{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T13:54:14Z","timestamp":1784296454971,"version":"3.55.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726514","type":"print"},{"value":"9783031726521","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72652-1_22","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"368-385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Zero-Shot Object Counting with\u00a0Good Exemplars"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1607-7283","authenticated-orcid":false,"given":"Huilin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7924-8620","authenticated-orcid":false,"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8190-1438","authenticated-orcid":false,"given":"Zhengwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0642-7684","authenticated-orcid":false,"given":"Yu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5242-0467","authenticated-orcid":false,"given":"Xian","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arteta, C., Lempitsky, V.S., Zisserman, A.: Counting in the wild. In: Proceedings of European Conference on Computer Vision, pp. 483\u2013498 (2016)","DOI":"10.1007\/978-3-319-46478-7_30"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: RaSa: relation and sensitivity aware representation learning for text-based person search. In: Proceeding of International Joint Conference on Artificial Intelligence, pp. 555\u2013563 (2023)","DOI":"10.24963\/ijcai.2023\/62"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: Proceedings of European Conference on Computer Vision, pp. 397\u2013414 (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"issue":"6","key":"22_CR4","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TPAMI.2020.3043372","volume":"44","author":"L Chai","year":"2022","unstructured":"Chai, L., Liu, Y., Liu, W., Han, G., He, S.: CrowdGAN: identity-free interactive crowd video generation and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 2856\u20132871 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Ye, M., Jiang, D.: Towards modality-agnostic person re-identification with descriptive query. In: Proceedings of the IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 15128\u201315137 (2023)","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"22_CR6","unstructured":"Dou, Z., et al.: Coarse-to-fine vision-language pre-training with fusion in the backbone. In: Advance Neural Information Processing System, pp. 32942\u201332956 (2022)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Gong, S., Zhang, S., Yang, J., Dai, D., Schiele, B.: Class-agnostic object counting robust to intraclass diversity. In: Proceedings of the Conference on Computer Vision, pp. 388\u2013403 (2022)","DOI":"10.1007\/978-3-031-19827-4_23"},{"key":"22_CR9","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/TIFS.2023.3318956","volume":"19","author":"S He","year":"2023","unstructured":"He, S., et al.: Region generation and assessment network for occluded person re-identification. IEEE Trans. Inf. Forensics Secur. 19, 120\u2013132 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"22_CR10","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 Pattern Recognition (2023)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Hsieh, M., Lin, Y., Hsu, W.H.: Drone-based object counting by spatially regularized regional proposal network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision, pp. 4165\u20134173 (2017)","DOI":"10.1109\/ICCV.2017.446"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dai, M., Zhang, Y., Zhang, J., Shan, H.: Point, segment and count: a generalized framework for object counting. arXiv:2311.12386 (2023)","DOI":"10.1109\/CVPR52733.2024.01615"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, R., Liu, L., Chen, C.: CLIP-Count: towards text-guided zero-shot object counting. In: Proceedings of the ACM Multimedia, pp. 4535\u20134545 (2023)","DOI":"10.1145\/3581783.3611789"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Kang, S., Moon, W., Kim, E., Heo, J.: VLCounter: ext-aware visual representation for zero-shot object counting. