{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T03:02:57Z","timestamp":1789268577887,"version":"build-2803163510"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T00:00:00Z","timestamp":1628812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T00:00:00Z","timestamp":1628812800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11263-021-01507-2","type":"journal-article","created":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T07:03:01Z","timestamp":1628838181000},"page":"2927-2946","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Context and Structure Mining Network for Video Object Detection"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-1114","authenticated-orcid":false,"given":"Liang","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaozheng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,13]]},"reference":[{"key":"1507_CR1","unstructured":"Bertasius, G., Torresani, L., & Shi, J. (2018). Object detection in video with spatiotemporal sampling networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (pp. 331\u2013346)."},{"key":"1507_CR2","doi-asserted-by":"crossref","unstructured":"Chen, K., Wang, J., Yang, S., Zhang, X., Xiong, Y., Change\u00a0Loy, C., & Lin, D. (2018a). Optimizing video object detection via a scale-time lattice. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7814\u20137823).","DOI":"10.1109\/CVPR.2018.00815"},{"key":"1507_CR3","unstructured":"Chen, Y., Cao, Y., Hu, H., & Wang, L. (2020). Memory enhanced global-local aggregation for video object detection. In: CVPR."},{"key":"1507_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Huang, S., & Tao, D. (2018b). Context refinement for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV) (pp. 71\u201386).","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"1507_CR5","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. In: Advances in neural information processing systems (pp. 379\u2013387)."},{"key":"1507_CR6","doi-asserted-by":"crossref","unstructured":"Deng, H., Hua, Y., Song, T., Zhang, Z., Xue, Z., Ma, R., Robertson, N., & Guan, H. (2019a). Object guided external memory network for video object detection. In: Proceedings of the IEEE international conference on computer vision (pp. 6678\u20136687).","DOI":"10.1109\/ICCV.2019.00678"},{"key":"1507_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., & Mei, T. (2019b). Relation distillation networks for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision (pp. 7023\u20137032).","DOI":"10.1109\/ICCV.2019.00712"},{"key":"1507_CR8","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der\u00a0Smagt, P., Cremers, D., Brox, T . (2015). Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE international conference on computer vision (pp. 2758\u20132766)."},{"key":"1507_CR9","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2017). Detect to track and track to detect. In: Proceedings of the IEEE international conference on computer vision (pp. 3038\u20133046)."},{"key":"1507_CR10","unstructured":"Fu, C. Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). DSSD: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659"},{"issue":"3","key":"1507_CR11","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1109\/TIP.2018.2872831","volume":"28","author":"Z Gao","year":"2018","unstructured":"Gao, Z., Wang, L., & Zhou, L. (2018). A probabilistic approach to cross-region matching-based image retrieval. IEEE Transactions on Image Processing, 28(3), 1191\u20131204.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1507_CR12","unstructured":"Girshick, R. (2015). Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision (pp. 1440\u20131448)."},{"key":"1507_CR13","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 conference on computer vision and pattern recognition (pp. 580\u2013587)."},{"key":"1507_CR14","unstructured":"Guo, C., Fan, B., Gu, J., Zhang, Q., Xiang, S., Prinet, V., & Pan, C. (2019). Progressive sparse local attention for video object detection. In: Proceedings of the IEEE international conference on computer vision."},{"key":"1507_CR15","doi-asserted-by":"crossref","unstructured":"Han, L,, Wang, P., Yin, Z., Wang, F., & Li, H. (2020a). Exploiting better feature aggregation for video object detection. In: ACM MM.","DOI":"10.1145\/3394171.3413927"},{"key":"1507_CR16","doi-asserted-by":"crossref","unstructured":"Han, M., Wang, Y., Chang, X., & Qiao, Y. (2020b). Mining inter-video proposal relations for video object detection. In: European conference on computer vision (pp. 431\u2013446). Springer.","DOI":"10.1007\/978-3-030-58589-1_26"},{"key":"1507_CR17","unstructured":"Han, W., Khorrami, P., Paine, T. L., Ramachandran, P., Babaeizadeh, M., Shi, H., Li, J., Yan, S., & Huang, T. S. (2016). Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465"},{"key":"1507_CR18","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778)."},{"key":"1507_CR19","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision (pp. 2961\u20132969)."},{"key":"1507_CR20","unstructured":"Howard, AG., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"1507_CR21","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018). Relation networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3588\u20133597)."},{"key":"1507_CR22","doi-asserted-by":"publisher","first-page":"8529","DOI":"10.1609\/aaai.v33i01.33018529","volume":"33","author":"Z Jiang","year":"2019","unstructured":"Jiang, Z., Gao, P., Guo, C., Zhang, Q., Xiang, S., & Pan, C. (2019). Video object detection with locally-weighted deformable neighbors. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8529\u20138536.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1507_CR23","unstructured":"Jiang, Z., Liu, Y., Yang, C., Liu, J., Gao, P., Zhang, Q., Xiang, S., & Pan, C. (2020). Learning where to focus for efficient video object detection. In: European conference on computer vision (pp. 18\u201334). Springer."