{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:27:14Z","timestamp":1760956034211,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T00:00:00Z","timestamp":1591574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["61303029"],"award-info":[{"award-number":["61303029"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,8]]},"DOI":"10.1145\/3372278.3390714","type":"proceedings-article","created":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T04:35:27Z","timestamp":1591072527000},"page":"548-554","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimizing Queries over Video via Lightweight Keypoint-based Object Detection"],"prefix":"10.1145","author":[{"given":"Jiansheng","family":"Dong","sequence":"first","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Xian","family":"Zhong","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Weiru","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2020,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Xception: Deep learning with depthwise separable convolutions. In CVPR. 1251--1258.","author":"Chollet F.","year":"2017","unstructured":"F. Chollet . 2017 . Xception: Deep learning with depthwise separable convolutions. In CVPR. 1251--1258. F. Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. In CVPR. 1251--1258."},{"key":"e_1_3_2_1_2_1","volume-title":"Centernet: Keypoint triplets for object detection. In ICCV. 6569--6578.","author":"Duan K.","year":"2019","unstructured":"K. Duan , S. Bai , L. Xie , H. Qi , Q. Huang , and Q. Tian . 2019 . Centernet: Keypoint triplets for object detection. In ICCV. 6569--6578. K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian. 2019. Centernet: Keypoint triplets for object detection. In ICCV. 6569--6578."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"C. Eggert D. Zecha S. Brehm and R. Lienhart. 2017. Improving small object proposals for company logo detection. In ICMR. 167--174.  C. Eggert D. Zecha S. Brehm and R. Lienhart. 2017. Improving small object proposals for company logo detection. In ICMR. 167--174.","DOI":"10.1145\/3078971.3078990"},{"key":"e_1_3_2_1_4_1","volume-title":"Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659","author":"Fu C.-Y.","year":"2017","unstructured":"C.-Y. Fu , W. Liu , A. Ranga , A. Tyagi , and A. C Berg . 2017 . Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017). C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C Berg. 2017. Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"R. Girshick J. Donahue T. Darrell and J. Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR. 580--587.  R. Girshick J. Donahue T. Darrell and J. Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR. 580--587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"K. He G. Gkioxari P. Doll\u00e1r and R. Girshick. 2017. Mask r-cnn. In CVPR. 2961--2969.  K. He G. Gkioxari P. Doll\u00e1r and R. Girshick. 2017. Mask r-cnn. In CVPR. 2961--2969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_7_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard A.","year":"2017","unstructured":"A. Howard , Me. Zhu , B. Chen , D. Kalenichenko , W. Wang , T. Weyand , M. Andreetto , and H. Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). A. Howard, Me. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_8_1","volume-title":"Focus: Querying large video datasets with low latency and low cost. In OSDI. 269--286.","author":"Hsieh K.","year":"2018","unstructured":"K. Hsieh , G. Ananthanarayanan , P. Bodik , S. Venkataraman , P. Bahl , M. Philipose , P. Gibbons , and O. Mutlu . 2018 . Focus: Querying large video datasets with low latency and low cost. In OSDI. 269--286. K. Hsieh, G. Ananthanarayanan, P. Bodik, S. Venkataraman, P. Bahl, M. Philipose, P. Gibbons, and O. Mutlu. 2018. Focus: Querying large video datasets with low latency and low cost. In OSDI. 269--286."},{"key":"e_1_3_2_1_9_1","volume-title":"Blazeit: Fast exploratory video queries using neural networks. arXiv preprint arXiv:1805.01046","author":"Kang D.","year":"2018","unstructured":"D. Kang , P. Bailis , and M. Zaharia . 2018 . Blazeit: Fast exploratory video queries using neural networks. arXiv preprint arXiv:1805.01046 (2018). D. Kang, P. Bailis, and M. Zaharia. 2018. Blazeit: Fast exploratory video queries using neural networks. arXiv preprint arXiv:1805.01046 (2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"D. Kang J. Emmons F. Abuzaid P. Bailis and M. Zaharia. 2017. Noscope: optimizing neural network queries over video at scale. arXiv preprint arXiv:1703.02529 (2017).  D. Kang J. Emmons F. Abuzaid P. Bailis and M. Zaharia. 2017. Noscope: optimizing neural network queries over video at scale. arXiv preprint arXiv:1703.02529 (2017).","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_1_11_1","volume-title":"Cornernet: Detecting objects as paired keypoints. In ECCV. 734--750.","author":"Law H.","year":"2018","unstructured":"H. Law and J. Deng . 2018 . Cornernet: Detecting objects as paired keypoints. In ECCV. 734--750. H. Law and J. Deng. 2018. Cornernet: Detecting objects as paired keypoints. In ECCV. 734--750."