{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:03:56Z","timestamp":1784131436149,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819235094","type":"print"},{"value":"9789819235100","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3510-0_23","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:07:45Z","timestamp":1784128065000},"page":"270-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TMFF-Count: Text-Guided Multimodal Fusion Framework for Zero-Shot Object Counting"],"prefix":"10.1007","author":[{"given":"Yangjie","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunming","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mintao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"23_CR1","unstructured":"Lempitsky, V., Zisserman, A.: Learning To Count Objects in Images. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (Eds.), Advances in Neural Information Processing Systems (Vol. 23, pp. 1324\u20131332) (2010)."},{"key":"23_CR2","first-page":"669","volume":"2018","author":"E Lu","year":"2019","unstructured":"Lu, E., Xie, W., Zisserman, A.: Class-agnostic counting. Computer Vision \u2013 ACCV. 2018, 669\u2013684 (2019)","journal-title":"Computer Vision \u2013 ACCV"},{"key":"23_CR3","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M Hobley","year":"2023","unstructured":"Hobley, M., Prisacariu, V.: Learning to count anything: reference-less class-agnostic counting with weak supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)"},{"key":"23_CR4","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML), vol. 139, pp. 8748\u20138763, (2021)."},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2023.","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Jiang R., Liu, L., Chen, C.: CLIP-count: towards text-guided zero-shot object counting. In: Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), (2023).","DOI":"10.1145\/3581783.3611789"},{"key":"23_CR7","first-page":"2714","volume":"38","author":"S Kang","year":"2024","unstructured":"Kang, S., Moon, W., Kim, E., Heo, J.-P.: VLCounter: text-aware visual representation for zero-shot object counting. Proc. AAAI Conf. Artif. Intell. (AAAI). 38, 2714\u20132722 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Qian, Y., et al.: T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2025).","DOI":"10.1109\/CVPR52734.2025.02359"},{"key":"23_CR9","first-page":"368","volume":"2024","author":"H Zhu","year":"2024","unstructured":"Zhu, H., et al.: Zero-shot Object counting with good exemplars. Computer Vision \u2013 ECCV. 2024, 368\u2013385 (2024)","journal-title":"Computer Vision \u2013 ECCV"},{"key":"23_CR10","unstructured":"Sim\u00e9oni, O., et al., \u201cDINOv3,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2508.10104, 2025."},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Sharma, U., Nguyen, T., Hoai, M.: Learning to count everything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3394\u20133403, (2021).","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Hsieh, M.-R., Lin, Y.-L., Hsu, W.H.: Drone-based object counting by spatially regularized regional proposal network. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4145\u20134153, (2017).","DOI":"10.1109\/ICCV.2017.446"},{"key":"23_CR13","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"N Amini-Naieni","year":"2023","unstructured":"Amini-Naieni, N., Amini-Naieni, K., Han, T., Zisserman, A.: Open-world Text-specified Object Counting. In: Proceedings of the British Machine Vision Conference (BMVC) (2023)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Shi, M., Lu, H., Feng, C., Liu, C., Cao, Z.: Represent, compare, and learn: a similarity-aware framework for class-agnostic counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9519\u20139528, (2022).","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"23_CR15","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Z Huang","year":"2024","unstructured":"Huang, Z., Dai, M., Zhang, Y., Zhang, J., Shan, H.: Point, segment and count: a generalized framework for object counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Rao, Y. et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18082\u201318091, (2022).","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"23_CR17","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Y Zhong","year":"2022","unstructured":"Zhong, Y., et al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)"},{"key":"23_CR18","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: ZegCLIP: towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Doll\u00e1r, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5356\u20135364, 2019.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"\u0110uki\u0107, N., Luke\u017ei\u010d, A., Zavrtanik, V., Kristan, M.: A low-shot object counting network with iterative prototype adaptation. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), pp. 18826\u201318835, (2023).","DOI":"10.1109\/ICCV51070.2023.01730"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Shi, Z., Sun, Y., Zhang, M..: Training-free object counting with prompts, In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 323\u2013331, (2024).","DOI":"10.1109\/WACV57701.2024.00039"},{"key":"23_CR22","first-page":"38","volume":"2024","author":"S Liu","year":"2024","unstructured":"Liu, S., et al.: Grounding DINO: ,arrying DINO with grounded pre-training for open-set object detection. Computer Vision \u2013 ECCV. 2024, 38\u201355 (2024)","journal-title":"Computer Vision \u2013 ECCV"}],"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\/978-981-92-3510-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:07:49Z","timestamp":1784128069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3510-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819235094","9789819235100"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3510-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","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":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}