},{"key":"1507_CR24","unstructured":"Kang, K., Ouyang, W., Li, H., & Wang, X. (2016). Object detection from video tubelets with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 817\u2013825)."},{"issue":"10","key":"1507_CR25","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., Li, H., Yan, J., Zeng, X., Yang, B., Xiao, T., et al. (2017). T-CNN: Tubelets with convolutional neural networks for object detection from videos. IEEE Transactions on Circuits and Systems for Video Technology, 28(10), 2896\u20132907.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1507_CR26","unstructured":"Kantorov, V., Oquab, M., Cho, M., & Laptev, I. (2016). Contextlocnet: Context-aware deep network models for weakly supervised localization. In: European Conference on Computer Vision (pp 350\u2013365). Springer."},{"key":"1507_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017a). Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1507_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017b). Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.324"},{"key":"1507_CR29","unstructured":"Liu, M., & Zhu, M. (2018). Mobile video object detection with temporally-aware feature maps. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5686\u20135695)."},{"key":"1507_CR30","unstructured":"Liu, M., Zhu, M., White, M., Li, Y., & Kalenichenko, D. (2019). Looking fast and slow: Memory-guided mobile video object detection. arXiv preprint arXiv:1903.10172"},{"key":"1507_CR31","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, AC. (2016). SSD: Single shot multibox detector. In: European conference on computer vision (pp. 21\u201337). Springer."},{"key":"1507_CR32","unstructured":"Redmon, J., Farhadi, A .(2017) . Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263\u20137271)."},{"key":"1507_CR33","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"1507_CR34","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779\u2013788)."},{"key":"1507_CR35","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, vol 28 (pp. 91\u201399)."},{"issue":"3","key":"1507_CR36","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., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1507_CR37","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510\u20134520)."},{"key":"1507_CR38","unstructured":"Sharif Razavian A, Sullivan J, Maki A, Carlsson S (2015) A baseline for visual instance retrieval with deep convolutional networks. In: International conference on learning representations, 7\u20139 May 2015. San Diego. ICLR: CA."},{"key":"1507_CR39","unstructured":"Shvets, M., Liu, W., & Berg, A. C. (2019). Leveraging long-range temporal relationships between proposals for video object detection. In: Proceedings of the IEEE international conference on computer vision (pp. 9756\u20139764)."},{"key":"1507_CR40","unstructured":"Tian, Z., Shen, C., Chen, H., & He, T. (2019). FCOS: Fully convolutional one-stage object detection. In: ICCV."},{"key":"1507_CR41","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In: Advances in neural information processing systems pp. 5998\u20136008."},{"key":"1507_CR42","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhou, Y., Yan, J., & Deng, Z. (2018a). Fully motion-aware network for video object detection. In: Proceedings of the European Conference on Computer Vision (ECCV) (pp. 542\u2013557).","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"1507_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018b). Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1507_CR44","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z. (2019). Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE international conference on computer vision (pp. 9217\u20139225)."},{"key":"1507_CR45","unstructured":"Xiao, F., & Jae Lee, Y. (2018). Video object detection with an aligned spatial-temporal memory. In: Proceedings of the European Conference on Computer Vision (ECCV) (pp. 485\u2013501)."},{"key":"1507_CR46","unstructured":"Xu, Z., Hrustic, E., & Vivet, D. (2020). Centernet heatmap propagation for real-time video object detection. In: European conference on computer vision (pp. 220\u2013234)."},{"key":"1507_CR47","unstructured":"Yao, CH., Fang, C., Shen, X., Wan, Y., & Yang, MH. (2020). Video object detection via object-level temporal aggregation. In: European conference on computer vision (pp. 160\u2013177)."},{"key":"1507_CR48","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"1507_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., & Wei, Y. (2017a). Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE international conference on computer vision (pp. 408\u2013417).","DOI":"10.1109\/ICCV.2017.52"},{"key":"1507_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., & Wei, Y. (2017b). Deep feature flow for video recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.441"},{"key":"1507_CR51","unstructured":"Zhu, X., Dai, J., Yuan, L., & Wei, Y. (2018). Towards high performance video object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7210\u20137218)."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01507-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01507-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01507-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:06:36Z","timestamp":1725624396000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01507-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,13]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["1507"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01507-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,13]]},"assertion":[{"value":"17 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}