},{"key":"e_1_3_2_1_12_1","volume-title":"Ssd: Single shot multibox detector. In ECCV. 21--37.","author":"Liu W.","year":"2016","unstructured":"W. Liu , D. Anguelov , D. Erhan , C. Szegedy , S. Reed , C.-Y. Fu , and A. C Berg . 2016 . Ssd: Single shot multibox detector. In ECCV. 21--37. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C Berg. 2016. Ssd: Single shot multibox detector. In ECCV. 21--37."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"A. Newell K. Yang and J. Deng. 2016. Stacked hourglass networks for human pose estimation. In ECCV. 483--499.  A. Newell K. Yang and J. Deng. 2016. Stacked hourglass networks for human pose estimation. In ECCV. 483--499.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_3_2_1_14_1","volume-title":"Thundernet: Towards real-time generic object detection. arXiv preprint arXiv:1903.11752","author":"Qin Z.","year":"2019","unstructured":"Z. Qin , Z. Li , Z. Zhang , Y. Bao , G. Yu , Y. Peng , and J. Sun . 2019 . Thundernet: Towards real-time generic object detection. arXiv preprint arXiv:1903.11752 (2019). Z. Qin, Z. Li, Z. Zhang, Y. Bao, G. Yu, Y. Peng, and J. Sun. 2019. Thundernet: Towards real-time generic object detection. arXiv preprint arXiv:1903.11752 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"J. Redmon S. Divvala R. Girshick and A. Farhadi. 2016. You only look once: Unified real-time object detection. In CVPR. 779--788.  J. Redmon S. Divvala R. Girshick and A. Farhadi. 2016. You only look once: Unified real-time object detection. In CVPR. 779--788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"J. Redmon and A. Farhadi. 2017. YOLO9000: better faster stronger. In CVPR. 7263--7271.  J. Redmon and A. Farhadi. 2017. YOLO9000: better faster stronger. In CVPR. 7263--7271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_17_1","unstructured":"J. Redmon and A. Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018).  J. Redmon and A. Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_18_1","unstructured":"S. Ren K. He R. Girshick and J. Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS. 91--99.  S. Ren K. He R. Girshick and J. Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS. 91--99."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"M. Sandler A. Howard M. Zhu A. Zhmoginov and L.-C. Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR. 4510--4520.  M. Sandler A. Howard M. Zhu A. Zhmoginov and L.-C. Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR. 4510--4520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"K. Sun B. Xiao D. Liu and J. Wang. 2019. Deep high-resolution representation learning for human pose estimation. In CVPR. 5693--5703.  K. Sun B. Xiao D. Liu and J. Wang. 2019. Deep high-resolution representation learning for human pose estimation. In CVPR. 5693--5703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_21_1","volume-title":"Pelee: A real-time object detection system on mobile devices. In NIPS. 1963--1972.","author":"Wang R.","year":"2018","unstructured":"R. Wang , X. Li , and C. Ling . 2018 . Pelee: A real-time object detection system on mobile devices. In NIPS. 1963--1972. R. Wang, X. Li, and C. Ling. 2018. Pelee: A real-time object detection system on mobile devices. In NIPS. 1963--1972."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"S. Zhang L. Wen X. Bian Z. Lei and S. Li. 2018. Single-shot refinement neural network for object detection. In CVPR. 4203--4212.  S. Zhang L. Wen X. Bian Z. Lei and S. Li. 2018. Single-shot refinement neural network for object detection. In CVPR. 4203--4212.","DOI":"10.1109\/CVPR.2018.00442"},{"key":"e_1_3_2_1_23_1","first-page":"4","article-title":"2019. Panorama: a data system for unbounded vocabulary querying over video","volume":"13","author":"Zhang Y.","year":"2019","unstructured":"Y. Zhang and A. Kumar . 2019. Panorama: a data system for unbounded vocabulary querying over video . VLDB , Vol. 13 , 4 ( 2019 ), 477--491. Y. Zhang and A. Kumar. 2019. Panorama: a data system for unbounded vocabulary querying over video. VLDB, Vol. 13, 4 (2019), 477--491.","journal-title":"VLDB"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"X. Zhou J. Zhuo and P. Krahenbuhl. 2019. Bottom-up object detection by grouping extreme and center points. In CVPR. 850--859.  X. Zhou J. Zhuo and P. Krahenbuhl. 2019. Bottom-up object detection by grouping extreme and center points. In CVPR. 850--859.","DOI":"10.1109\/CVPR.2019.00094"}],"event":{"name":"ICMR '20: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"ICMR '20"},"container-title":["Proceedings of the 2020 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372278.3390714","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3372278.3390714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:24Z","timestamp":1750199604000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372278.3390714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,8]]},"references-count":24,"alternative-id":["10.1145\/3372278.3390714","10.1145\/3372278"],"URL":"https:\/\/doi.org\/10.1145\/3372278.3390714","relation":{},"subject":[],"published":{"date-parts":[[2020,6,8]]},"assertion":[{"value":"2020-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}