{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:56:36Z","timestamp":1781538996709,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U25A20532"],"award-info":[{"award-number":["U25A20532"]}]},{"name":"the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","award":["VRLAB2025A01"],"award-info":[{"award-number":["VRLAB2025A01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810809","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"958-966","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HIRNet: Hypergraph-Induced Iterative Reasoning Network for Crowd Counting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2104-6214","authenticated-orcid":false,"given":"Ruihan","family":"Wang","sequence":"first","affiliation":[{"name":"Xiamen University, xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5894-8776","authenticated-orcid":false,"given":"Mengqi","family":"Lei","sequence":"additional","affiliation":[{"name":"Tsinghua University, beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9720-826X","authenticated-orcid":false,"given":"Siqi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2578-1574","authenticated-orcid":false,"given":"Wei","family":"Bao","sequence":"additional","affiliation":[{"name":"Tsinghua University, beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Lijia Deng Qinghua Zhou Shuihua Wang Juan\u00a0Manuel G\u00f3rriz and Yudong Zhang. 2024. Deep learning in crowd counting: A survey. CAAI Transactions on Intelligence Technology 9 5 (2024) 1043\u20131077.","DOI":"10.1049\/cit2.12241"},{"key":"e_1_3_3_1_5_2","unstructured":"Yihe Dong Will Sawin and Yoshua Bengio. 2020. Hnhn: Hypergraph networks with hyperedge neurons. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.12278 (2020)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Zizhu Fan Hong Zhang Zheng Zhang Guangming Lu Yudong Zhang and Yaowei Wang. 2022. A survey of crowd counting and density estimation based on convolutional neural network. Neurocomputing 472 (2022) 224\u2013251.","DOI":"10.1016\/j.neucom.2021.02.103"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Yifan Feng Jiangang Huang Shaoyi Du Shihui Ying Jun-Hai Yong Yipeng Li Guiguang Ding Rongrong Ji and Yue Gao. 2024. Hyper-yolo: When visual object detection meets hypergraph computation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).","DOI":"10.1109\/TPAMI.2024.3524377"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yue Gao Yifan Feng Shuyi Ji and Rongrong Ji. 2022. Hgnn+: General hypergraph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 3 (2022) 3181\u20133199.","DOI":"10.1109\/TPAMI.2022.3182052"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Yue Gao Shuyi Ji Xiangmin Han and Qionghai Dai. 2024. Hypergraph computation. Engineering 40 (2024) 188\u2013201.","DOI":"10.1016\/j.eng.2024.04.017"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Silky Goel Deepika Koundal and Rahul Nijhawan. 2025. Learning models in crowd analysis: A review. Archives of Computational Methods in Engineering 32 2 (2025) 943\u2013961.","DOI":"10.1007\/s11831-024-10151-1"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Shenjian Gong Zhaoliang Yao Wangmeng Zuo Jian Yang PongChi Yuen and Shanshan Zhang. 2025. Spatially adaptive pyramid feature fusion for scale-aware crowd counting. Pattern Recognition (2025) 111832.","DOI":"10.1016\/j.patcog.2025.111832"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02681"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01820"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/353"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"e_1_3_3_1_18_2","unstructured":"Diederik\u00a0P Kingma. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980 (2014)."},{"key":"e_1_3_3_1_19_2","unstructured":"Mengqi Lei Siqi Li Yihong Wu Han Hu You Zhou Xinhu Zheng Guiguang Ding Shaoyi Du Zongze Wu and Yue Gao. 2025. YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.17733 (2025)."},{"key":"e_1_3_3_1_20_2","unstructured":"Mengqi Lei Haochen Wu Xinhua Lv and Liangxiao Jiang. 2024. DDRANet: A Dynamic Density-Region-Aware Network for Crowd Counting. IEEE Signal Processing Letters (2024)."},{"key":"e_1_3_3_1_21_2","unstructured":"Mengqi Lei Yihong Wu Siqi Li Xinhu Zheng Juan Wang Yue Gao and Shaoyi Du. 2025. Softhgnn: Soft hypergraph neural networks for general visual recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.15325 (2025)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"e_1_3_3_1_24_2","unstructured":"Hui Lin Xiaopeng Hong Zhiheng Ma Yaowei Wang and Deyu Meng. 2024. Multidimensional measure matching for crowd counting. IEEE Transactions on Neural Networks and Learning Systems (2024)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00545"},{"key":"e_1_3_3_1_26_2","unstructured":"Xinyan Liu Guorong Li Yuankai Qi Zhenjun Han Anton van\u00a0den Hengel Nicu Sebe Ming-Hsuan Yang and Qingming Huang. 