)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: ECCV, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, S., Zhang, X., Zhang, P.: Multi-dimensional frequency dynamic convolution with confident mean teacher for sound event detection. In: ICASSP, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096306"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zamora\u00a0Esquivel, J., Cruz\u00a0Vargas, A., Lopez\u00a0Meyer, P., Tickoo, O.: Adaptive convolutional kernels. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00249"},{"key":"18_CR29","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. ICLR (2018)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, X., Song, Y., McLoughlin, I., Liu, L., Dai, L.R.: An improved mean teacher based method for large scale weakly labeled semi-supervised sound event detection. In: ICASSP, pp. 356\u2013360 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414931"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, J., Jampani, V., Pi, Z., Liu, Q., Yang, M.H.: Decoupled dynamic filter networks. In: CVPR, pp. 6647\u20136656 (2021)","DOI":"10.1109\/CVPR46437.2021.00658"},{"issue":"3","key":"18_CR32","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"},{"issue":"6","key":"18_CR33","first-page":"1291","volume":"25","author":"E \u00c7ak\u0131r","year":"2017","unstructured":"\u00c7ak\u0131r, E., Parascandolo, G., Heittola, T., Huttunen, H., Virtanen, T.: Convolutional recurrent neural networks for polyphonic sound event detection. IEEE\/ACM TASLP 25(6), 1291\u20131303 (2017)","journal-title":"IEEE\/ACM TASLP"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78498-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,27]],"date-time":"2025-04-27T14:15:36Z","timestamp":1745763336000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78498-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784972","9783031784989"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78498-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 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"}}]}}