{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:11:02Z","timestamp":1780056662356,"version":"3.54.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007195","name":"Universit\u00e0 degli Studi di Napoli Federico II","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007195","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the current landscape of sports data analysis, particularly in football, the automatic extraction of information from match videos is a key challenge. Traditional video annotation techniques rely on the generation of natural language descriptions from videos or detection analysis of static frames. The first approach has limitations in the level of detail of the information extracted, while the second does not analyze the information at a high semantic level. This work presents an efficient framework for the automatic construction of Temporal Knowledge Graphs from unlabeled football match videos, using computer vision techniques and multimodal large-language models. The constructed graph refers to the entire video of the match and contains information on the positional values of the players on the field, jersey number identification, team recognition, interactions, and ball possession. The framework implements a solution for handling failures without keyframe loss, as well as support for parallel processing. In addition, we propose two metrics to assess the quality of the resulting graph in terms of overall consistency and missing information.<\/jats:p>","DOI":"10.1007\/s00521-026-12037-8","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:27:59Z","timestamp":1776832079000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal knowledge graph construction from football match videos"],"prefix":"10.1007","volume":"38","author":[{"given":"Antonio Maria","family":"Rinaldi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8732-1733","authenticated-orcid":false,"given":"Cristiano","family":"Russo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian","family":"Tommasino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Vitale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"issue":"5","key":"12037_CR1","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/TCSVT.2017.2655624","volume":"28","author":"H-C Shih","year":"2017","unstructured":"Shih H-C (2017) A survey of content-aware video analysis for sports. IEEE Trans Circuits Syst Video Technol 28(5):1212\u20131231","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"6","key":"12037_CR2","doi-asserted-by":"publisher","first-page":"4409","DOI":"10.1007\/s00521-022-07131-6","volume":"35","author":"Z Li","year":"2023","unstructured":"Li Z, Ye X, Liang H (2023) Sports video analysis system based on dynamic image analysis. Neural Comput Appl 35(6):4409\u20134420","journal-title":"Neural Comput Appl"},{"key":"12037_CR3","doi-asserted-by":"crossref","unstructured":"Qi J, Yu J, Tu T, Gao K, Xu Y, Guan X, Wang X, Xu B, Hou L, Li J et al (2023) Goal: a challenging knowledge-grounded video captioning benchmark for real-time soccer commentary generation. In: Proc 32nd ACM Int Conf Inf Knowl Manag, pp 5391\u20135395","DOI":"10.1145\/3583780.3615120"},{"key":"12037_CR4","doi-asserted-by":"crossref","unstructured":"Mkhallati H, Cioppa A, Giancola S, Ghanem B, Van Droogenbroeck M (2023) Soccernet-caption: dense video captioning for soccer broadcasts commentaries. In: Proc IEEE\/CVF Conf Comput Vision and Pattern Recog, pp 5074\u20135085","DOI":"10.1109\/CVPRW59228.2023.00536"},{"key":"12037_CR5","doi-asserted-by":"crossref","unstructured":"Cheng F, Bertasius G (2022) Tallformer: temporal action localization with a long-memory transformer. In: European