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2714\u20132722 (2024)","DOI":"10.1609\/aaai.v38i3.28050"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3992\u20134003 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"22_CR16","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International Conference Machine Learning, pp. 19730\u201319742 (2023)"},{"key":"22_CR17","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the International Conference Machine Learning, pp. 12888\u201312900 (2022)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Sun, L., Li, Q.: CLIP-ReID: exploiting vision-language model for image re-identification without concrete text labels. In: Proceedings of the AAAI Conference Artificial Intelligence, pp. 1405\u20131413 (2023)","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"22_CR19","unstructured":"Liu, C., Zhong, Y., Zisserman, A., Xie, W.: CounTR: transformer-based generalised visual counting. In: Proceedings of the Brit. Machine Vision Conference, p.\u00a0370 (2022)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Liu, X., Yang, J., Ding, W., Wang, T., Wang, Z., Xiong, J.: Adaptive mixture regression network with local counting map for crowd counting. In: Proceedings of the European Conference on Computer Vision, pp. 241\u2013257 (2020)","DOI":"10.1007\/978-3-030-58586-0_15"},{"issue":"7","key":"22_CR22","doi-asserted-by":"publisher","first-page":"9248","DOI":"10.1109\/TPAMI.2022.3232712","volume":"45","author":"Y Liu","year":"2023","unstructured":"Liu, Y., et al.: Reducing spatial labeling redundancy for active semi-supervised crowd counting. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 9248\u20139255 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR23","doi-asserted-by":"publisher","first-page":"6800","DOI":"10.1109\/TIP.2020.2994410","volume":"29","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Crowd counting via cross-stage refinement networks. IEEE Trans. Image Process. 29, 6800\u20136812 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xu, D., Ren, S., Wu, H., Cai, H., He, S.: Fine-grained domain adaptive crowd counting via point-derived segmentation. In: Proceedings of the IEEE International Conference Multimedia Expo, pp. 2363\u20132368 (2023)","DOI":"10.1109\/ICME55011.2023.00403"},{"key":"22_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representation (2019)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Lu, E., Xie, W., Zisserman, A.: Class-agnostic counting. In: Proceedings of the Asian Conference on Computer Vision, pp. 669\u2013684 (2019)","DOI":"10.1007\/978-3-030-20893-6_42"},{"key":"22_CR27","unstructured":"Ming, Y., Cai, Z., Gu, J., Sun, Y., Li, W., Li, Y.: Delving into out-of-distribution detection with vision-language representations. In: Advance Neural Information Processing System, pp. 35087\u201335102 (2022)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Mundhenk, T.N., Konjevod, G., Sakla, W.A., Boakye, K.: A large contextual dataset for classification, detection and counting of cars with deep learning. In: Proceedings of the European Conference on Computer Vision, pp. 785\u2013800 (2016)","DOI":"10.1007\/978-3-319-46487-9_48"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Pham, C., Nguyen, K., Hoai, M.: Few-shot object counting and detection. In: Proceedings of the European Conference on Computing Vision, pp. 348\u2013365 (2022)","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"22_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Le, H.M., Hoai, M.: Iterative crowd counting. In: Proceedings of the European Conference on Computing Vision, pp. 278\u2013293 (2018)","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Nguyen, M.H.: Exemplar free class agnostic counting. In: Proceedings of the Asian Conference on Computing Vision, pp. 71\u201387 (2022)","DOI":"10.1007\/978-3-031-26316-3_5"},{"key":"22_CR33","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 Computing Vision Pattern Recognition, pp. 3394\u20133403 (2021)","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Sam, D.B., Agarwalla, A., Joseph, J., Sindagi, V.A., Babu, R.V., Patel, V.M.: Completely self-supervised crowd counting via distribution matching. In: Proceedings of the European Conference onComputing Vision, pp. 186\u2013204 (2022)","DOI":"10.1007\/978-3-031-19821-2_11"},{"key":"22_CR35","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 Computing Vision Pattern Recognition, pp. 9529\u20139538 (2022)","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"22_CR36","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 Applied Computing Vision, pp. 323\u2013331 (2024)","DOI":"10.1109\/WACV57701.2024.00039"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Song, S., et al.: Vision-language pre-training for boosting scene text detectors. In: Proceedings of the IEEE\/CVF Conference Computing Vision Pattern Recognition, pp. 