{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T05:37:06Z","timestamp":1793338626145,"version":"4.5.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012571","type":"print"},{"value":"9783030012588","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01258-8_21","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:35:31Z","timestamp":1538757331000},"page":"342-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":182,"title":["Object Detection in Video with Spatiotemporal Sampling Networks"],"prefix":"10.1007","author":[{"given":"Gedas","family":"Bertasius","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Torresani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"21_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"21_CR3","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Shi, J., Torresani, L.: DeepEdge: a multi-scale bifurcated deep network for top-down contour detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7299067"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L., Yu, S.X., Shi, J.: Convolutional random walk networks for semantic image segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.650"},{"key":"21_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"21_CR12","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural Information Processing Systems (NIPS) (2015)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"21_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","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.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"21_CR17","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems vol. 29, pp. 379\u2013387. Curran Associates Inc. (2016)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 6517\u20136525 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"21_CR20","unstructured":"Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE TCSVT 2017 (2017)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Kang, K., Ouyang, W., Li, H., Wang, X.: Object detection from video tubelets with convolutional neural networks. CoRR abs\/1604.04053 (2016)","DOI":"10.1109\/CVPR.2016.95"},{"key":"21_CR22","unstructured":"Han, W., et al.: Seq-NMS for video object detection. CoRR abs\/1602.08465 (2016)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Lee, B., Erdenee, E., Jin, S., Rhee, P.: Multi-class multi-object tracking using changing point detection. CoRR abs\/1608.08434 (2016)","DOI":"10.1007\/978-3-319-48881-3_6"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 764\u2013773, October 2017","DOI":"10.1109\/ICCV.2017.89"},{"issue":"3","key":"21_CR26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"21_CR28","unstructured":"Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. CoRR abs\/1512.01274 (2015)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.441"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01258-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,4]],"date-time":"2022-10-04T20:40:20Z","timestamp":1664916020000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01258-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012571","9783030012588"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01258-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}