Conference on Computer Vision, pp 503\u2013521. Springer","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"12037_CR6","doi-asserted-by":"crossref","unstructured":"Huang L, Wang L, Li H (2022) Weakly supervised temporal action localization via representative snippet knowledge propagation. In: Proc IEEE\/CVF Conf Comput Vision and Pattern Recog, pp 3272\u20133281","DOI":"10.1109\/CVPR52688.2022.00327"},{"key":"12037_CR7","doi-asserted-by":"publisher","first-page":"8253","DOI":"10.1109\/TMM.2023.3234362","volume":"25","author":"Y Zhao","year":"2023","unstructured":"Zhao Y, Zhang H, Gao Z, Gao W, Wang M, Chen S (2023) A novel action saliency and context-aware network for weakly-supervised temporal action localization. IEEE Trans Multimedia 25:8253\u20138266","journal-title":"IEEE Trans Multimedia"},{"key":"12037_CR8","doi-asserted-by":"crossref","unstructured":"Shao J, Wang X, Quan R, Zheng J, Yang J, Yang Y (2023) Action sensitivity learning for temporal action localization. In: Proc IEEE\/CVF Int Conf Comput Vision, pp 13457\u201313469","DOI":"10.1109\/ICCV51070.2023.01238"},{"key":"12037_CR9","doi-asserted-by":"publisher","first-page":"6937","DOI":"10.1109\/TIP.2022.3217368","volume":"31","author":"Y Liu","year":"2022","unstructured":"Liu Y, Wang L, Wang Y, Ma X, Qiao Y (2022) Fineaction: a fine-grained video dataset for temporal action localization. IEEE Trans Image Process 31:6937\u20136950. https:\/\/doi.org\/10.1109\/TIP.2022.3217368","journal-title":"IEEE Trans Image Process"},{"key":"12037_CR10","unstructured":"Jo Y, Lee S, Lee AS, Lee H, Oh H, Seo M (2023) Zero-shot dense video captioning by jointly optimizing text and moment. arXiv preprint arXiv:2307.02682"},{"issue":"7","key":"12037_CR11","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1049\/cvi2.12195","volume":"17","author":"T Xu","year":"2023","unstructured":"Xu T, Cui Y, He X, Liu C (2023) A latent topic-aware network for dense video captioning. IET Comput Vision 17(7):795\u2013803","journal-title":"IET Comput Vision"},{"key":"12037_CR12","unstructured":"Xi Z, Shi G, Wu L, Li X, Yan J, Wang L, Liu Z (2024) Knowledge graph supported benchmark and video captioning for basketball. arXiv preprint arXiv:2401.13888"},{"key":"12037_CR13","unstructured":"Xu L, Zhao Y, Zhou D, Lin Z, Ng SK, Feng J (2024) Pllava: parameter-free llava extension from images to videos for video dense captioning. arXiv preprint arXiv:2404.16994"},{"key":"12037_CR14","doi-asserted-by":"crossref","unstructured":"Wang Z, Yu S, Stengel-Eskin E, Yoon J, Cheng F, Bertasius G, Bansal M (2024) Videotree: adaptive tree-based video representation for llm reasoning on long videos. arXiv preprint arXiv:2405.19209","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"12037_CR15","doi-asserted-by":"crossref","unstructured":"Solberg HM, Sarkhoosh MH, Gautam S, Sabet SS, Halvorsen P, Midoglu C (2024) Playertv: advanced player tracking and identification for automatic soccer highlight clips. arXiv preprint arXiv:2407.16076","DOI":"10.1109\/ISM63611.2024.00019"},{"issue":"1","key":"12037_CR16","volume":"32","author":"BT Naik","year":"2023","unstructured":"Naik BT, Hashmi MF (2023) Yolov3-sort: detection and tracking player\/ball in soccer sport. J Electron Imaging 32(1):011003\u2013011003","journal-title":"J Electron Imaging"},{"key":"12037_CR17","doi-asserted-by":"crossref","unstructured":"Majeed F, Gilal NU, Al-Thelaya K, Yang Y, Agus M, Schneider J (2024) Mv-soccer: motion-vector augmented instance segmentation for soccer player tracking. In: Proc IEEE\/CVF Conf Comput Vision and Pattern Recog, pp 3245\u20133255","DOI":"10.1109\/CVPRW63382.2024.00330"},{"key":"12037_CR18","doi-asserted-by":"crossref","unstructured":"Van