{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T07:19:43Z","timestamp":1765610383542,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:00:00Z","timestamp":1688515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Horizon Europe","award":["GA no. 101070381 (project: PILLAR-Robots)"],"award-info":[{"award-number":["GA no. 101070381 (project: PILLAR-Robots)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,5]]},"DOI":"10.1145\/3594806.3594840","type":"proceedings-article","created":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T17:38:12Z","timestamp":1691689092000},"page":"197-205","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Action Recognition in Vehicle Environments With Human Pose Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8115-9213","authenticated-orcid":false,"given":"Michaela","family":"Konstantinou","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, National Technical University of Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6734-3575","authenticated-orcid":false,"given":"George","family":"Retsinas","sequence":"additional","affiliation":[{"name":"Institute of Robotics, Athena Research Center, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0534-2707","authenticated-orcid":false,"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, National Technical University of Athens, Greece and Institute of Robotics, Athena Research Center, Greece"}]}],"member":"320","published-online":{"date-parts":[[2023,8,10]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1007\/s11760-019-01589-z"},{"doi-asserted-by":"publisher","unstructured":"Valentin Bazarevsky Ivan Grishchenko Karthik Raveendran Tyler Zhu Fan Zhang and Matthias Grundmann. 2020. BlazePose: On-device Real-time Body Pose tracking. https:\/\/doi.org\/10.48550\/ARXIV.2006.10204","key":"e_1_3_2_1_2_1","DOI":"10.48550\/ARXIV.2006.10204"},{"doi-asserted-by":"publisher","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo Vadis Action Recognition? A New Model and the Kinetics Dataset. https:\/\/doi.org\/10.48550\/ARXIV.1705.07750","key":"e_1_3_2_1_3_1","DOI":"10.48550\/ARXIV.1705.07750"},{"key":"e_1_3_2_1_4_1","first-page":"9703","article-title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","volume":"40","author":"Das Srijan","year":"2021","unstructured":"Srijan Das, Rui Dai, Di Yang, and Fran\u00e7ois Br\u00e9mond. 2021. VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (2021), 9703\u20139717.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","unstructured":"Haodong Duan Yue Zhao Kai Chen Dahua Lin and Bo Dai. 2021. Revisiting Skeleton-based Action Recognition. https:\/\/doi.org\/10.48550\/ARXIV.2104.13586","key":"e_1_3_2_1_5_1","DOI":"10.48550\/ARXIV.2104.13586"},{"key":"e_1_3_2_1_6_1","volume-title":"Revisiting Skeleton-based Action Recognition. CoRR abs\/2104.13586","author":"Duan Haodong","year":"2021","unstructured":"Haodong Duan, Yue Zhao, Kai Chen, Dian Shao, Dahua Lin, and Bo Dai. 2021. Revisiting Skeleton-based Action Recognition. CoRR abs\/2104.13586 (2021), 2959\u20132968."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.3390\/technologies9040086"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/LRA.2019.2930434"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.48550\/ARXIV.1502.03167"},{"key":"e_1_3_2_1_10_1","volume-title":"MDAD: A Multimodal and Multiview in-Vehicle Driver Action Dataset. In Computer Analysis of Images and Patterns","author":"Jegham Imen","year":"2019","unstructured":"Imen Jegham, Anouar Ben\u00a0Khalifa, Ihsen Alouani, and Mohamed\u00a0Ali Mahjoub. 2019. MDAD: A Multimodal and Multiview in-Vehicle Driver Action Dataset. In Computer Analysis of Images and Patterns, Mario Vento and Gennaro Percannella (Eds.). Springer International Publishing, Cham, 518\u2013529."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1109\/JSEN.2020.3019258"},{"doi-asserted-by":"publisher","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev Mustafa Suleyman and Andrew Zisserman. 