{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:58:45Z","timestamp":1750309125402,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"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":[[2023,4,14]]},"DOI":"10.1145\/3616901.3616957","type":"proceedings-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T23:07:06Z","timestamp":1709680026000},"page":"234-237","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multiscale Models for Real-Time Human Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3098-2079","authenticated-orcid":false,"given":"Zongyou","family":"Liu","sequence":"first","affiliation":[{"name":"Computer Scienc Shenyang Aerospace University, Shenyang, China, Computer Scienc Shenyang Aerospace University, Shenyang, China, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6048-4850","authenticated-orcid":false,"given":"Wenbai","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science\/Shenyang Aerospace University\/Shenyang, China, Computer Science\/Shenyang Aerospace University\/Shenyang, China, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2254-8720","authenticated-orcid":false,"given":"Hongtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Science\/Shenyang Aerospace University\/Shenyang, China, Computer Scienc Shenyang Aerospace University, Shenyang, China, China"}]}],"member":"320","published-online":{"date-parts":[[2024,3,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25."},{"key":"e_1_3_2_1_2_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems","author":"Ren S","year":"2015","unstructured":"Ren S, He K, Girshick R, Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28."},{"key":"e_1_3_2_1_3_1","volume-title":"Das A","author":"Selvaraju R R","year":"2017","unstructured":"Selvaraju R R, Cogswell M, Das A, Grad-cam: Visual explanations from deep networks via gradient-based localization[C]\/\/Proceedings of the IEEE international conference on computer vision. 2017: 618-626."},{"key":"e_1_3_2_1_4_1","volume-title":"Two-stream convolutional networks for action recognition in videos[J]. Advances in neural information processing systems","author":"Simonyan K","year":"2014","unstructured":"Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[J]. Advances in neural information processing systems, 2014, 27."},{"key":"e_1_3_2_1_5_1","volume-title":"Chen B","author":"Howard A G","year":"2017","unstructured":"Howard A G, Zhu M, Chen B, Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Sandler M Howard A Zhu M Mobilenetv2: Inverted residuals and linear bottlenecks[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_7_1","volume-title":"Real-time 2d multi-person pose estimation on cpu: Lightweight openpose[J]. arXiv preprint arXiv:1811.12004","author":"Osokin D.","year":"2018","unstructured":"Osokin D. Real-time 2d multi-person pose estimation on cpu: Lightweight openpose[J]. arXiv preprint arXiv:1811.12004, 2018."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Girshick R Donahue J Darrell T Rich feature hierarchies for accurate object detection and semantic segmentation[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_9_1","volume-title":"Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556","author":"Simonyan K","year":"2014","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Lin T Y Doll\u00e1r P Girshick R Feature pyramid networks for object detection[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_12_1","volume-title":"Erhan D","author":"Liu W","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D, Ssd: Single shot multibox detector[C]\/\/European conference on computer vision. Springer, Cham, 2016: 21-37."},{"key":"e_1_3_2_1_13_1","volume-title":"Big-little net: An efficient multi-scale feature representation for visual and speech recognition[J]. arXiv preprint arXiv:1807.03848","author":"Chen C F","year":"2018","unstructured":"Chen C F, Fan Q, Mallinar N, Big-little net: An efficient multi-scale feature representation for visual and speech recognition[J]. arXiv preprint arXiv:1807.03848, 2018."},{"key":"e_1_3_2_1_14_1","first-page":"3435","volume":"2019","author":"Chen Y","unstructured":"Chen Y, Fan H, Xu B, Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 3435-3444.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_15_1","volume-title":"High frequency residual learning for multi-scale image classification[J]. arXiv preprint arXiv:1905.02649","author":"Cheng B","year":"2019","unstructured":"Cheng B, Xiao R, Wang J, High frequency residual learning for multi-scale image classification[J]. arXiv preprint arXiv:1905.02649, 2019."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Sun K Xiao B Liu D Deep high-resolution representation learning for human pose estimation[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 5693-5703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_17_1","volume-title":"High-resolution representations for labeling pixels and regions[J]. arXiv preprint arXiv:1904.04514","author":"Sun K","year":"2019","unstructured":"Sun K, Zhao Y, Jiang B, High-resolution representations for labeling pixels and regions[J]. arXiv preprint arXiv:1904.04514, 2019."},{"key":"e_1_3_2_1_18_1","volume-title":"Big-little net: An efficient multi-scale feature representation for visual and speech recognition[J]. arXiv preprint arXiv:1807.03848","author":"Chen C F","year":"2018","unstructured":"Chen C F, Fan Q, Mallinar N, Big-little net: An efficient multi-scale feature representation for visual and speech recognition[J]. arXiv preprint arXiv:1807.03848, 2018."},{"key":"e_1_3_2_1_19_1","first-page":"3435","volume":"2019","author":"Chen Y","unstructured":"Chen Y, Fan H, Xu B, Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 3435-3444.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_20_1","volume-title":"High frequency residual learning for multi-scale image classification[J]. arXiv preprint arXiv:1905.02649","author":"Cheng B","year":"2019","unstructured":"Cheng B, Xiao R, Wang J, High frequency residual learning for multi-scale image classification[J]. arXiv preprint arXiv:1905.02649, 2019."},{"key":"e_1_3_2_1_21_1","volume-title":"High-resolution representations for labeling pixels and regions[J]. arXiv preprint arXiv:1904.04514","author":"Sun K","year":"2019","unstructured":"Sun K, Zhao Y, Jiang B, High-resolution representations for labeling pixels and regions[J]. arXiv preprint arXiv:1904.04514, 2019."}],"event":{"name":"FAIML 2023: 2023 International Conference on Frontiers of Artificial Intelligence and Machine Learning","acronym":"FAIML 2023","location":"Beijing China"},"container-title":["Proceedings of the 2023 International Conference on Frontiers of Artificial Intelligence and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616901.3616957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616901.3616957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:14Z","timestamp":1750286954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616901.3616957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,14]]},"references-count":21,"alternative-id":["10.1145\/3616901.3616957","10.1145\/3616901"],"URL":"https:\/\/doi.org\/10.1145\/3616901.3616957","relation":{},"subject":[],"published":{"date-parts":[[2023,4,14]]},"assertion":[{"value":"2024-03-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}