{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:35:57Z","timestamp":1783697757775,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1145\/3703323.3703722","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T12:03:28Z","timestamp":1750853008000},"page":"210-219","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Industrial Safety Violation Detection using Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6401-9082","authenticated-orcid":false,"given":"Suryanarayana Reddy","family":"Yarrabothula","sequence":"first","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Bhilai, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0509-8699","authenticated-orcid":false,"given":"Vaibhav","family":"Kurrey","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Bhilai, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7435-8441","authenticated-orcid":false,"given":"Mayank","family":"Nagar","sequence":"additional","affiliation":[{"name":"Chennai Mathematical Institute, Chennai, Tamilnadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8568-2949","authenticated-orcid":false,"given":"Gagan Raj","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Bhilai, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Apostol Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. ArXiv (2016)."},{"key":"e_1_3_3_1_3_2","unstructured":"Hafiz\u00a0Mughees Ahmad and Afshin Rahimi. 2024. SH17: A Dataset for Human Safety and Personal Protective Equipment Detection in Manufacturing Industry."},{"key":"e_1_3_3_1_4_2","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding? ArXiv (2021)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Moshe Blank Lena Gorelick Eli Shechtman Michal Irani and Ronen Basri. 2005. Actions as space-time shapes. Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1 (2005).","DOI":"10.1109\/ICCV.2005.28"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Zhe Cao Tomas Simon Shih-En Wei and Yaser Sheikh. 2016. Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016) 1302\u20131310.","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo Vadis Action Recognition? A New Model and the Kinetics Dataset. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017) 4724\u20134733. https:\/\/api.semanticscholar.org\/CorpusID:206596127","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Shi Chen and Kazuyuki Demachi. 2020. A Vision-Based Approach for Ensuring Proper Use of Personal Protective Equipment (PPE) in Decommissioning of Fukushima Daiichi Nuclear Power Station. Applied Sciences (2020).","DOI":"10.1115\/1.0000425V"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS49158.2020.9209531"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Mejdi Dallel Vincent Havard David Baudry and Xavier Savatier. 2020. InHARD - Industrial Human Action Recognition Dataset in the Context of Industrial Collaborative Robotics. 2020 IEEE International Conference on Human-Machine Systems (ICHMS) (2020).","DOI":"10.1109\/ICHMS49158.2020.9209531"},{"key":"e_1_3_3_1_11_2","volume-title":"North American Chapter of the Association for Computational Linguistics","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In North American Chapter of the Association for Computational Linguistics."},{"key":"e_1_3_3_1_12_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv (2020)."},{"key":"e_1_3_3_1_13_2","unstructured":"Haoqi Fan Yanghao Li Bo Xiong Wan-Yen Lo and Christoph Feichtenhofer. 2020. PySlowFast. https:\/\/github.com\/facebookresearch\/slowfast."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer. 2020. X3D: Expanding Architectures for Efficient Video Recognition. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020).","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Haoqi Fan Jitendra Malik and Kaiming He. 2018. SlowFast Networks for Video Recognition. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2018).","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_3_1_17_2","unstructured":"Chunhui Gu Chen Sun Sudheendra Vijayanarasimhan Caroline Pantofaru David\u00a0A. Ross George Toderici Yeqing Li Susanna Ricco Rahul Sukthankar Cordelia Schmid and Jitendra Malik. 2017. AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Fabian\u00a0Caba Heilbron Victor Escorcia Bernard Ghanem and Juan\u00a0Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Haroon Idrees Amir Zamir Yu-Gang Jiang Alexander\u00a0N. Gorban Ivan Laptev Rahul Sukthankar and Mubarak Shah. 2016. The THUMOS challenge on action recognition for videos \"in the wild\". ArXiv (2016).","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956300"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Francesco Iodice Elena\u00a0De Momi and Arash Ajoudani. 