{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:14:34Z","timestamp":1762841674781,"version":"build-2065373602"},"reference-count":9,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1109\/ipta66025.2025.11222029","type":"proceedings-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:45:24Z","timestamp":1762800324000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Modular System for Human Action Detection Combining YOLO and Transformer-Based Video Understanding"],"prefix":"10.1109","author":[{"given":"Awatef","family":"Edhib","sequence":"first","affiliation":[{"name":"Claude Bernard Lyon 1 University,Lyon,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Achraf","family":"Chabbouh","sequence":"additional","affiliation":[{"name":"Anavid Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Chaari","sequence":"additional","affiliation":[{"name":"Anavid Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rostom","family":"Kachouri","sequence":"additional","affiliation":[{"name":"Gustave Eiffel University,LIGM Laboratory, A3SI Team, ESIEE Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3169","article-title":"Action recognition by dense trajectories","volume-title":"*Proc. IEEEE Conf. Comput. Vis. Pattern Recognit.*","author":"Wang","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"*arXiv preprint*"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref7","article-title":"VideoMAE: Masked Autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"*Advances in Neural Information Processing Systems (NeurIPS)*"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref9","article-title":"YOLOv8: The next generation of YOLO models","author":"Jocher","year":"2023","journal-title":"Ultralytics"}],"event":{"name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA)","start":{"date-parts":[[2025,10,13]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,10,16]]}},"container-title":["2025 Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11221202\/11221998\/11222029.pdf?arnumber=11222029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:11:38Z","timestamp":1762841498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/ipta66025.2025.11222029","relation":{},"subject":[],"published":{"date-parts":[[2025,10,13]]}}}