{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:05:55Z","timestamp":1776888355879,"version":"3.51.2"},"reference-count":36,"publisher":"Tsinghua University Press","issue":"1","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T00:00:00Z","timestamp":1585785600000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s41095-020-0158-8","type":"journal-article","created":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T08:02:35Z","timestamp":1585814555000},"page":"79-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["What and where: A context-based recommendation system for object insertion"],"prefix":"10.26599","volume":"6","author":[{"given":"Song-Hai","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing 100084, China; Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing 100084, China"}]},{"given":"Zheng-Ping","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing 100084, China"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing 100084, China"}]},{"given":"Xi","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing 100084, China"}]},{"given":"Peter","family":"Hall","sequence":"additional","affiliation":[{"name":"Department of Computer Science Media Technology Research Center, University of Bath, Bath BA2 7AY, UK"}]}],"member":"11138","reference":[{"key":"158_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3","volume-title":"Recommender Systems Handbook","author":"F Ricci","year":"2011","unstructured":"Ricci, F.; Rokach, L.; Shapira, B. Recommender Systems Handbook. Boston: Springer, 2011."},{"key":"158_CR2","unstructured":"Recommender system. Available at https:\/\/en.wikipedia.org\/wiki\/Recommender_system."},{"key":"158_CR3","first-page":"3668","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Johnson","year":"2015","unstructured":"Johnson, J.; Krishna, R.; Stark, M.; Li, L. J.; Shamma, D. A.; Bernstein, M. S.; Fei-Fei, L. Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3668\u20133678, 2015."},{"issue":"1","key":"158_CR4","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/JPROC.2015.2487976","volume":"104","author":"J Wang","year":"2016","unstructured":"Wang, J.; Liu, W.; Kumar, S.; Chang, S. F. Learning to hash for indexing big data: A survey. Proceedings of the IEEE Vol. 104, No. 1, 34\u201357, 2016.","journal-title":"Proceedings of the IEEE"},{"issue":"5","key":"158_CR5","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TPAMI.2017.2709749","volume":"40","author":"L Zheng","year":"2018","unstructured":"Zheng, L.; Yang, Y.; Tian, Q. SIFT meets CNN: A decade survey of instance retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 5, 1224\u20131244, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"158_CR6","first-page":"1","volume-title":"Proceedings of the IEEE 11th International Conference on Computer Vision","author":"A Rabinovich","year":"2007","unstructured":"Rabinovich, A.; Vedaldi, A.; Galleguillos, C.; Wiewiora, E.; Belongie, S. Objects in context. In: Proceedings of the IEEE 11th International Conference on Computer Vision, 1\u20138, 2007."},{"key":"158_CR7","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"K M He","year":"2016","unstructured":"He, K. M.; Zhang, X. Y.; Ren, S. Q.; Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778, 2016."},{"key":"158_CR8","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A.; Sutskever, I.; Hinton, G. E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems 25, 1097\u20131105, 2012.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"158_CR9","first-page":"1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"C Szegedy","year":"2015","unstructured":"Szegedy, C.; Liu, W.; Jia, Y. Q.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1\u20139, 2015."},{"key":"158_CR10","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. In: Proceedings of the Advances in Neural Information Processing Systems 28, 91\u201399, 2015.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"158_CR11","first-page":"580","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"R Girshick","year":"2014","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, 580\u2013587, 2014."},{"key":"158_CR12","first-page":"21","volume-title":"Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9905","author":"W Liu","year":"2016","unstructured":"Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C. Y.; Berg, A. C. SSD: Single shot MultiBox detector. In: Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9905. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 21\u201337, 2016."},{"key":"158_CR13","first-page":"2921","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"B L Zhou","year":"2016","unstructured":"Zhou, B. L.; Khosla, A.; Lapedriza, A.; Oliva, A.; Torralba, A. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921\u20132929, 2016."},{"key":"158_CR14","first-page":"2846","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"H Bilen","year":"2016","unstructured":"Bilen, H.; Vedaldi, A. Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2846\u20132854, 2016."},{"key":"158_CR15","first-page":"350","volume-title":"Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9909","author":"V Kantorov","year":"2016","unstructured":"Kantorov, V.; Oquab, M.; Cho, M.; Laptev, I. ContextLocNet: Context-aware deep network models for weakly supervised localization. In: Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9909. Leibe B.; Matas J.; Sebe N.; Welling M. Eds. Springer Cham, 350\u2013365, 2016."},{"key":"158_CR16","first-page":"2961","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"K M He","year":"2017","unstructured":"He, K. M.; Gkioxari, G.; Dollar, P.; Girshick, R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2961\u20132969, 2017."},{"key":"158_CR17","first-page":"3431","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Long","year":"2015","unstructured":"Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431\u20133440, 2015."},{"key":"158_CR18","volume-title":"Parsenet: Looking wider to see better","author":"W Liu","year":"2015","unstructured":"Liu, W.; Rabinovich, A.; Berg, A. C. Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579, 2015."},{"key":"158_CR19","volume-title":"Recent advance in content-based image retrieval: A literature survey","author":"W Zhou","year":"2017","unstructured":"Zhou, W.; Li, H.; Tian, Q. Recent advance in content-based image retrieval: A literature survey. arXiv preprint arXiv:1706.06064, 2017."},{"issue":"6","key":"158_CR20","volume":"32","year":"2013","unstructured":"Hu, S.-M.; Zhang, F.-L.; Wang, M; Martin, R. R.; Wang, J. PatchNet: A patch-based image representation for interactive library-driven image editing. ACM Transactions on Graphics Vol. 32, No. 6, Article No. 196, 2013.","journal-title":"ACM Transactions on Graphics"},{"key":"158_CR21","first-page":"5505","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J H Yu","year":"2018","unstructured":"Yu, J. H.; Lin, Z.; Yang, J. M.; Shen, X. H.; Lu, X.; Huang, T. S. Generative image inpainting with contextual attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5505\u20135514, 2018."},{"key":"158_CR22","first-page":"2708","volume-title":"Proceedings of the 32nd Conference on Neural Information Processing Systems","author":"S Hong","year":"2018","unstructured":"Hong, S.; Yan, X.; Huang, T.; Lee, H. Learning hierarchical semantic image manipulation through structured representations. In: Proceedings of the 32nd Conference on Neural Information Processing Systems, 2708\u20132718, 2018."},{"key":"158_CR23","first-page":"10393","volume":"31","author":"D Lee","year":"2018","unstructured":"Lee, D.; Liu, S.; Gu, J.; Liu, M.-Y.; Yang, M.-H.; Kautz, J. Context-aware synthesis and placement of object instances. In: Proceedings of the Advances in Neural Information Processing Systems 31, 10393\u201310403, 2018.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"158_CR24","first-page":"9455","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"CH Lin","year":"2018","unstructured":"Lin, C.H.; Yumer, E.; Wang, O.; Shechtman, E.; Lucey, S. ST-GAN: Spatial transformer generative adversarial networks for image compositing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9455\u20139464, 2018."},{"key":"158_CR25","first-page":"1519","volume-title":"Proceedings of the IEEE Winter Conference on Applications of Computer Vision","author":"F W Tan","year":"2018","unstructured":"Tan, F. W.; Bernier, C.; Cohen, B.; Ordonez, V.; Barnes, C. Where and who? Automatic semantic-aware person composition. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1519\u20131528, 2018."},{"key":"158_CR26","first-page":"6077","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"P Anderson","year":"2018","unstructured":"Anderson, P.; He, X. D.; Buehler, C.; Teney, D.; Johnson, M.; Gould, S.; Zhang, L. Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6077\u20136086, 2018."},{"key":"158_CR27","first-page":"3097","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"D F Xu","year":"2017","unstructured":"Xu, D. F.; Zhu, Y. K.; Choy, C. B.; Fei-Fei, L. Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3097\u20133106, 2017."},{"issue":"1","key":"158_CR28","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R.; Zhu, Y. K.; Groth, O.; Johnson, J.; Hata, K. J.; Kravitz, J.; Chen, S.; Kalantidis, Y.; Li, L.-J.; Shamma, D. A. et al. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision Vol. 123, No. 1, 32\u201373, 2017.","journal-title":"International Journal of Computer Vision"},{"key":"158_CR29","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research Vol. 12, 2825\u20132830, 2011.","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"158_CR30","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K.; Kek\u00e4l\u00e4inen, J. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems Vol. 20, No. 4, 422\u2013446, 2002.","journal-title":"ACM Transactions on Information Systems"},{"key":"158_CR31","unstructured":"Bag-of-words model. Available at https:\/\/en.wikipedia.org\/wiki\/Bag-of-words_model."},{"key":"158_CR32","unstructured":"Yu, F.; Koltun, V. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122, 2015."},{"key":"158_CR33","first-page":"740","volume-title":"Computer Vision \u2014 ECCV 2014. Lecture Notes in Computer Science, Vol. 8693","author":"T Y Lin","year":"2014","unstructured":"Lin, T. Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollar, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision \u2014 ECCV 2014. Lecture Notes in Computer Science, Vol. 8693. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 740\u2013755, 2014."},{"issue":"3","key":"158_CR34","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1007\/s11390-019-1929-5","volume":"34","author":"S H Zhang","year":"2019","unstructured":"Zhang, S. H.; Zhang, S. K.; Liang, Y.; Hall, P. A survey of 3D indoor scene synthesis. Journal of Computer Science and Technology Vol. 34, No. 3, 594\u2013608, 2019.","journal-title":"Journal of Computer Science and Technology"},{"issue":"1","key":"158_CR35","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s41095-017-0102-8","volume":"4","author":"S M Ge","year":"2018","unstructured":"Ge, S. M.; Jin, X.; Ye, Q. T.; Luo, Z.; Li, Q. Image editing by object-aware optimal boundary searching and mixed-domain composition. Computational Visual Media Vol. 4, No. 1, 71\u201382, 2018.","journal-title":"Computational Visual Media"},{"issue":"1","key":"158_CR36","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s41095-016-0066-0","volume":"3","author":"H Todo","year":"2017","unstructured":"Todo, H.; Yamaguchi, Y. Estimating reflectance and shape of objects from a single cartoon-shaded image. Computational Visual Media Vol. 3, No. 1, 21\u201331, 2017.","journal-title":"Computational Visual Media"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41095-020-0158-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897456\/10897464.pdf?arnumber=10897464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:28Z","timestamp":1762367908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-020-0158-8","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2020,3]]},"assertion":[{"value":"24 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}