{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:41:33Z","timestamp":1769186493681,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5567-3_20","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:04Z","timestamp":1769116444000},"page":"284-297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Two-Stage Modal Feature Enhancement for\u00a0Multispectral Object Detection"],"prefix":"10.1007","author":[{"given":"Tichao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ziliang","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Qieshi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yimin","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Hou, S., Yang, M., Zheng, W.S., Gao, S.: Multispectral transformer fusion via exploiting similarity and complementarity for robust pedestrian detection. Pattern Recogn. (PR) 162, 111383 (2025)","DOI":"10.1016\/j.patcog.2025.111383"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Qingyun, F., Zhaokui, W.: Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery. Pattern Recogn. (PR) 130, 108786 (2022)","DOI":"10.1016\/j.patcog.2022.108786"},{"issue":"12","key":"20_CR3","doi-asserted-by":"publisher","first-page":"20628","DOI":"10.1109\/TITS.2024.3450584","volume":"25","author":"Y Xing","year":"2024","unstructured":"Xing, Y., et al.: MS-DETR: multispectral pedestrian detection transformer with loosely coupled fusion and modality-balanced optimization. IEEE Trans. Intell. Transp. Syst. (TITS) 25(12), 20628\u201320642 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst. (TITS)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Hsu, W.-Y., Yang, P.-Y.: Pedestrian detection using multi-scale structure-enhanced super-resolution. IEEE Trans. Intell. Transp. Syst. (TITS) 24(11), 12312\u201312322 (2023)","DOI":"10.1109\/TITS.2023.3287574"},{"key":"20_CR5","doi-asserted-by":"publisher","first-page":"6090","DOI":"10.1109\/TIP.2023.3328471","volume":"32","author":"S Taiyi","year":"2023","unstructured":"Taiyi, S., Wang, H., Wang, L.: Multi-level content-aware boundary detection for temporal action proposal generation. IEEE Trans. Image Process. (TIP) 32, 6090\u20136101 (2023)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"20_CR6","first-page":"1","volume":"74","author":"W Qingtian","year":"2025","unstructured":"Qingtian, W., Wang, X., Li, N., Fong, S., Zhang, L., Yang, J.: Real-time face and facial landmark joint detection based on end-to-end deep network. IEEE Trans. Instrum. Meas. (TIM) 74, 1\u201313 (2025)","journal-title":"IEEE Trans. Instrum. Meas. (TIM)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Lee, W.Y., Jovanov, L., Philips, W.: Cross-modality attention and multimodal fusion transformer for pedestrian detection. In: European Conference on Computer Vision Workshops (ECCVW), pp. 608\u2013623 (2023)","DOI":"10.1007\/978-3-031-25072-9_41"},{"key":"20_CR8","first-page":"1","volume":"62","author":"D Liu","year":"2024","unstructured":"Liu, D., Zhang, J., Qi, Y., Yinhu, W., Zhang, Y.: Tiny object detection in remote sensing images based on object reconstruction and multiple receptive field adaptive feature enhancement. IEEE Trans. Geosci. Remote Sens. (TGRS) 62, 1\u201313 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens. (TGRS)"},{"key":"20_CR9","unstructured":"Qingyun, F., Dapeng, H., Zhaokui, W.: Cross-modality fusion transformer for multispectral object detection (2022)"},{"key":"20_CR10","unstructured":"FA\u00a0Team et\u00a0al. Free flir thermal dataset for algorithm training"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., Zhou, W.: LLVIP: a visible-infrared paired dataset for low-light vision. In: IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3489\u20133497 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"issue":"1","key":"20_CR12","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 38(1), 142\u2013158 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Inoue, R., Tsuchiya, M., Yasui, Y.: Decoupled PROB: decoupled query initialization tasks and objectness-class learning for open world object detection. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8207\u20138216 (2025)","DOI":"10.1109\/WACV61041.2025.00796"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"9","key":"20_CR15","doi-asserted-by":"publisher","first-page":"5967","DOI":"10.1109\/TPAMI.2024.3380604","volume":"46","author":"C Zhao","year":"2024","unstructured":"Zhao, C., Hsiao, J.H., Chan, A.B.: Gradient-based instance-specific visual explanations for object specification and object discrimination. