{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:11:52Z","timestamp":1783656712260,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Science and Technology Council, Taiwan","award":["NSTC-113-2640-B-005-001, NSTC-112-2221-E-A49-059-MY3 and NSTC-112-2221-E-A49-094-MY3"],"award-info":[{"award-number":["NSTC-113-2640-B-005-001, NSTC-112-2221-E-A49-059-MY3 and NSTC-112-2221-E-A49-094-MY3"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755385","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"8234-8243","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Flowing Crowd to Count Flows: A Self-Supervised Framework for Video Individual Counting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6100-6520","authenticated-orcid":false,"given":"Feng-Kai","family":"Huang","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9804-5046","authenticated-orcid":false,"given":"Bo-Lun","family":"Huang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0935-3842","authenticated-orcid":false,"given":"Li-Wu","family":"Tsao","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-3980","authenticated-orcid":false,"given":"Jhih-Ciang","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-077X","authenticated-orcid":false,"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7875","authenticated-orcid":false,"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Self-supervised object-centric learning for videos. Advances in Neural Information Processing Systems","author":"Aydemir G\u00f6rkay","year":"2023","unstructured":"G\u00f6rkay Aydemir, Weidi Xie, and Fatma Guney. 2023. Self-supervised object-centric learning for videos. Advances in Neural Information Processing Systems (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01343"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01136"},{"key":"e_1_3_2_2_6_1","volume-title":"Jigsaw-vit: Learning jigsaw puzzles in vision transformer. Pattern Recognition Letters","author":"Chen Yingyi","year":"2023","unstructured":"Yingyi Chen, Xi Shen, Yahui Liu, Qinghua Tao, and Johan AK Suykens. 2023. Jigsaw-vit: Learning jigsaw puzzles in vision transformer. Pattern Recognition Letters (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"Mamico: Macro-to-micro semantic correspondence for self-supervised video representation learning. In ACM Multimedia.","author":"Fang Bo","year":"2022","unstructured":"Bo Fang, Wenhao Wu, Chang Liu, Yu Zhou, Dongliang He, and Weipinng Wang. 2022. Mamico: Macro-to-micro semantic correspondence for self-supervised video representation learning. In ACM Multimedia."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"e_1_3_2_2_10_1","volume-title":"Siamese masked autoencoders. Advances in Neural Information Processing Systems","author":"Gupta Agrim","year":"2023","unstructured":"Agrim Gupta, Jiajun Wu, Jia Deng, and Fei-Fei Li. 2023. Siamese masked autoencoders. Advances in Neural Information Processing Systems (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 3083-3092","author":"Han Tao","year":"2022","unstructured":"Tao Han, Lei Bai, Junyu Gao, Qi Wang, and Wanli Ouyang. 2022. Dr. vic: Decomposition and reasoning for video individual counting. In IEEE Conference on Computer Vision and Pattern Recognition. 3083-3092."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Qi He Zhaoquan Yuan Xiao Wu and Jun-Yan He. 2022. Domain-Specific Conditional Jigsaw Adaptation for Enhancing transferability and Discriminability. In ACM Multimedia.","DOI":"10.1145\/3503161.3547890"},{"key":"e_1_3_2_2_13_1","volume-title":"Asian Conference on Computer Vision.","author":"Hossain Mohammad Asiful","year":"2020","unstructured":"Mohammad Asiful Hossain, Kevin Cannons, Daesik Jang, Fabio Cuzzolin, and Zhan Xu. 2020. Video-based crowd counting using a multi-scale optical flow pyramid network. In Asian Conference on Computer Vision."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jretconser.2023.103355"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"e_1_3_2_2_16_1","volume-title":"A comprehensive survey of recent trends in deep learning for digital images augmentation. Artificial Intelligence Review","author":"Khalifa Nour Eldeen","year":"2022","unstructured":"Nour Eldeen Khalifa, Mohamed Loey, and Seyedali Mirjalili. 2022. A comprehensive survey of recent trends in deep learning for digital images augmentation. Artificial Intelligence Review (2022)."},{"key":"e_1_3_2_2_17_1","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, Vol. 25 (2012)."},{"key":"e_1_3_2_2_18_1","first-page":"2050","article-title":"DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy","author":"Lei Yi","year":"2024","unstructured":"Yi Lei, Huilin Zhu, Jingling Yuan, Guangli Xiang, Xian Zhong, and Shengfeng He. 2024. DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy. In ACM Multimedia. 2050-2058.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205210"},{"key":"e_1_3_2_2_20_1","unstructured":"Qiankun Li Xiaolong Huang Zhifan Wan Lanqing Hu Shuzhe Wu Jie Zhang Shiguang Shan and Zengfu Wang. 2023. Data-efficient masked video modeling for self-supervised action recognition. In ACM Multimedia."},{"key":"e_1_3_2_2_21_1","first-page":"10258","article-title":"Prototype-Guided Dual-Transformer Reasoning for Video Individual Counting","author":"Li Rui","year":"2024","unstructured":"Rui Li, Yishu Liu, Huafeng Li, Jinxing Li, and Guangming Lu. 2024. Prototype-Guided Dual-Transformer Reasoning for Video Individual Counting. In ACM Multimedia. 10258-10267.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_2_22_1","first-page":"3395","article-title":"Gramformer: learning crowd counting via graph-modulated transformer","volume":"38","author":"Lin Hui","year":"2024","unstructured":"Hui Lin, Zhiheng Ma, Xiaopeng Hong, Qinnan Shangguan, and Deyu Meng. 2024. Gramformer: learning crowd counting via graph-modulated transformer. In Association for the Advancement of Artificial Intelligence, Vol. 38. 3395-3403.","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_26"},{"key":"e_1_3_2_2_24_1","first-page":"8151","article-title":"Counting people by estimating people flows","volume":"44","author":"Liu Weizhe","year":"2021","unstructured":"Weizhe Liu, Mathieu Salzmann, and Pascal Fua. 2021. Counting people by estimating people flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 11 (2021), 8151-8166.