{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:00:52Z","timestamp":1754154052231,"version":"3.41.2"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819697939"},{"type":"electronic","value":"9789819697946"}],"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\/978-981-96-9794-6_3","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:11:52Z","timestamp":1752473512000},"page":"24-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HybridScale-GuideTokens DETR: Enhancing Object Detection with GuideToken-Optimized Multi-scale Feature Fusion in a Transformer Model"],"prefix":"10.1007","author":[{"given":"Dengke","family":"Deng","sequence":"first","affiliation":[]},{"given":"Huihui","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Biyi","family":"chen","sequence":"additional","affiliation":[]},{"given":"Pengcheng","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Chengguang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"3_CR1","unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint, arXiv:2010.04159 (2020)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3_CR5","unstructured":"Wang, A., Chen, H., Liu, L., et al.: YOLOv10: real-time end-to-end object detection. In: Advances in Neural Information Processing Systems, vol. 37, pp. 107984\u2013108011 (2024)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Li, Z., Chen, Y., et al.: Efficient deformable convnets: rethinking dynamic and sparse operator for vision applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135661 (2024)","DOI":"10.1109\/CVPR52733.2024.00540"},{"key":"3_CR7","unstructured":"Tang, Y., Wang, Y., Guo, J., et al.: A survey on transformer compression. arXiv preprint, arXiv:2402.05964 (2024)"},{"key":"3_CR8","unstructured":"Zhang, H., Li, F., Liu, S., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint, arXiv:2203.03605 (2022)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"3_CR11","unstructured":"Yao, Z., Ai, J., Li, B., et al.: Efficient DETR: improving end-to-end object detector with dense prior. arXiv preprint, arXiv:2104.01318 (2021)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., et al.: Anchor DETR: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Xiao, B., et al.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7373\u20137382 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"3_CR14","unstructured":"Liu, S., Li, F., Zhang, H., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. arXiv preprint, arXiv:2201.12329 (2022)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., et al.: UP-DETR: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Yu, Y., et al.: Accelerating DETR convergence via semantic-aligned matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 949\u2013958 (2022)","DOI":"10.1109\/CVPR52688.2022.00102"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., et al.: DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Iranmanesh, S. M., Chen, S. X., Lien, K.-C.: Pair DETR: toward faster convergent DETR. In: ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095608"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Wang, T., Yuan, L., Chen, Y., et al.: PNP-DETR: towards efficient visual analysis with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4661\u20134670 (2021)","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"3_CR20","unstructured":"Roh, B., Shin, J., Shin, W., et al.: Sparse DETR: efficient end-to-end object detection with learnable sparsity. arXiv preprint, arXiv:2111.14330 (2021)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., et al.: Microsoft COCO: common objects in context. In: Computer Vision\u2013ECCV 2014, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., et al.: Fast convergence of DETR with spatially modulated coattention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3621\u20133630 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., et al.: Less is more: focus attention for efficient DETR. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6674\u20136683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Chen, B., Wei, Z., Lei, W., et al.: GMMotion: neighborhood information matters for online multi-pedestrian tracking. In: Pacific Rim International Conference on Artificial Intelligence, pp. 76\u201388. Springer (2024)","DOI":"10.1007\/978-981-96-0122-6_8"}],"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\/978-981-96-9794-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T22:12:35Z","timestamp":1753308755000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_3","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":"15 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"}}]}}