2017. The Kinetics Human Action Video Dataset. https:\/\/doi.org\/10.48550\/ARXIV.1705.06950","key":"e_1_3_2_1_12_1","DOI":"10.48550\/ARXIV.1705.06950"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.48550\/ARXIV.1811.08383"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1109\/ACCESS.2021.3109815"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/ICCV.2019.00289"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1016\/j.patrec.2017.12.023"},{"key":"e_1_3_2_1_17_1","volume-title":"Global status report on road safety","author":"World\u00a0Health Organization","year":"2018","unstructured":"World\u00a0Health Organization. 2018. Global status report on road safety 2018. World Health Organization, Geneva. https:\/\/www.who.int\/publications\/i\/item\/9789241565684"},{"key":"e_1_3_2_1_18_1","volume-title":"DMD: A Large-Scale Multi-modal Driver Monitoring Dataset for Attention and Alertness Analysis. In Computer Vision \u2013 ECCV 2020 Workshops","author":"Ortega Juan\u00a0Diego","year":"2020","unstructured":"Juan\u00a0Diego Ortega, Neslihan Kose, Paola Ca\u00f1as, Min-An Chao, Alexander Unnervik, Marcos Nieto, Oihana Otaegui, and Luis Salgado. 2020. DMD: A Large-Scale Multi-modal Driver Monitoring Dataset for Attention and Alertness Analysis. In Computer Vision \u2013 ECCV 2020 Workshops, Adrien Bartoli and Andrea Fusiello (Eds.). Springer International Publishing, Cham, 387\u2013405."},{"doi-asserted-by":"publisher","unstructured":"Kunyu Peng Alina Roitberg Kailun Yang Jiaming Zhang and Rainer Stiefelhagen. 2022. TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration. https:\/\/doi.org\/10.48550\/ARXIV.2203.00927","key":"e_1_3_2_1_19_1","DOI":"10.48550\/ARXIV.2203.00927"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/TITS.2021.3063521"},{"doi-asserted-by":"publisher","unstructured":"Zhaofan Qiu Ting Yao and Tao Mei. 2017. Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks. https:\/\/doi.org\/10.48550\/ARXIV.1711.10305","key":"e_1_3_2_1_21_1","DOI":"10.48550\/ARXIV.1711.10305"},{"doi-asserted-by":"publisher","unstructured":"George Retsinas Panagiotis\u00a0Paraskevas Filntisis Nikos Kardaris and Petros Maragos. 2022. Attribute-based Gesture Recognition: Generalization to Unseen Classes. In 2022 IEEE 14th Image Video and Multidimensional Signal Processing Workshop (IVMSP). 1\u20135. https:\/\/doi.org\/10.1109\/IVMSP54334.2022.9816275","key":"e_1_3_2_1_22_1","DOI":"10.1109\/IVMSP54334.2022.9816275"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_24_1","volume-title":"Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos. CoRR abs\/2106.13967","author":"Vasileiou I.","year":"2021","unstructured":"Vasiliki\u00a0I. Vasileiou, Nikolaos Kardaris, and Petros Maragos. 2021. Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos. CoRR abs\/2106.13967 (2021)."},{"doi-asserted-by":"publisher","unstructured":"Hongsong Wang and Liang Wang. 2017. Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks. https:\/\/doi.org\/10.48550\/ARXIV.1704.02581","key":"e_1_3_2_1_25_1","DOI":"10.48550\/ARXIV.1704.02581"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_27_1","volume-title":"Coarse Temporal Attention Network (CTA-Net) for Driver\u2019s Activity Recognition. CoRR abs\/2101.06636","author":"Wharton Zachary","year":"2021","unstructured":"Zachary Wharton, Ardhendu Behera, Yonghuai Liu, and Nik Bessis. 2021. Coarse Temporal Attention Network (CTA-Net) for Driver\u2019s Activity Recognition. CoRR abs\/2101.06636 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/TPAMI.2022.3177813"}],"event":{"acronym":"PETRA '23","name":"PETRA '23: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments","location":"Corfu Greece"},"container-title":["Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3594806.3594840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3594806.3594840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:01Z","timestamp":1750182541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3594806.3594840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,5]]},"references-count":28,"alternative-id":["10.1145\/3594806.3594840","10.1145\/3594806"],"URL":"https:\/\/doi.org\/10.1145\/3594806.3594840","relation":{},"subject":[],"published":{"date-parts":[[2023,7,5]]},"assertion":[{"value":"2023-08-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}