{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:16:39Z","timestamp":1740147399452,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T00:00:00Z","timestamp":1620345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T00:00:00Z","timestamp":1620345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Robotics Institute of Zhejiang University under","award":["110202-I21707"],"award-info":[{"award-number":["110202-I21707"]}]},{"name":"Stable Support Project of State Administration of Science, Technology and Industry for National Defence Grant, PRC","award":["HTKJ2019KL502005"],"award-info":[{"award-number":["HTKJ2019KL502005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s11760-021-01926-1","type":"journal-article","created":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T07:03:07Z","timestamp":1620370987000},"page":"1785-1795","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A novel memory mechanism for video object detection from indoor mobile robots"],"prefix":"10.1007","volume":"15","author":[{"given":"Jiyuan","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-2224","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehua","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"1926_CR1","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1007\/s11760-020-01710-7","volume":"14","author":"J Chen","year":"2020","unstructured":"Chen, J., Wang, J., Zhao, L., et al.: Branch-structured detector for fast face detection using asymmetric LBP features. SIViP 14, 1699\u20131706 (2020)","journal-title":"SIViP"},{"issue":"3","key":"1926_CR2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"1926_CR3","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistnet, C., Civera, J., et al.: Learning object class detectors from weakly annotated video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"1926_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1926_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1926_CR6","unstructured":"Ren, S., He, K., R. Girshick, et al.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"1926_CR7","unstructured":"Dai, J., Li, Y., He, K., et al.: R-fcn: Object detection via region-based fully convolutional networks. In: NIPS (2016)"},{"key":"1926_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00b4ar, P., et al.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1926_CR9","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., et al.: Libra R-CNN: towards balanced learning for object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1926_CR10","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D. et al.: SSD: single shot multibox detector. In: ICCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1926_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1926_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A., et al.: YOLO9000: better, faster, stronger. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1926_CR13","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv preprint https:\/\/arxiv.org\/abs\/1804.02767 (2018)"},{"key":"1926_CR14","unstructured":"Han, W., Khorrami, P., Le Paine, T., et al.: Seq-nms for video object detection. arXiv preprinthttps:\/\/arxiv.org\/abs\/1602.08465, 2016."},{"key":"1926_CR15","doi-asserted-by":"crossref","unstructured":"Kang, K., Li, H., Xiao, T., et al.: Object detection in videos with tubelet proposal networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.101"},{"key":"1926_CR16","doi-asserted-by":"crossref","unstructured":"Kang, K., Li, H., Yan, J., et al.: T-cnn: Tubelets with convolutional neural networks for object detection from videos. arXiv preprint https:\/\/arxiv.org\/abs\/1604.02532 (2016)","DOI":"10.1109\/CVPR.2016.95"},{"key":"1926_CR17","unstructured":"Kang, K., Ouyang, W., Li, H.: Detect to track and track to detect. In convolutional neural networks. In: CVPR (2016)"},{"key":"1926_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"1926_CR19","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., et al.: Deep feature flow for video recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.441"},{"key":"1926_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., et al.: Flow-guided feature aggregation for video object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"1926_CR21","doi-asserted-by":"crossref","unstructured":"Lee, B., Erdenee, E., Jin, S., et al.: Multi-class multi-object tracking using changing point detection. In: ECCV (2016).","DOI":"10.1007\/978-3-319-48881-3_6"},{"key":"1926_CR22","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., et al.: Towards high performance video object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"1926_CR23","unstructured":"Liu, M., Zhu, M., White, M., et al.: Looking Fast and slow: memory-guided mobile video object detection. arXiv preprint https:\/\/arxiv.org\/abs\/1903.10172."},{"key":"1926_CR24","doi-asserted-by":"crossref","unstructured":"Xiao, F., Lee, Y.: Video Object detection with an aligned spatial-temporal memory. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"1926_CR25","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatiotemporal sampling networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"1926_CR26","unstructured":"Liu, M., Zhu, M.: Mobile video object detection with temporally-aware feature maps. In: CVPR (2018)"},{"key":"1926_CR27","doi-asserted-by":"crossref","unstructured":"Ren, Z., Yu, Z., Yang X., et al.: Instance-aware, context-focused, and memory-efficient weakly supervised object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"1926_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Liu, Y., Yang, C.: Learning Where to focus for efficient video object detection. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"1926_CR29","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T.: Relation distillation networks for video object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"issue":"8","key":"1926_CR30","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1926_CR31","doi-asserted-by":"crossref","unstructured":"Cho, K., Merri\u00a8enboer, B., Gulcehre, C., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint https:\/\/arxiv.org\/abs\/1406.1078, (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1926_CR32","doi-asserted-by":"crossref","unstructured":"Deng, H., Hua, Y., Song, T., et al.: Object guided external memory network for video object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00678"},{"key":"1926_CR33","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H.: Memory enhanced global-local aggregation for video object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"1926_CR34","unstructured":"Howard, A., Zhu, M., Chen, B., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint https:\/\/arxiv.org\/abs\/1704.04861, 2017."},{"key":"1926_CR35","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N.: Sequence level semantics aggregation for video object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"1926_CR36","doi-asserted-by":"crossref","unstructured":"Choi, W.: Near-online multi-target tracking with aggregated local flow descriptor. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.347"},{"key":"1926_CR37","doi-asserted-by":"crossref","unstructured":"Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: ECCV (2008)","DOI":"10.1007\/978-3-540-88688-4_58"},{"issue":"4","key":"1926_CR38","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1037\/0033-295X.96.4.703","volume":"96","author":"JR Anderson","year":"1989","unstructured":"Anderson, J.R., Milson, R.: Human memory: an adaptive perspective. Psychol. Rev. 96(4), 703\u2013719 (1989)","journal-title":"Psychol. Rev."},{"key":"1926_CR39","doi-asserted-by":"crossref","unstructured":"Kalal, Z., Mikolajczyk, K., Matas, J.: Forward-Backward error: automatic detection of tracking failures. In: ICPR (2010)","DOI":"10.1109\/ICPR.2010.675"},{"key":"1926_CR40","unstructured":"Melonee, W., Tully, F.: Specification for turtlebot compatible platforms. ROSWeb. https:\/\/www.ros.org\/reps\/rep-0119.html (2021). Accessed 1 March 2021."},{"key":"1926_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1926_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S.,et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1926_CR43","doi-asserted-by":"crossref","unstructured":"Deselaers, T., Alexe, B., Ferrari, V.: Localizing objects while learning their appearance. In: ECCV (2010)","DOI":"10.1007\/978-3-642-15561-1_33"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01926-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-01926-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01926-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T15:47:53Z","timestamp":1672069673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-01926-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,7]]},"references-count":43,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1926"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-01926-1","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2021,5,7]]},"assertion":[{"value":"21 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}