{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T19:10:05Z","timestamp":1755976205335,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3688867.3690170","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:28:27Z","timestamp":1729708107000},"page":"26-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["High Quality Fire Smoke Dataset: A Benchmark for Fire and Smoke Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2696-4928","authenticated-orcid":false,"given":"Jialong","family":"Qian","sequence":"first","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4472-7298","authenticated-orcid":false,"given":"Chaoqun","family":"Hong","sequence":"additional","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1722-6292","authenticated-orcid":false,"given":"Kejie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hangzhou Hyperchain Technology Co., Ltd, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1778-0685","authenticated-orcid":false,"given":"Jianglong","family":"Huang","sequence":"additional","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"AhmadA.A.Alkhatib.2014. AReviewonForestFireDetectionTechniques. InternationalJournalofDistributedSensorNetworks10 3(2014) 597368. https: \/\/doi.org\/10.1155\/2014\/597368arXiv:https:\/\/doi.org\/10.1155\/2014\/597368","DOI":"10.1155\/2014\/597368arXiv:https:\/\/10.1155\/2014\/597368"},{"key":"e_1_3_2_1_2_1","unstructured":"AlexeyBochkovskiy Chien-YaoWang andHong-YuanMarkLiao.2020.YOLOv4: OptimalSpeedandAccuracyofObjectDetection.CoRRabs\/2004.10934(2020). arXiv:2004.10934https:\/\/arxiv.org\/abs\/2004.10934"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"ZhaoweiCaiandNunoVasconcelos.2021.CascadeR-CNN:HighQualityObject DetectionandInstanceSegmentation. IEEETransactionsonPatternAnalysisand MachineIntelligence43 5(2021) 1483--1498. https:\/\/doi.org\/10.1109\/TPAMI.2019. 2956516","DOI":"10.1109\/TPAMI.2019"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"NicolasCarion FranciscoMassa GabrielSynnaeve NicolasUsunier Alexan derKirillov andSergeyZagoruyko.2020. End-to-EndObjectDetectionwith Transformers.InComputerVision--ECCV2020 AndreaVedaldi HorstBischof ThomasBrox andJan-MichaelFrahm(Eds.).SpringerInternationalPublishing Cham 213--229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2006.12.003"},{"key":"e_1_3_2_1_6_1","volume-title":"Retrieved","author":"Cetin A. Enis","year":"2014","unstructured":"A. Enis Cetin. 2014. visFire. Retrieved February 28, 2008 from http:\/\/signal.ee. bilkent.edu.tr\/VisiFire\/"},{"key":"e_1_3_2_1_7_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2004.1421401"},{"key":"e_1_3_2_1_9_1","volume-title":"Jose F Rodrigues, and Agma JM Traina.","author":"Chino Daniel YT","year":"2015","unstructured":"Daniel YT Chino, Letricia PS Avalhais, Jose F Rodrigues, and Agma JM Traina. 2015. Bowfire: detection of fire in still images by integrating pixel color and texture analysis. In 2015 28th SIBGRAPIconference ongraphics, patterns andimages. IEEE, 95--102."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07467-z"},{"volume-title":"2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255","key":"e_1_3_2_1_11_1","unstructured":"JiaDeng,WeiDong,RichardSocher,Li-JiaLi,KaiLi,andLiFei-Fei.2009. Imagenet: Alarge-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255."},{"key":"e_1_3_2_1_12_1","volume-title":"Retrieved","author":"Andy Dunnings","year":"2018","unstructured":"Dunnings and Andy. 2018. Fire Image Data Set for Dunnings 2018 Study- PNG Still Image Set. Retrieved May 27, 2019 from http:\/\/collections.durham.ac.uk\/ f iles\/r2d217qp536"},{"key":"e_1_3_2_1_13_1","volume-title":"Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2010","unstructured":"Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. Inter national journal of computer vision 88 (2010), 303--338."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2392531"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2894665"},{"key":"e_1_3_2_1_16_1","volume-title":"YOLOX: Exceeding YOLO Series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. YOLOX: Exceeding YOLO Series in 2021. arXiv preprint arXiv:2107.08430 (2021)."},{"volume-title":"Retrieved","year":"2020","key":"e_1_3_2_1_17_1","unstructured":"gengyanlei. 2020. fire-smoke-detect-yolov4. Retrieved July 14, 2020 from https: \/\/github.com\/gengyanlei\/fire-smoke-detect-yolov4"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"e_1_3_2_1_19_1","volume-title":"Region based convolutional networks for accurate object detection and segmentation","author":"Girshick Ross","year":"2015","unstructured":"Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2015. Region based convolutional networks for accurate object detection and segmentation. IEEE transactions on pattern analysis and machine intelligence 38, 1 (2015), 142 158."},{"key":"e_1_3_2_1_20_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Nikos Grammalidis Kosmas Dimitropoulos and Enis Cetin. 2017. FIRESENSE database of videos for flame and smoke detection. https:\/\/doi.org\/10.5281\/zenodo. 