{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:40:20Z","timestamp":1743122420482,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030821951"},{"type":"electronic","value":"9783030821968"}],"license":[{"start":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T00:00:00Z","timestamp":1627948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T00:00:00Z","timestamp":1627948800000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-82196-8_55","type":"book-chapter","created":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T09:09:10Z","timestamp":1627895350000},"page":"736-754","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Enabled Object Detection to\u00a0Improve One-Stage Tracker"],"prefix":"10.1007","author":[{"given":"Neelu","family":"Madan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kamal","family":"Nasrollahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas B.","family":"Moeslund","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,3]]},"reference":[{"key":"55_CR1","doi-asserted-by":"crossref","unstructured":"Bera, A., Kim, S., Manocha, D.: Realtime anomaly detection using trajectory-level crowd behavior learning. In: CVPRW, pp. 1289\u20131296 (2016)","DOI":"10.1109\/CVPRW.2016.163"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"55_CR3","first-page":"2008","volume":"1\u201310","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J. Image Video Process. 1\u201310, 2008 (2008)","journal-title":"EURASIP J. Image Video Process."},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, F., Vedaldi, A., Philip Torr, H.S.: Fully-convolutional siamese networks for object tracking. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Chu, P., Ling, H.: FamNET: joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In: ICCV, pp. 6171\u20136180 (2019)","DOI":"10.1109\/ICCV.2019.00627"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Ess, A., Leibe, B., Schindler, K., van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR. IEEE Press (2008)","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"55_CR9","doi-asserted-by":"crossref","unstructured":"Fitts, J.M.: Precision correlation tracking via optimal weighting functions. In: 1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes, vol. 2, pp. 280\u2013283 (1979)","DOI":"10.1109\/CDC.1979.270181"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"issue":"1","key":"55_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/TIT.1975.1055330","volume":"21","author":"K Fukunaga","year":"1975","unstructured":"Fukunaga, K., Hostetler, L.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21(1), 32\u201340 (1975)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: Graph convolutional tracking. In: CVPR, pp. 4644\u20134654 (2019)","DOI":"10.1109\/CVPR.2019.00478"},{"key":"55_CR13","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. CoRR, abs\/1308.0850 (2013)"},{"key":"55_CR14","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural Turing machines. CoRR, abs\/1410.5401 (2014)"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Guo, H., Zheng, K., Fan, X., Yu, H., Wang, S.: Visual attention consistency under image transforms for multi-label image classification. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00082"},{"issue":"1","key":"55_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3292058","volume":"15","author":"C He","year":"2019","unstructured":"He, C., Hu, H.: Image captioning with visual-semantic double attention. ACM Trans. Multimedia Comput. Commun. Appl. 15(1), 1\u201316 (2019)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Hoffmann, G.M., Tomlin, C.J., Montemerlo, M., Thrun, S.: Autonomous automobile trajectory tracking for off-road driving: controller design, experimental validation and racing. In: American Control Conference, pp. 2296\u20132301 (2007)","DOI":"10.1109\/ACC.2007.4282788"},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"55_CR19","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Y., Liao, I., Chen, C., \u0130k, T., Peng, W.: TrackNet: a deep learning network for tracking high-speed and tiny objects in sports applications*. In 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20138 (2019)","DOI":"10.1109\/AVSS.2019.8909871"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liang, S., Liang, M., Yang, H.: DiaNet: dense-and-implicit attention network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 4206\u20134214 (2020)","DOI":"10.1609\/aaai.v34i04.5842"},{"key":"55_CR22","doi-asserted-by":"crossref","unstructured":"Jadhav, A., Mukherjee, P., Kaushik, V., Lall, B.: Aerial multi-object tracking by detection using deep association networks. In: 2020 National Conference on Communications (NCC), pp. 1\u20136 (2020)","DOI":"10.1109\/NCC48643.2020.9056035"},{"key":"55_CR23","unstructured":"Jetley, A., Lord, N.A., Lee, N., Torr, P.: Learn to pay attention. In: International Conference on Learning Representations (2018)"},{"key":"55_CR24","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"55_CR25","doi-asserted-by":"crossref","unstructured":"Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.101"},{"key":"55_CR26","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)"},{"key":"55_CR27","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W., Yaw, B.: The Hungarian method for the assignment problem. Naval Res. Logist. Quart. 