2022. HRI30: An Action Recognition Dataset for Industrial Human-Robot Interaction. 2022 26th International Conference on Pattern Recognition (ICPR) (2022).","DOI":"10.1109\/ICPR56361.2022.9956300"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Velibor Isailovi\u0107 Aleksandar Peuli\u0107 Marko Djapan Marija Savkovi\u0107 and Arso\u00a0M. Vukicevic. 2022. The compliance of head-mounted industrial PPE by using deep learning object detectors. Scientific Reports (2022).","DOI":"10.1038\/s41598-022-20282-9"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Hueihan Jhuang Juergen Gall Silvia Zuffi Cordelia Schmid and Michael\u00a0J. Black. 2013. Towards Understanding Action Recognition. 2013 IEEE International Conference on Computer Vision (2013).","DOI":"10.1109\/ICCV.2013.396"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy George Toderici Sanketh Shetty Thomas Leung Rahul Sukthankar and Li Fei-Fei. 2014. Large-Scale Video Classification with Convolutional Neural Networks. 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014).","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Yan Ke Rahul Sukthankar and Martial Hebert. 2005. Efficient visual event detection using volumetric features. Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1 (2005).","DOI":"10.1109\/ICCV.2005.85"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Kyunghwan Kim Kangeun Kim and Soyoon Jeong. 2023. Application of YOLO v5 and v8 for Recognition of Safety Risk Factors at Construction Sites. Sustainability 15 (10 2023) 15179.","DOI":"10.3390\/su152015179"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Yu Kong and Yun\u00a0Raymond Fu. 2018. Human Action Recognition and Prediction: A Survey. International Journal of Computer Vision 130 (2018) 1366 \u2013 1401. https:\/\/api.semanticscholar.org\/CorpusID:49551723","DOI":"10.1007\/s11263-022-01594-9"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Hilde Kuehne Hueihan Jhuang Est\u00edbaliz Garrote Tomaso\u00a0A. Poggio and Thomas Serre. 2011. HMDB: A large video database for human motion recognition. 2011 International Conference on Computer Vision (2011).","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Ivan Laptev. 2005. On Space-Time Interest Points. International Journal of Computer Vision 64 (2005) 107\u2013123. https:\/\/api.semanticscholar.org\/CorpusID:2619278","DOI":"10.1007\/s11263-005-1838-7"},{"key":"e_1_3_3_1_31_2","volume-title":"Advances in Neural Information Processing Systems","author":"Leng Luziwei","year":"2022","unstructured":"Luziwei Leng, Kaiwei Che, Kaixuan Zhang, Jianguo Zhang, Qinghu Meng, Jie Cheng, Qinghai Guo, and Jianxing Liao. 2022. Differentiable hierarchical and surrogate gradient search for spiking neural networks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_32_2","unstructured":"Ang Li Meghana Thotakuri David\u00a0A. Ross Jo\u00e3o Carreira Alexander Vostrikov and Andrew Zisserman. 2020. The AVA-Kinetics Localized Human Actions Video Dataset. ArXiv (2020)."},{"key":"e_1_3_3_1_33_2","unstructured":"Ang Li Meghana Thotakuri David\u00a0A. Ross Jo\u00e3o Carreira Alexander Vostrikov and Andrew Zisserman. 2020. The AVA-Kinetics Localized Human Actions Video Dataset. arxiv:2005.00214\u00a0[cs.CV]"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"W. Li Zhengyou Zhang and Zicheng Liu. 2010. Action recognition based on a bag of 3D points. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops (2010).","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"e_1_3_3_1_35_2","unstructured":"Yixuan Li Lei Chen Runyu He Zhenzhi Wang Gangshan Wu and Limin Wang. 2021. MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_1_37_2","unstructured":"Jingen Liu Benjamin Kuipers and Silvio Savarese. 2011. Recognizing human actions by attributes. CVPR 2011 (2011) 3337\u20133344. https:\/\/api.semanticscholar.org\/CorpusID:9119671"},{"key":"e_1_3_3_1_38_2","volume-title":"European Conference on Computer Vision","author":"Liu W.","year":"2015","unstructured":"W. Liu, Dragomir Anguelov, D. Erhan, Christian Szegedy, Scott\u00a0E. Reed, Cheng-Yang Fu, and Alexander\u00a0C. Berg. 2015. SSD: Single Shot MultiBox Detector. In European Conference on Computer Vision."