{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:07:18Z","timestamp":1769033238503,"version":"3.49.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005416","name":"Research Council of Norway","doi-asserted-by":"publisher","award":["RCN 270053"],"award-info":[{"award-number":["RCN 270053"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339347","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding"],"prefix":"10.1109","author":[{"given":"Sushant","family":"Gautam","sequence":"first","affiliation":[{"name":"Simula Metropolitan Center for Digital Engineering,Norway"}]},{"given":"Cise","family":"Midoglu","sequence":"additional","affiliation":[{"name":"Simula Metropolitan Center for Digital Engineering,Norway"}]},{"given":"Vajira L.","family":"Thambawita","sequence":"additional","affiliation":[{"name":"Simula Metropolitan Center for Digital Engineering,Norway"}]},{"given":"Michael A.","family":"Riegler","sequence":"additional","affiliation":[{"name":"Simula Research Laboratory,Norway"}]},{"given":"Pal","family":"Halvorsen","sequence":"additional","affiliation":[{"name":"Simula Metropolitan Center for Digital Engineering,Norway"}]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Central Florida,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3232034"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652197"},{"key":"ref6","article-title":"Towards Universal Soccer Video Understanding","author":"Rao","year":"2024","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00536"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISM63611.2024.00016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3552463.3557019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00511"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03386-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00332"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/17461391.2020.1747552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12283-024-00466-4"},{"key":"ref16","article-title":"SPORTU: A Comprehensive Sports Under-standing Benchmark for Multimodal Large Language Models","author":"Xia","year":"2024","journal-title":"ar Xiv"},{"key":"ref17","article-title":"SoccerDB: A Large-Scale Database for Comprehensive Video Understanding","author":"Jiang","year":"2019","journal-title":"a rXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00332"},{"key":"ref19","article-title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","author":"Xia","year":"2024","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3566695"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.052618"},{"key":"ref22","article-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution","volume-title":"arXiv","author":"Wang","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11688"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.009"},{"key":"ref25","article-title":"Multimodal deep learning approach for event detection in sports using Amazon SageMaker","volume-title":"AWS Machine Learning Blog","author":"Sarraf","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/e24070939"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09186-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-73462-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app132312965"},{"key":"ref30","article-title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","author":"Li","year":"2024","journal-title":"Ar Xiv e-prints"},{"key":"ref31","article-title":"ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition","author":"Salehi","year":"2024","journal-title":"ArXiv e-prints"},{"key":"ref32","article-title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","author":"Bao","year":"2025","journal-title":"ArXiv e-prints"},{"key":"ref33","article-title":"TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types","author":"Chen","year":"2025","journal-title":"arXiv"},{"key":"ref34","article-title":"Foundation Models for Video Understanding: A Survey","author":"Madan","year":"2024","journal-title":"arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456332"},{"key":"ref36","article-title":"VideoGPT +: Integrating Image and Video Encoders for Enhanced Video Understanding","author":"Maaz","year":"2024","journal-title":"arXiv"},{"key":"ref37","article-title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref39","first-page":"14","article-title":"Ai Commentator: A Multimodal Conversational Agent for Embedded Visualization in Football Viewing","volume-title":"ACM Con-ferences","author":"Andrews","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2020.1738569"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/app10093280"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.10.013"},{"key":"ref43","article-title":"SCBench: A Sports Commentary Benchmark for Video LLMs","author":"Ge","year":"2024","journal-title":"arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45965-x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/1754337120932023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3389\/fspor.2023.1284086"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0236643"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSST60641.2023.10414235"},{"key":"ref49","volume-title":"Ibm study: Fan engagement and consumption of sports shifting, reveals new opportunities for technology integrations including ai.","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14030461"},{"key":"ref51","first-page":"252","article-title":"Integrating AI with Edge Computing and Cloud Services for Real-Time Data Processing and Decision Making","volume":"2","author":"Hossain","year":"2023","journal-title":"ijmdsa"},{"key":"ref52","article-title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","author":"Cao","year":"2023","journal-title":"a rXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3397775"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/app142411612"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339347.pdf?arnumber=11339347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:38Z","timestamp":1768979498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339347","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}