2, 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quart."},{"key":"55_CR28","doi-asserted-by":"crossref","unstructured":"Li, K., Wu, Z., Peng, K.-C., Ernst, J., Fu, Y.: Tell me where to look: guided attention inference network. In: CVPR, pp. 9215\u20139223 (2018)","DOI":"10.1109\/CVPR.2018.00960"},{"key":"55_CR29","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, J., Sha, F., Alan Yuille, L.: Attention correctness in neural image captioning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"55_CR30","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV2020","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV2020, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"55_CR31","unstructured":"Milan, a., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: Mot16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"55_CR32","doi-asserted-by":"crossref","unstructured":"Ning, G., et al.: Spatially supervised recurrent convolutional neural networks for visual object tracking. In: IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20134 (2017)","DOI":"10.1109\/ISCAS.2017.8050867"},{"key":"55_CR33","unstructured":"Oktay, O., et al.: Attention U-NET: learning where to look for the pancreas. ArXiv, abs\/1804.03999 (2018)"},{"key":"55_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_9","volume-title":"Computer Vision","author":"J Peng","year":"2020","unstructured":"Peng, J., et al.: Chained-tracker: chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision. Lecture Notes in Computer Science, vol. 12349. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_9"},{"key":"55_CR35","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. CoRR, abs\/1506.02640 (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"55_CR36","unstructured":"Ren, s., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, NIPS 2015, pp. 91\u201399 (2015)"},{"key":"55_CR37","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R.S., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV Workshops, vol. 2, pp. 17\u201335 (2016)","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"55_CR38","doi-asserted-by":"crossref","unstructured":"Schlemper, J., et al.: Learning to leverage salient regions in medical images, Attention gated networks (2019)","DOI":"10.1016\/j.media.2019.01.012"},{"key":"55_CR39","doi-asserted-by":"crossref","unstructured":"Song, Y., et al.: Vital: visual tracking via adversarial learning. In: CVPR, pp. 8990\u20138999 (2018)","DOI":"10.1109\/CVPR.2018.00937"},{"key":"55_CR40","unstructured":"Sun, K., et al.: Bottom-up human pose estimation by ranking heatmap-guided adaptive keypoint estimates (2020)"},{"key":"55_CR41","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: Mots: multi-object tracking and segmentation. In: CVPR, pp. 7934\u20137943 (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"55_CR42","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.683"},{"key":"55_CR43","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"55_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Wang, S.: Towards real-time multi-object tracking. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"55_CR45","unstructured":"Welch, G., Bishop, G.: An introduction to the Kalman filter (1995)"},{"key":"55_CR46","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645\u20133649 (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"55_CR47","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Convolutional block attention module. In: ECCV, Cham (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"55_CR48","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.360"},{"key":"55_CR49","doi-asserted-by":"crossref","unstructured":"Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., Yan, J.: Poi: multiple object tracking with high performance detection and appearance feature. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-48881-3_3"},{"key":"55_CR50","doi-asserted-by":"crossref","unstructured":"Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., Yan, J.: Poi: multiple object tracking with high performance detection and appearance feature. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-48881-3_3"},{"key":"55_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: A diverse dataset for pedestrian detection. In: CVPR, Citypersons (2017)","DOI":"10.1109\/CVPR.2017.474"},{"key":"55_CR52","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: A simple baseline for multi-object tracking. arXiv preprint arXiv:2004.01888 (2020)"},{"key":"55_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., Tian, Q.: Person re-identification in the wild. In: CVPR, pp. 1367\u20131376 (2017)","DOI":"10.1109\/CVPR.2017.357"},{"key":"55_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Tracking objects as points. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58548-8_28"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82196-8_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T04:10:42Z","timestamp":1672978242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82196-8_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,3]]},"ISBN":["9783030821951","9783030821968"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82196-8_55","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2021,8,3]]},"assertion":[{"value":"3 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}