836749","DOI":"10.5281\/zenodo"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_1_23_1","volume-title":"Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV).","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. 2017. Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)."},{"volume-title":"Deep Residual LearningforImageRecognition","author":"He Kaiming","key":"e_1_3_2_1_24_1","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual LearningforImageRecognition.InProceedingsoftheIEEEConferenceonComputer Vision and Pattern Recognition (CVPR)."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Huang Gao","key":"e_1_3_2_1_25_1","unstructured":"Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBR-LARS-R.2017.8215312"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Glenn Jocher. 2020. YOLOv5 by Ultralytics. https:\/\/doi.org\/10.5281\/zenodo. 3908559","DOI":"10.5281\/zenodo"},{"key":"e_1_3_2_1_28_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. Ultralytics YOLO. https: \/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Kang Kim and Hee Seok Lee. 2020. Probabilistic Anchor Assignment with IoU Prediction for Object Detection. In ECCV.","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.OE.51.1.017208"},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Wein berger (Eds.)","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Clas sification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Wein berger (Eds.), Vol. 25. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/ paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov et al. 2020. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. International journal of computer vision 128 7 (2020) 1956--1981.","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_33_1","volume-title":"Deep learning. nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_35_1","unstructured":"Chuyi Li Lulu Li Hongliang Jiang Kaiheng Weng Yifei Geng Liang Li Zaidan Ke Qingyuan Li Meng Cheng Weiqiang Nie et al. 2022. YOLOv6: A single stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03243-7"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740 755."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1333722"},{"key":"e_1_3_2_1_40_1","volume-title":"Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329","author":"Liu Shilong","year":"2022","unstructured":"Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"Berg","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. In Computer Vision-- ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 21--37."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023"},{"key":"e_1_3_2_1_43_1","volume-title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. arXiv preprint arXiv:2006.02334","author":"Qiao Siyuan","year":"2020","unstructured":"Siyuan Qiao, Liang-Chieh Chen, and Alan Yuille. 2020. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. arXiv preprint arXiv:2006.02334 (2020)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-020-1269-5"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_46_1","volume-title":"Stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Redmon Joseph","year":"2017","unstructured":"Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better, Faster, Stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_47_1","volume-title":"YOLOv3: An Incremental Improvement. CoRR abs\/1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. CoRR abs\/1804.02767 (2018). arXiv:1804.02767 http:\/\/arxiv.org\/abs\/1804.02767"},{"key":"e_1_3_2_1_48_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-020-01044-0"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108001"},{"key":"e_1_3_2_1_51_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Net works for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV] https: \/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-00999-4"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.firesaf.2017.06.012"},{"key":"e_1_3_2_1_55_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, 'ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7464--7475","author":"Wang Chien-Yao","key":"e_1_3_2_1_56_1","unstructured":"Chien-Yao Wang,AlexeyBochkovskiy, and Hong-YuanMarkLiao.2023. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detec tors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7464--7475."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13580-x"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"e_1_3_2_1_60_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050628"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"e_1_3_2_1_63_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 2nd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690170","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688867.3690170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:34:16Z","timestamp":1755974056000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":64,"alternative-id":["10.1145\/3688867.3690170","10.1145\/3688867"],"URL":"https:\/\/doi.org\/10.1145\/3688867.3690170","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}