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_25_1","volume-title":"Weakly Supervised Video Individual Counting. In IEEE Conference on Computer Vision and Pattern Recognition. 19228-19237","author":"Liu Xinyan","year":"2024","unstructured":"Xinyan Liu, Guorong Li, Yuankai Qi, Ziheng Yan, Zhenjun Han, Anton Van Den Hengel, Ming-Hsuan Yang, and Qingming Huang. 2024b. Weakly Supervised Video Individual Counting. In IEEE Conference on Computer Vision and Pattern Recognition. 19228-19237."},{"key":"e_1_3_2_2_26_1","volume-title":"CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding. In IEEE International Conference on Robotics and Automation.","author":"Liu Yunze","year":"2024","unstructured":"Yunze Liu, Changxi Chen, Zifan Wang, and Li Yi. 2024a. CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding. In IEEE International Conference on Robotics and Automation."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050059"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"e_1_3_2_2_31_1","volume-title":"David Osowiechi, Ismail Ben Ayed, and Christian Desrosiers.","author":"Noori Mehrdad","year":"2024","unstructured":"Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A Vargas Hakim, David Osowiechi, Ismail Ben Ayed, and Christian Desrosiers. 2024. Tfs-vit: Token-level feature stylization for domain generalization. Pattern Recognition (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Learning Representations","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (2015)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00386"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_2_2_36_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_2_2_37_1","volume-title":"European Conference on Computer Vision.","author":"Tumanyan Narek","year":"2024","unstructured":"Narek Tumanyan, Assaf Singer, Shai Bagon, and Tali Dekel. 2024. Dino-tracker: Taming dino for self-supervised point tracking in a single video. In European Conference on Computer Vision."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06381-7_11"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00644"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"e_1_3_2_2_41_1","first-page":"1964","article-title":"Tracking game: Self-adaptative agent based multi-object tracking","author":"Wang Shuai","year":"2022","unstructured":"Shuai Wang, Da Yang, Yubin Wu, Yang Liu, and Hao Sheng. 2022. Tracking game: Self-adaptative agent based multi-object tracking. In ACM Multimedia. 1964-1972.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"e_1_3_2_2_43_1","first-page":"5740","article-title":"Smiletrack: Similarity learning for occlusion-aware multiple object tracking","volume":"38","author":"Wang Yu-Hsiang","year":"2024","unstructured":"Yu-Hsiang Wang, Jun-Wei Hsieh, Ping-Yang Chen, Ming-Ching Chang, Hung-Hin So, and Xin Li. 2024. Smiletrack: Similarity learning for occlusion-aware multiple object tracking. In Association for the Advancement of Artificial Intelligence, Vol. 38. 5740-5748.","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"e_1_3_2_2_44_1","volume-title":"Chain: Exploring global-local spatio-temporal information for improved self-supervised video hashing. In ACM Multimedia.","author":"Wei Rukai","year":"2023","unstructured":"Rukai Wei, Yu Liu, Jingkuan Song, Heng Cui, Yanzhao Xie, and Ke Zhou. 2023. Chain: Exploring global-local spatio-temporal information for improved self-supervised video hashing. In ACM Multimedia."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00772"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00506"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012554769303412"},{"key":"e_1_3_2_2_48_1","volume-title":"A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognition","author":"Xu Mingle","year":"2023","unstructured":"Mingle Xu, Sook Yoon, Alvaro Fuentes, and Dong Sun Park. 2023. A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognition (2023)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Wenhan Yang Rizhao Cai and Alex Kot. 2022. Image inpainting detection via enriched attentive pattern with near original image augmentation. In ACM Multimedia.","DOI":"10.1145\/3503161.3547921"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS-C57518.2022.00124"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01359"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_2_54_1","first-page":"1192","article-title":"Boosting end-to-end multi-object tracking and person search via knowledge distillation","author":"Zhang Wei","year":"2021","unstructured":"Wei Zhang, Lingxiao He, Peng Chen, Xingyu Liao, Wu Liu, Qi Li, and Zhenan Sun. 2021a. Boosting end-to-end multi-object tracking and person search via knowledge distillation. In ACM Multimedia. 1192-1201.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_2_55_1","volume-title":"Fairmot: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision","author":"Zhang Yifu","year":"2021","unstructured":"Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, and Wenyu Liu. 2021b. Fairmot: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision (2021), 3069-3087."},{"key":"e_1_3_2_2_56_1","first-page":"8740","article-title":"Hybrid Cost Volume for Memory-Efficient Optical Flow","author":"Zhao Yang","year":"2024","unstructured":"Yang Zhao, Gangwei Xu, and Gang Wu. 2024. Hybrid Cost Volume for Memory-Efficient Optical Flow. In ACM Multimedia. 8740-8749.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_43"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Jiquan Zhong Xiaolin Huang and Xiao Yu. 2023. Multi-frame self-supervised depth estimation with multi-scale feature fusion in dynamic scenes. In ACM Multimedia.","DOI":"10.1145\/3581783.3612042"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:29Z","timestamp":1765339709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755385","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755385","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}