{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T07:03:26Z","timestamp":1763795006840,"version":"3.45.0"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"12","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176027"],"award-info":[{"award-number":["62176027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Chongqing Talent","award":["cstc2024ycjh-bgzxm0082"],"award-info":[{"award-number":["cstc2024ycjh-bgzxm0082"]}]},{"name":"Central University Operating Expenses","award":["2024CDJGF-044"],"award-info":[{"award-number":["2024CDJGF-044"]}]},{"name":"Chongqing New YC Project","award":["CSTB2024YCJH-KYXM0126"],"award-info":[{"award-number":["CSTB2024YCJH-KYXM0126"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>\n                    Graphs offer a flexible structure for vision tasks, with CNNs and Transformers conditioned as two specific cases of graph structures. In CNNs, the input images are treated as graphs where only neighboring patches are connected, whereas Transformers view images as fully connected graphs. To leverage the potential of graphs in video representation learning, effective graph generation and training methods are crucial. To this end, we propose VideoGNN, which represents the video as a discrete time dynamic graph and learns the dynamic graph efficiently. Given the multitude of frames in videos, we introduce an efficient graph generation module characterized by low complexity and high quality, facilitating the transformation of videos into dynamic graphs. Additionally, we introduce a dual-view graph neural network to capture spatial and temporal information from the generated dynamic graphs. Then, a sequential model is applied to capture the long-term temporal information and generate the final frame embeddings. Experiments demonstrate that VideoGNN can achieve competitive results in terms of graph quality assessment and video downstream tasks. The codes are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Dodo-D-Caster\/VideoGNN\">https:\/\/github.com\/Dodo-D-Caster\/VideoGNN<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3760532","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T16:00:46Z","timestamp":1755532846000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["VideoGNN: Video Representation Learning via Dynamic Graph Modelling"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1477-7352","authenticated-orcid":false,"given":"Zijie","family":"Zhou","sequence":"first","affiliation":[{"name":"State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-3641","authenticated-orcid":false,"given":"Mingliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9576-5433","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-3955","authenticated-orcid":false,"given":"Huayan","family":"Pu","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5135-5165","authenticated-orcid":false,"given":"Leong Hou","family":"U","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3761-1759","authenticated-orcid":false,"given":"Xuekai","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0231-3196","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"BNU-UIC Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, Guangdong, China and Guangdong Key Lab of AI Multi-Modal Data Processing, BNU-HKBU United International College, Zhuhai, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"key":"e_1_3_1_2_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Alon Uri","year":"2021","unstructured":"Uri Alon and Eran Yahav. 2021. On the bottleneck of graph neural networks and its practical implications. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=i80OPhOCVH2"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"e_1_3_1_6_2","first-page":"4316","volume-title":"Advances in Neural Information Processing Systems","author":"Chen Rongqin","year":"2022","unstructured":"Rongqin Chen, Shenghui Zhang, Leong Hou U, and Ye Li. 2022. Redundancy-free message passing for graph neural networks. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 4316\u20134327."},{"key":"e_1_3_1_7_2","volume-title":"Convolutional Neural Network for Sentence Classification","author":"Chen Yahui","year":"2015","unstructured":"Yahui Chen. 2015. Convolutional Neural Network for Sentence Classification. Master\u2019s thesis. University of Waterloo."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_41"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10393912"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01279"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/85"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01037"},{"key":"e_1_3_1_14_2","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30, Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_15_2","first-page":"8291","article-title":"Vision GNN: An image is worth graph of nodes","volume":"35","author":"Han Kai","year":"2022","unstructured":"Kai Han, Yunhe Wang, Jianyuan Guo, Yehui Tang, and Enhua Wu. 2022. Vision GNN: An image is worth graph of nodes. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Neural Information Processing Systems, 8291\u20138303.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611745"},{"key":"e_1_3_1_20_2","unstructured":"Forrest N. Iandola Song Han Matthew W. Moskewicz Khalid Ashraf William J. Dally and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv:1602.07360. Retrieved from https:\/\/arxiv.org\/abs\/1602.07360"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01890"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00219"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170249"},{"key":"e_1_3_1_24_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3262163"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3688801"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441734"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_14"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00585"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01740"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126624500749"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02060"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371845"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390565"},{"key":"e_1_3_1_40_2","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in Neural Information Processing Systems. Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence and K.Q. Weinberger (Eds.), Vol. 27, Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_41_2","unstructured":"Khurram Soomro Amir Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402. Retrieved from https:\/\/arxiv.org\/abs\/1212.0402"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3615868"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02276"},{"key":"e_1_3_1_44_2","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","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. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho and A. Oh (Eds.), Vol. 35, Neural Information Processing Systems, 10078\u201310093.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_1_46_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan and R. Garnettpublisher (Eds.), Vol. 30, Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-023-03267-y"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572914"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109665"},{"key":"e_1_3_1_52_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks? In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=ryGs6iA5Km"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00811"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1142\/S021800142354023X"},{"key":"e_1_3_1_56_2","first-page":"28877","article-title":"Do transformers really perform badly for graph representation","volume":"34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation? In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang and J. Wortman Vaughan (Eds.), Vol. 34, Neural Information Processing Systems, 28877\u201328888.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01774"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/NNICE61279.2024.10499068"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2022.3147145"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514041"},{"key":"e_1_3_1_61_2","first-page":"11458","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zheng Cheng","year":"2020","unstructured":"Cheng Zheng, Bo Zong, Wei Cheng, Dongjin Song, Jingchao Ni, Wenchao Yu, Haifeng Chen, and Wei Wang. 2020. Robust graph representation learning via neural sparsification. In Proceedings of the International Conference on Machine Learning. PMLR, 11458\u201311468."},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/614"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33466"},{"key":"e_1_3_1_65_2","unstructured":"Yuecai Zhu Fuyuan Lyu Chengming Hu Chen Xi and Xue Liu. 2022. Encoder-decoder architecture for supervised dynamic graph learning: A survey. arXiv:2203.10480. Retrieved from https:\/\/arxiv.org\/abs\/2203.10480"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00507"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640815"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3760532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T07:00:05Z","timestamp":1763794805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3760532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":66,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3760532"],"URL":"https:\/\/doi.org\/10.1145\/3760532","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,11,21]]},"assertion":[{"value":"2025-02-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}