Zandycke G, Somers V, Istasse M, Don CD, Zambrano D (2022) Deepsportradar-v1: computer vision dataset for sports understanding with high quality annotations. In: Proc 5th Int ACM Workshop on Multimedia Content Analysis in Sports, pp 1\u20138","DOI":"10.1145\/3552437.3555699"},{"key":"12037_CR19","doi-asserted-by":"crossref","unstructured":"Cioppa A, Giancola S, Deli\u00e8ge A, Kang L, Zhou X, Cheng Z, Ghanem B, Van Droogenbroeck M (2022) Soccernet-tracking: multiple object tracking dataset and benchmark in soccer videos. In: Proc IEEE\/CVF Conf Comput Vision and Pattern Recog (CVPR) Works, pp 3491\u20133502","DOI":"10.1109\/CVPRW56347.2022.00393"},{"key":"12037_CR20","doi-asserted-by":"crossref","unstructured":"Cui Y, Zeng C, Zhao X, Yang Y, Wu G, Wang L (2023) Sportsmot: a large multi-object tracking dataset in multiple sports scenes. In: Proc IEEE\/CVF Int Conf Comput Vision (ICCV), pp 9921\u20139931","DOI":"10.1109\/ICCV51070.2023.00910"},{"issue":"9","key":"12037_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/app13095361","volume":"13","author":"X Fu","year":"2023","unstructured":"Fu X, Huang W, Sun Y, Zhu X, Evans J, Song X, Geng T, He S (2023) A novel dataset for multi-view multi-player tracking in soccer scenarios. Appl Sci 13(9):5361","journal-title":"Appl Sci"},{"key":"12037_CR22","doi-asserted-by":"crossref","unstructured":"Andrews P, Borch N, Fjeld M (2024) Footyvision: multi-object tracking, localisation, and augmentation of players and ball in football video. In: Proc 2024 9th Int Conf Multimedia and Image Proc, pp 15\u201325","DOI":"10.1145\/3665026.3665029"},{"issue":"18","key":"12037_CR23","doi-asserted-by":"publisher","DOI":"10.3390\/s23187938","volume":"23","author":"A Maglo","year":"2023","unstructured":"Maglo A, Orcesi A, Denize J, Pham QC (2023) Individual locating of soccer players from a single moving view. Sensors 23(18):7938","journal-title":"Sensors"},{"key":"12037_CR24","doi-asserted-by":"crossref","unstructured":"Theiner J, Ewerth R (2023) Tvcalib: camera calibration for sports field registration in soccer. In: Proc IEEE\/CVF Winter Conf Appl Comput Vision, pp 1166\u20131175","DOI":"10.1109\/WACV56688.2023.00122"},{"key":"12037_CR25","doi-asserted-by":"crossref","unstructured":"Theiner J, Ewerth R (2023) Tvcalib: camera calibration for sports field registration in soccer. In: Proc IEEE\/CVF Winter Conf Appl Comput Vision (WACV), pp 1166\u20131175","DOI":"10.1109\/WACV56688.2023.00122"},{"key":"12037_CR26","doi-asserted-by":"crossref","unstructured":"Balaji B, Bright J, Prakash H, Chen Y, Clausi DA, Zelek J (2023) Jersey number recognition using keyframe identification from low-resolution broadcast videos. In: Proc 6th Int Works on Multimedia Content Analysis in Sports, pp 123\u2013130","DOI":"10.1145\/3606038.3616162"},{"key":"12037_CR27","doi-asserted-by":"crossref","unstructured":"Liu J, Li Y, Ning T, Song J, Duan X (2023) Football player identification based on yolov5 backbone and spd-conv. In: Eighth Int Conf Elect Technol Inf Sci (ICETIS 2023), 12715:695\u2013701. SPIE","DOI":"10.1117\/12.2682544"},{"key":"12037_CR28","doi-asserted-by":"crossref","unstructured":"Shubhangi D, Gadgay B, Begum M, Waheed M (2023) Detection of snowball and jersey colour and jersey number using cnn. In: 2023 Int Conf Intell Innov Technol Comput, Electrical and Electronics (IITCEE), pp 745\u2013749. IEEE","DOI":"10.1109\/IITCEE57236.2023.10091073"},{"key":"12037_CR29","doi-asserted-by":"crossref","unstructured":"Akan S, Varl\u0131 S (2023) Reidentifying soccer players in broadcast videos using body feature alignment based on pose. In: Proc 2023 4th Int Conf Comput, Networks and Internet of Things, pp 