{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:19:21Z","timestamp":1757618361025,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819681792"},{"type":"electronic","value":"9789819681808"}],"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\/978-981-96-8180-8_35","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T09:15:30Z","timestamp":1750324530000},"page":"446-455","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Token Fusion for\u00a0Transformer-Based Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8323-7216","authenticated-orcid":false,"given":"Zelin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4778-7206","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9475-9818","authenticated-orcid":false,"given":"Aibo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"unstructured":"Anonymous: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers (2021)","key":"35_CR1"},{"unstructured":"Bolya, D., Fu, C.Y., Dai, X., et\u00a0al.: Token merging: your vit but faster. arXiv preprint arXiv:2210.09461 (2022)","key":"35_CR2"},{"issue":"4","key":"35_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","key":"35_CR4","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"35_CR5","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)","key":"35_CR6"},{"key":"35_CR7","first-page":"24101","volume":"35","author":"W Kwon","year":"2022","unstructured":"Kwon, W., Kim, S., Mahoney, M.W., et al.: A fast post-training pruning framework for transformers. Adv. Neural. Inf. Process. Syst. 35, 24101\u201324116 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","key":"35_CR8","DOI":"10.1109\/CVPR.2015.7298965"},{"doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","key":"35_CR9","DOI":"10.1109\/ICCV48922.2021.01196"},{"doi-asserted-by":"crossref","unstructured":"Ren, S., Zhou, D., He, S., et\u00a0al.: Shunted self-attention via multi-scale token aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10853\u201310862 (2022)","key":"35_CR10","DOI":"10.1109\/CVPR52688.2022.01058"},{"doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","key":"35_CR11","DOI":"10.1109\/ICCV48922.2021.00717"},{"unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., et\u00a0al.: FastViT: a fast hybrid vision transformer using structural reparameterization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5785\u20135795 (2023)","key":"35_CR12"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"35_CR13"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, X., Cao, L., et\u00a0al.: Multimodal token fusion for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12186\u201312195 (2022)","key":"35_CR14","DOI":"10.1109\/CVPR52688.2022.01187"},{"doi-asserted-by":"crossref","unstructured":"Xia, M., Zhong, Z., Chen, D.: Structured pruning learns compact and accurate models. arXiv preprint arXiv:2204.00408 (2022)","key":"35_CR15","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"35_CR16","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., et al.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Zhang, W., Huang, Z., Luo, G., et\u00a0al.: TopFormer: token pyramid transformer for mobile semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12083\u201312093 (2022)","key":"35_CR17","DOI":"10.1109\/CVPR52688.2022.01177"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8180-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:33:55Z","timestamp":1757190835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8180-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681792","9789819681808"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8180-8_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}