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 46(9), 5967\u20135985 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"20_CR17","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B, Jiri, M., Nicu, S., Max, W. (eds.) European Conference on Computer Vision (ECCV), pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision (ECCV), pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"7","key":"20_CR20","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1109\/TCSVT.2023.3234340","volume":"33","author":"W Tang","year":"2023","unstructured":"Tang, W., Fazhi He, Yu., Liu, Y.D., Si, T.: DATFuse: infrared and visible image fusion via dual attention transformer. IEEE Trans. Circ. Syst. Video Technol. (TCSVT) 33(7), 3159\u20133172 (2023)","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"key":"20_CR21","first-page":"1","volume":"71","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Chen, Y., Shao, W., Li, H., Zhang, L.: SwinFuse: a residual swin transformer fusion network for infrared and visible images. IEEE Trans. Instrum. Meas. (TIM) 71, 1\u201312 (2022)","journal-title":"IEEE Trans. Instrum. Meas. (TIM)"},{"key":"20_CR22","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1109\/LSP.2023.3309578","volume":"30","author":"S You","year":"2023","unstructured":"You, S., Xie, X., Feng, Y., Mei, C., Ji, Y.: Multi-scale aggregation transformers for multispectral object detection. IEEE Signal Processing Letters (SPL) 30, 1172\u20131176 (2023)","journal-title":"IEEE Signal Processing Letters (SPL)"},{"key":"20_CR23","first-page":"1","volume":"61","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Lei, J., Xie, W., Fang, Z., Li, Y., Qian, D.: SuperYOLO: super resolution assisted object detection in multimodal remote sensing imagery. IEEE Trans. Geosci. Remote Sens. (TGRS) 61, 1\u201315 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens. (TGRS)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Cai, H., Yin, D., Yu, F., Xiong, S.: MFT: modal fusion transformer for cross-modal fusion in 3D object detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10888740"},{"key":"20_CR25","first-page":"1","volume":"74","author":"S Huang","year":"2025","unstructured":"Huang, S., Kong, X., Yang, Y., Wan, W., Song, Z.: FTSFN: a two-stage feature transfer and supplement fusion network for infrared and visible image fusion. IEEE Trans. Instrum. Meas. (TIM) 74, 1\u201315 (2025)","journal-title":"IEEE Trans. Instrum. Meas. (TIM)"},{"issue":"5","key":"20_CR26","doi-asserted-by":"publisher","first-page":"3673","DOI":"10.1109\/TPAMI.2025.3535617","volume":"47","author":"H Li","year":"2025","unstructured":"Li, H., Yang, Z., Zhang, Y., Jia, W., Zhengtao, Yu., Liu, Yu.: MulFS-CAP: multimodal fusion-supervised cross-modality alignment perception for unregistered infrared-visible image fusion. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 47(5), 3673\u20133690 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"issue":"2","key":"20_CR27","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1109\/TCSVT.2023.3293228","volume":"34","author":"X Li","year":"2024","unstructured":"Li, X., Li, Y., Chen, H., Peng, Y., Pan, P.: CCAFusion: cross-modal coordinate attention network for infrared and visible image fusion. IEEE Trans. Circ. Syst. Video Technol. (TCSVT) 34(2), 866\u2013881 (2024)","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, W., Cui, H., Wang, H., He, Y., Lu, H.: FreeFusion: infrared and visible image fusion via cross reconstruction learning. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 1\u201317 (2025)","DOI":"10.1109\/TPAMI.2025.3572599"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Park, S., Vien, A.G., Lee, C.: Cross-modal transformers for infrared and visible image fusion. IEEE Trans. Circ. Syst. Video Technol. (TCSVT) 34(2), 770\u2013785 (2024)","DOI":"10.1109\/TCSVT.2023.3289170"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: CDDFuse: correlation-driven dual-branch feature decomposition for multi-modality image fusion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5906\u20135916 (2023)","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"20_CR31","unstructured":"Ultralytics. Yolov5 (024)"},{"key":"20_CR32","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement (2018)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Shen, J., Chen, Y., Liu, Y., Zuo, X., Fan, H., Yang, W.: ICAFusion: iterative cross-attention guided feature fusion for multispectral object detection. Pattern Recogn. (PR) 145, 109913 (2024)","DOI":"10.1016\/j.patcog.2023.109913"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5567-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:10Z","timestamp":1769116450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}