2024. Consistency-aware anchor pyramid network for crowd localization. IEEE transactions on pattern analysis and machine intelligence (2024)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6839"},{"key":"e_1_3_3_1_28_2","volume-title":"The Fourteenth International Conference on Learning Representations","author":"Luo Bingjun","year":"2026","unstructured":"Bingjun Luo, Tony Wang, Chaoqi Chen, and Xinpeng Ding. 2026. ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs. In The Fourteenth International Conference on Learning Representations."},{"key":"e_1_3_3_1_29_2","volume-title":"The Fourteenth International Conference on Learning Representations","author":"Luo Bingjun","year":"2026","unstructured":"Bingjun Luo, Tony Wang, Hanqi Chen, and Xinpeng Ding. 2026. Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and Gridding. In The Fourteenth International Conference on Learning Representations."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Sami Abdulla\u00a0Mohsen Saleh Shahrel\u00a0Azmin Suandi and Haidi Ibrahim. 2015. Recent survey on crowd density estimation and counting for visual surveillance. Engineering Applications of Artificial Intelligence 41 (2015) 103\u2013114.","DOI":"10.1016\/j.engappai.2015.01.007"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Deepak\u00a0Babu Sam Skand\u00a0Vishwanath Peri Mukuntha\u00a0Narayanan Sundararaman Amogh Kamath and R\u00a0Venkatesh Babu. 2020. Locate size and count: accurately resolving people in dense crowds via detection. IEEE transactions on pattern analysis and machine intelligence 43 8 (2020) 2739\u20132751.","DOI":"10.1109\/TPAMI.2020.2974830"},{"key":"e_1_3_3_1_33_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Vishwanath\u00a0A Sindagi Rajeev Yasarla and Vishal\u00a0M Patel. 2020. Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE transactions on pattern analysis and machine intelligence 44 5 (2020) 2594\u20132609.","DOI":"10.1109\/TPAMI.2020.3035969"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"e_1_3_3_1_36_2","unstructured":"Ye Tian Xiangxiang Chu and Hongpeng Wang. 2021. Cctrans: Simplifying and improving crowd counting with transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2109.14483 (2021)."},{"key":"e_1_3_3_1_37_2","unstructured":"Boyu Wang Huidong Liu Dimitris Samaras and Minh\u00a0Hoai Nguyen. 2020. Distribution matching for crowd counting. Advances in neural information processing systems 33 (2020) 1595\u20131607."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Juncheng Wang Junyu Gao Yuan Yuan and Qi Wang. 2023. Crowd localization from Gaussian mixture scoped knowledge and scoped teacher. IEEE Transactions on Image Processing 32 (2023) 1802\u20131814.","DOI":"10.1109\/TIP.2023.3251727"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00025"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Chenfeng Xu Dingkang Liang Yongchao Xu Song Bai Wei Zhan Xiang Bai and Masayoshi Tomizuka. 2022. Autoscale: Learning to scale for crowd counting. International Journal of Computer Vision 130 2 (2022) 405\u2013434.","DOI":"10.1007\/s11263-021-01542-z"},{"key":"e_1_3_3_1_41_2","unstructured":"Naganand Yadati Madhav Nimishakavi Prateek Yadav Vikram Nitin Anand Louis and Partha Talukdar. 2019. Hypergcn: A new method for training graph convolutional networks on hypergraphs. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Ying Yu Feng Zhu Jin Qian Hamido Fujita Jiamao Yu Kangli Zeng and Enhong Chen. 2025. CrowdFPN: crowd counting via scale-enhanced and location-aware feature pyramid network. Applied Intelligence 55 5 (2025) 359.","DOI":"10.1007\/s10489-025-06263-1"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/PRAI55851.2022.9904241"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Xia Zhao Limin Wang Yufei Zhang Xuming Han Muhammet Deveci and Milan Parmar. 2024. A review of convolutional neural networks in computer vision. Artificial Intelligence Review 57 4 (2024) 99.","DOI":"10.1007\/s10462-024-10721-6"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Xin Zhong Zhaoyi Yan Jing Qin Wangmeng Zuo and Weigang Lu. 2022. An improved normed-deformable convolution for crowd counting. IEEE Signal Processing Letters 29 (2022) 1794\u20131798.","DOI":"10.1109\/LSP.2022.3198371"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:30:56Z","timestamp":1781537456000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":45,"alternative-id":["10.1145\/3805622.3810809","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810809","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}