{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T08:32:51Z","timestamp":1769070771720,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s11042-021-11267-3","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T19:11:41Z","timestamp":1631905901000},"page":"22289-22305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Channel spatial attention based single-shot object detector for autonomous vehicles"],"prefix":"10.1007","volume":"81","author":[{"given":"Divya","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"11267_CR1","doi-asserted-by":"crossref","unstructured":"Bernardin K, Stiefelhagen R (2018) Evaluating multiple object tracking performance: the CLEAR MOT Metrics. 2008","DOI":"10.1155\/2008\/246309"},{"key":"11267_CR2","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. Lect Notes Comput Sci\u00a0(including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), vol 9908 LNCS, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"11267_CR3","doi-asserted-by":"crossref","unstructured":"Casanova A, Cucurull G, Drozdzal M, Romero A, Bengio Y (2018) On the iterative refinement of densely connected representation levels for semantic segmentation. In: IEEE Comput Soc Conf Comput Vis Pattern Recognit workshops, vol 2018-June, pp 1091\u20131100","DOI":"10.1109\/CVPRW.2018.00144"},{"key":"11267_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02067-9","author":"G Chen","year":"2021","unstructured":"Chen G, Qin H (2021) Class-discriminative focal loss for extreme imbalanced multiclass object detection towards autonomous driving. Vis Comput. https:\/\/doi.org\/10.1007\/s00371-021-02067-9","journal-title":"Vis Comput"},{"key":"11267_CR5","doi-asserted-by":"crossref","unstructured":"Choi J, Chun D, Kim H, Lee HJ (2019) Gaussian YOLOv3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: Proceedings of the IEEE Int Conf Comput Vis, vol 2019-Oct, pp 502\u2013511","DOI":"10.1109\/ICCV.2019.00059"},{"key":"11267_CR6","doi-asserted-by":"crossref","unstructured":"Gao Z, Xie J, Wang Q, Li P (2018) Global second-order pooling convolutional networks. arXiv, pp 3024\u20133033","DOI":"10.1109\/CVPR.2019.00314"},{"issue":"11","key":"11267_CR7","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the KITTI dataset. Int J Rob Res 32(11):1231\u20131237","journal-title":"Int J Rob Res"},{"key":"11267_CR8","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"11267_CR9","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE Int Conf Comput Vis, vol. 2015 Inter, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"11267_CR10","unstructured":"Hu J, Shen L, Albanie S, Sun G, Vedaldi A (2018) Gather-excite: exploiting feature context in convolutional neural networks. In: Adv Neural Inf Process Syst, vol 2018-Dec, no NeurIPS, pp 9401\u20139411"},{"key":"11267_CR11","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"3","key":"11267_CR12","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/TITS.2018.2838132","volume":"20","author":"X Hu","year":"2019","unstructured":"Hu X et al (2019) SINet: a scale-insensitive convolutional neural network for fast vehicle detection. IEEE Trans Intell Transport Syst 20(3):1010\u20131019","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"3","key":"11267_CR13","doi-asserted-by":"publisher","first-page":"128837","DOI":"10.1109\/ACCESS.2019.2939201","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao L et al (2019) A survey of deep learning-based object detection. IEEE Access 7(3):128837\u2013128868","journal-title":"IEEE Access"},{"key":"11267_CR14","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. Proceedings of the IEEE Int Conf Comput Vis, vol 2017-Oct, pp 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"11267_CR15","doi-asserted-by":"crossref","unstructured":"Liu W et al (2016) SSD: Single shot multibox detector. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), vol 9905 LNCS, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11267_CR16","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2018) Receptive field block net for accurate and fast object detection. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), vol 11215 LNCS, pp 404\u2013419","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"11267_CR17","unstructured":"Lu J, J. Yang J, Batra D, Parikh D (2016) Hierarchical question-image co-attention for visual question answering. In: Adv Neural Inf Process Syst, no c, pp 289\u2013297"},{"key":"11267_CR18","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, vol 2016-Dec, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"11267_CR19","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the 30th IEEE Comput Soc Conf Comput Vis Pattern Recognit, CVPR 2017, vol 2017-Jan, pp 6517\u20136525","DOI":"10.1109\/CVPR.2017.690"},{"key":"11267_CR20","unstructured":"Redmon J, Farhadi A (2017) YOLOv3: an incremental improvement. In: Proceedings of the tech report, Comp Vis Pattern Recognit, CVPR 2018, vol 2017"},{"issue":"6","key":"11267_CR21","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"11267_CR22","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/TMI.2018.2867261","volume":"38","author":"AG Roy","year":"2019","unstructured":"Roy AG, Navab N, Wachinger C (2019) Recalibrating fully convolutional networks with spatial and channel \u2018squeeze and excitation\u2019 blocks. IEEE Trans Med Imaging 38(2):540\u2013549","journal-title":"IEEE Trans Med Imaging"},{"key":"11267_CR23","unstructured":"Seo PH, Lehrmann A, Han B, Sigal L (2017) Visual reference resolution using attention memory for visual dialog. In: Adv Neural Inf Process Syst, vol 2017-Dec, no Nips, pp 3720\u20133730"},{"key":"11267_CR24","unstructured":"Seo PH, Lin Z, Cohen S, Shen X, Han B (2019) Progressive attention networks for visual attribute prediction. In: BMVC\u00a02018, BMVC 2018, pp 1\u201319"},{"key":"11267_CR25","doi-asserted-by":"crossref","unstructured":"Singh S, Krishnan S (2019) Filter response normalization layer: eliminating batch dependence in the training of deep neural networks.","DOI":"10.1109\/CVPR42600.2020.01125"},{"key":"11267_CR26","doi-asserted-by":"crossref","unstructured":"SWoo S, Park J, Lee JY, Kweon IS (2018) CBAM: convolutional block attention module. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), vol 11211 LNCS, pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11267_CR27","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE Int Conf Comput Vis, vol 2019-Oct, pp 9626\u20139635","DOI":"10.1109\/ICCV.2019.00972"},{"key":"11267_CR28","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2019) ECA-Net: efficient channel attention for deep convolutional neural networks.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"11267_CR29","doi-asserted-by":"crossref","unstructured":"Yu F et al (2020) BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp 2633\u20132642","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"11267_CR30","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"11267_CR31","doi-asserted-by":"crossref","unstructured":"Zhao Q, Wang Y, Sheng T, Tang Z (2019) Comprehensive feature enhancement module for single-shot object detector. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), vol 11365 LNCS, pp 325\u2013340","DOI":"10.1007\/978-3-030-20873-8_21"},{"key":"11267_CR32","doi-asserted-by":"crossref","unstructured":"Zhu Y, Groth O, Bernstein M, Fei-Fei L (2016) Visual7W: grounded question answering in images. In: Proceedings of the IEEE Comput Soc Conf Comput Vis Pattern Recognit, vol 2016-December, pp 4995\u20135004","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11267-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11267-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11267-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T07:31:45Z","timestamp":1655883105000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11267-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,17]]},"references-count":32,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["11267"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11267-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,17]]},"assertion":[{"value":"25 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}