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Marcin Marszalek Ivan Laptev and Cordelia Schmid. 2009. Actions in context. 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009).","DOI":"10.1109\/CVPRW.2009.5206557"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Naval\u00a0Kishore Mehta Shyam\u00a0Sunder Prasad Sumeet Saurav Ravi Saini and Sanjay Singh. 2024. IAR-Net: A Human\u2013Object Context Guided Action Recognition Network for Industrial Environment Monitoring. IEEE Transactions on Instrumentation and Measurement 73 (2024) 1\u20138.","DOI":"10.1109\/TIM.2024.3379075"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Louis-Philippe Morency Ariadna Quattoni and Trevor Darrell. 2007. Latent-Dynamic Discriminative Models for Continuous Gesture Recognition. 2007 IEEE Conference on Computer Vision and Pattern Recognition (2007) 1\u20138. https:\/\/api.semanticscholar.org\/CorpusID:7117722","DOI":"10.1109\/CVPR.2007.383299"},{"key":"e_1_3_3_1_44_2","volume-title":"Documentation Mocap Database HDM05","author":"M\u00fcller M.","year":"2007","unstructured":"M. M\u00fcller, T. R\u00f6der, M. Clausen, B. Eberhardt, B. Kr\u00fcger, and A. Weber. 2007. Documentation Mocap Database HDM05. Technical Report CG-2007-2. Universit\u00e4t Bonn."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Emre\u00a0O. Neftci Hesham Mostafa and Friedemann Zenke. 2019. Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine 36 (2019) 51\u201363.","DOI":"10.1109\/MSP.2019.2931595"},{"key":"e_1_3_3_1_46_2","unstructured":"njvisionpower. 2024. Safety-Helmet-Wearing-Dataset. GitHub (2024)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Munkh-Erdene Otgonbold Munkhjargal Gochoo Fady\u00a0S. Alnajjar Luqman Ali Tan-Hsu Tan Jun-Wei Hsieh and Ping-Yang Chen. 2022. SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection. Sensors (Basel Switzerland) 22 (2022).","DOI":"10.3390\/s22062315"},{"key":"e_1_3_3_1_48_2","unstructured":"Paul Over Jon Fiscus Gregory Sanders David Joy Martial Michel George Awad Alan Smeaton Wessel Kraaij and Georges Qu\u00e9not. 2014. TRECVID 2014 \u2013 An Overview of the Goals Tasks Data Evaluation Mechanisms and Metrics."},{"key":"e_1_3_3_1_49_2","volume-title":"International Conference on Intelligent Human-Machine Systems and Cybernetics","author":"Junfeng\u00a0Li Qinhan\u00a0Xiao Qiankun\u00a0Xiao,","year":"2013","unstructured":"Qinhan\u00a0Xiao Qiankun\u00a0Xiao, Junfeng\u00a0Li. 2013. Human Motion Capture Data Retrieval Based on Quaternion and EMD. In International Conference on Intelligent Human-Machine Systems and Cybernetics."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Shaoqing Ren Kaiming He Ross\u00a0B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39 (2015) 1137\u20131149.","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Mikel\u00a0D. Rodriguez Javed Ahmed and Mubarak Shah. 2008. Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition. 2008 IEEE Conference on Computer Vision and Pattern Recognition (2008).","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Paul Scovanner Saad Ali and Mubarak Shah. 2007. A 3-dimensional sift descriptor and its application to action recognition. Proceedings of the 15th ACM international conference on Multimedia (2007). https:\/\/api.semanticscholar.org\/CorpusID:1087061","DOI":"10.1145\/1291233.1291311"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Javen\u00a0Qinfeng Shi Li Cheng Li Wang and Alex Smola. 2011. Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models. International Journal of Computer Vision 93 (2011) 22\u201332. https:\/\/api.semanticscholar.org\/CorpusID:9054863","DOI":"10.1007\/s11263-010-0384-0"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_3_1_56_2","unstructured":"Khurram Soomro Amir Zamir and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. ArXiv (2012)."},{"key":"e_1_3_3_1_57_2","unstructured":"Khurram Soomro Amir\u00a0Roshan Zamir and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. arxiv:1212.0402"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Moritz Tenorth Jan Bandouch and Michael Beetz. 2009. The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition. 2009 IEEE 12th International Conference on Computer Vision Workshops ICCV Workshops (2009).","DOI":"10.1109\/ICCVW.2009.5457583"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Du Tran Lubomir\u00a0D. Bourdev Rob Fergus Lorenzo Torresani and Manohar Paluri. 2014. Learning Spatiotemporal Features with 3D Convolutional Networks. 