15681\u201315691 (2022)","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Sun, G., et al.: Indiscernible object counting in underwater scenes. In: Proceedings of the IEEE\/CVF Conference on Computing Vision Pattern Recognition, pp. 13791\u201313801 (2023)","DOI":"10.1109\/CVPR52729.2023.01325"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Tian, C., Zhang, X., Liang, X., Li, B., Sun, Y., Zhang, S.: Knowledge distillation with fast CNN for license plate detection. IEEE Trans. Intell. Transp. Syst. (2023)","DOI":"10.1109\/TIV.2023.3330164"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Tyagi, A.K., Mohapatra, C., Das, P., Makharia, G., Mehra, L., AP, P.: Mausam: DeGPR: Deep guided posterior regularization for multi-class cell detection and counting. In: Proceedings of the IEEE\/CVF Conference Computing Vision Pattern Recognition, pp. 23913\u201323923 (2023)","DOI":"10.1109\/CVPR52729.2023.02290"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"\u0110ukic, N., Lukezic, A., Zavrtanik, V., Kristan, M.: A low-shot object counting network with iterative prototype adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computing Vision, pp. 18872\u201318881 (2023)","DOI":"10.1109\/ICCV51070.2023.01730"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xiao, L., Cao, Z., Lu, H.: Vision transformer off-the-shelf: a surprising baseline for few-shot class-agnostic counting. In: Proceedings of the AAAI Conference Artificial Intelligence, pp. 5832\u20135840 (2024)","DOI":"10.1609\/aaai.v38i6.28396"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Xie, D., Liu, L., Zhang, S., Tian, J.: A unified multi-modal structure for retrieving tracked vehicles through natural language descriptions. In: Proceedings of the IEEE\/CVF Conference Computing Vision Pattern Recognition Workshops, pp. 5418\u20135426 (2023)","DOI":"10.1109\/CVPRW59228.2023.00572"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Chai, L., Liu, W., Liu, Y., Ren, S., He, S.: Glance to count: learning to rank with anchors for weakly-supervised crowd counting. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 342\u2013351 (2024)","DOI":"10.1109\/WACV57701.2024.00041"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Nguyen, V., Ranjan, V., Samaras, D.: Zero-shot object counting. In: Proceedings of the IEEE\/CVF Conference Computer Vision Pattern Recognition, pp. 15548\u201315557 (2023)","DOI":"10.1109\/CVPR52729.2023.01492"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Yang, S., Su, H., Hsu, W.H., Chen, W.: Class-agnostic few-shot object counting. In: Proceedings of the IEEE\/CVF Winter Conference on Application Computing Vision, pp. 869\u2013877 (2021)","DOI":"10.1109\/WACV48630.2021.00091"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"You, Z., Yang, K., Luo, W., Lu, X., Cui, L., Le, X.: Few-shot object counting with similarity-aware feature enhancement. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6304\u20136313 (2023)","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liu, K., Gao, F., Li, X., Wang, G.: Vision-based vehicle detecting and counting for traffic flow analysis. In: Proceedings of the IEEE International Joint Conference Neural Networks, pp. 2267\u20132273 (2016)","DOI":"10.1109\/IJCNN.2016.7727480"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Wu, J., Qin, Y., Zhang, F., Cui, L.: Zero-shot instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 2593\u20132602 (2021)","DOI":"10.1109\/CVPR46437.2021.00262"},{"key":"22_CR50","doi-asserted-by":"publisher","first-page":"3842","DOI":"10.1109\/TMM.2023.3316437","volume":"26","author":"H Zhu","year":"2024","unstructured":"Zhu, H., Yuan, J., Zhong, X., Liao, L., Wang, Z.: Find gold in sand: fine-grained similarity mining for domain-adaptive crowd counting. IEEE Trans. Multimedia 26, 3842\u20133855 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, H., Yuan, J., Zhong, X., Yang, Z., Wang, Z., He, S.: DAOT: domain-agnostically aligned optimal transport for domain-adaptive crowd counting. In: Proceedings of the ACM Multimedia, pp. 4319\u20134329 (2023)","DOI":"10.1145\/3581783.3611793"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72652-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T12:01:38Z","timestamp":1732968098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72652-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031726514","9783031726521"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72652-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}