440\u2013444","DOI":"10.1145\/3603781.3603860"},{"key":"12037_CR30","doi-asserted-by":"crossref","unstructured":"Promvijittrakarn P, Charoenpong T (2023) A method of soccer-team identification by histogram feature vector and support vector machine. In: Int Workshop on Adv Imaging Technol (IWAIT) 12592:210\u2013214. SPIE","DOI":"10.1117\/12.2665953"},{"key":"12037_CR31","doi-asserted-by":"crossref","unstructured":"Mansourian AM, Somers V, De Vleeschouwer C, Kasaei S (2023) Multi-task learning for joint re-identification, team affiliation, and role classification for sports visual tracking. In: Proc 6th Int Workshop on Multimedia Content Analysis in Sports, pp 103\u2013112","DOI":"10.1145\/3606038.3616172"},{"key":"12037_CR32","doi-asserted-by":"crossref","unstructured":"Somers V, Joos V, Cioppa A, Giancola S, Ghasemzadeh SA, Magera F, Standaert B, Mansourian AM, Zhou X, Kasaei S et al (2024) Soccernet game state reconstruction: end-to-end athlete tracking and identification on a minimap. In: Proc IEEE\/CVF Conf Comput Vision and Pattern Recog, pp 3293\u20133305","DOI":"10.1109\/CVPRW63382.2024.00334"},{"issue":"4","key":"12037_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618295","volume":"56","author":"L Zhong","year":"2023","unstructured":"Zhong L, Wu J, Li Q, Peng H, Wu X (2023) A comprehensive survey on automatic knowledge graph construction. ACM Comput Surv 56(4):1\u201362","journal-title":"ACM Comput Surv"},{"issue":"5","key":"12037_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01297-w","volume":"27","author":"Y Zhu","year":"2024","unstructured":"Zhu Y, Wang X, Chen J, Qiao S, Ou Y, Yao Y, Deng S, Chen H, Zhang N (2024) Llms for knowledge graph construction and reasoning: recent capabilities and future opportunities. World Wide Web 27(5):58","journal-title":"World Wide Web"},{"key":"12037_CR35","doi-asserted-by":"crossref","unstructured":"Zhang B, Soh H (2024) Extract, define, canonicalize: an llm-based framework for knowledge graph construction. arXiv preprint arXiv:2404.03868","DOI":"10.18653\/v1\/2024.emnlp-main.548"},{"key":"12037_CR36","doi-asserted-by":"publisher","unstructured":"Varghese R, Sambath M (2024) Yolov8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 Int Conf Adv Data Eng Intell Comput Syst (ADICS), pp 1\u20136. https:\/\/doi.org\/10.1109\/ADICS58448.2024.10533619","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"12037_CR37","unstructured":"Yao Y, Yu T, Zhang A, Wang C, Cui J, Zhu H, Cai T, Li H, Zhao W, He Z et al (2024) Minicpm-v: a gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800"},{"key":"12037_CR38","doi-asserted-by":"crossref","unstructured":"Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. arXiv:1707.02921","DOI":"10.1109\/CVPRW.2017.151"},{"key":"12037_CR39","doi-asserted-by":"crossref","unstructured":"Zhai X, Mustafa B, Kolesnikov A, Beyer L (2023) Sigmoid loss for language image pre-training. arXiv:2303.15343","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"12037_CR40","unstructured":"McInnes L, Healy J, Melville J (2020) UMAP: uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12037-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-026-12037-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12037-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:51:10Z","timestamp":1780055470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-026-12037-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":40,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["12037"],"URL":"https:\/\/doi.org\/10.1007\/s00521-026-12037-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,22]]},"assertion":[{"value":"20 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"328"}}