2015 IEEE International Conference on Computer Vision (ICCV) (2014) 4489\u20134497. https:\/\/api.semanticscholar.org\/CorpusID:1122604","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"crossref","unstructured":"Du Tran Heng Wang Lorenzo Torresani Jamie Ray Yann LeCun and Manohar Paluri. 2017. A Closer Look at Spatiotemporal Convolutions for Action Recognition. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017).","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_3_1_61_2","volume-title":"Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam\u00a0M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Neural Information Processing Systems."},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"Arso\u00a0M. Vukicevic Marko Djapan Velibor Isailovi\u0107 Danko\u00a0Z. Milasinovic Marija Savkovi\u0107 and Pavle Milo\u0107evi\u0107. 2022. Generic compliance of industrial PPE by using deep learning techniques. Safety Science (2022).","DOI":"10.1016\/j.ssci.2021.105646"},{"key":"e_1_3_3_1_63_2","unstructured":"Chien-Yao Wang I-Hau Yeh and Hong-Yuan\u00a0Mark Liao. 2024. Yolov9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616 (2024)."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"crossref","unstructured":"Heng Wang Dan Onea\u0163\u0103 Jakob\u00a0J. Verbeek and Cordelia Schmid. 2015. A Robust and Efficient Video Representation for Action Recognition. International Journal of Computer Vision 119 (2015) 219 \u2013 238. https:\/\/api.semanticscholar.org\/CorpusID:11491197","DOI":"10.1007\/s11263-015-0846-5"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","unstructured":"Zijian Wang Yimin Wu Lichao Yang Arjun Thirunavukarasu Colin Evison and Yifan Zhao. 2021. Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches. Sensors (Basel Switzerland) (2021).","DOI":"10.3390\/s21103478"},{"key":"e_1_3_3_1_66_2","unstructured":"Yuyang Wanyan Xiaoshan Yang Weiming Dong and Changsheng Xu. 2024. A Comprehensive Review of Few-shot Action Recognition."},{"key":"e_1_3_3_1_67_2","unstructured":"Jixiu Wu Nian Cai Wenjie Chen Huiheng Wang and Guotian Wang. 2019. Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset. Automation in Construction (2019)."},{"key":"e_1_3_3_1_68_2","unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_3_3_1_69_2","unstructured":"Fan Yang. 2022. CustomAva. https:\/\/github.com\/Whiffe\/ Custom-ava-dataset_Custom-Spatio-Temporally-Action-Video-Dataset."},{"key":"e_1_3_3_1_70_2","unstructured":"Serena Yeung Olga Russakovsky Ning Jin Mykhaylo Andriluka Greg Mori and Li Fei-Fei. 2015. Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos. International Journal of Computer Vision (2015)."},{"key":"e_1_3_3_1_71_2","unstructured":"Fusheng Yu Xiaoping Wang Jiang Li Shaojin Wu Jun jie Zhang and Zhigang Zeng. 2023. Towards Complex Real-World Safety Factory Inspection: A High-Quality Dataset for Safety Clothing and Helmet Detection. ArXiv (2023)."},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"crossref","unstructured":"Junsong Yuan Zicheng Liu and Ying Wu. 2009. Discriminative subvolume search for efficient action detection. 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009).","DOI":"10.1109\/CVPRW.2009.5206671"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"crossref","unstructured":"Faishal Zhafran Endah\u00a0Suryawati Ningrum Mohamad\u00a0Nasyir Tamara and Eny Kusumawati. 2019. Computer Vision System Based for Personal Protective Equipment Detection by Using Convolutional Neural Network. 2019 International Electronics Symposium (IES) (2019).","DOI":"10.1109\/ELECSYM.2019.8901664"},{"key":"e_1_3_3_1_74_2","unstructured":"Sijie Zhu Taojiannan Yang Mat\u2019ias Mendieta and Chen Chen. 2020. A3D: Adaptive 3D Networks for Video Action Recognition. ArXiv (2020)."}],"event":{"name":"CODS-COMAD 2024: 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","location":"Jodhpur India","acronym":"CODS-COMAD Dec '24"},"container-title":["Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703323.3703722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T13:01:22Z","timestamp":1750856482000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703323.3703722"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":73,"alternative-id":["10.1145\/3703323.3703722","10.1145\/3703323"],"URL":"https:\/\/doi.org\/10.1145\/3703323.3703722","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"2025-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}