Abstract
In many advertising areas, banners are often generated with different display sizes, so designers have to make huge efforts to retarget their designs to each size. Automating such retargeting process can greatly save time for designers and let them put creativity on new ads. This paper proposes a hierarchical reinforcement learning-based (HRL-based) method and a variational autoencoder-based (VAE-based) method by treating the automated banner retargeting problem as a layout retargeting task. The HRL and VAE models are trained separately to learn the scaling and positioning policy of the design elements from an original (base) layout. Hence, the proposed method can generate appropriate layouts for different target banner sizes. Meanwhile, evaluation metrics are proposed to assess the quality of generated layouts and are also reward conditions during the training process. To evaluate performances of the two models, SOTA methods such as Non-linear Inverse Optimization (NIO), Triangle Interpolation (TI), and Layout GAN (LGAN) are implemented and compared. Experimental results show that both HRL- and VAE-based methods retarget design layouts effectively, and the VAE model achieves better performance than the HRL model.
Similar content being viewed by others
References
Baluja S (2006) Browsing on small screens: recasting web-page segmentation into an efficient machine learning framework. In: Proceedings of the 15th international conference on World Wide Web. ACM, pp 33–42
Cao Y, Lau R W H, Chan A B (2014) Look over here: attention-directing composition of manga elements. ACM Trans Graph 33(4):94:1–94:11
Damera-Venkata N, Bento J, O’Brien-Strain E (2011) Probabilistic document model for automated document composition. In: Proceedings of the 11th ACM symposium on Document engineering. ACM, pp 3–12
Dietterich T G (2000) Hierarchical reinforcement learning with the maxq value function decomposition. J Artif Intell Res 13:227–303
Doersch C (2016) Tutorial on variational autoencoders. arXiv:1606.05908
Earl D J, Deem M W (2005) Parallel tempering: theory, applications, and new perspectives. Phys Chem Chem Phys 7(23):3910–3916
Hester T, Vecerik M, Pietquin, et al. (2018) Deep q-learning from demonstrations. In: Thirty-Second AAAI conference on artificial intelligence
Hirashima Y (2009) A q-learning system for container marshalling with group-based learning model at container yard terminals. In: Proceedings of the international multiconference of engineers and computer scientists 2009 (IMECS 2009), vol 1
Hu H, Zhang C, Liang Y (2021) A study on the automatic generation of banner layouts. Comput Electr Eng 93:107269
Hua X-S (2018) Challenges and practices of large scale visual intelligence in the real-world. In: Proceedings of the 26th ACM international conference on multimedia, MM ’18. ACM, New York, pp 364–364
Kingma D P, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Kingma D P, Welling M (2013) Auto-encoding variational bayes. arXiv:1312.6114
Kumar R, Talton J O, Ahmad S, Klemmer S R (2011) Bricolage: example-based retargeting for web design. In: Proceedings of the SIGCHI conference on human factors in computing systems. ACM, pp 2197–2206
Li J, Yang J, Hertzmann A, Zhang J, Xu T (2019) Layoutgan: generating graphic layouts with wireframe discriminators. arXiv:1901.06767
Li J, Yang J, Zhang J, Liu C, Wang C, Xu T (2020) Attribute-conditioned layout gan for automatic graphic design. IEEE Trans Vis Comput Graph
Liu C K, Hertzmann A, Popović Z (2005) Learning physics-based motion style with nonlinear inverse optimization. ACM Trans Graph (TOG) 24 (3):1071–1081
Liu L, Chen R, Wolf L, Cohen-Or D (2010) Optimizing photo composition. In: Computer graphics forum, vol 29. Wiley Online Library, pp 469–478
Maheshwari P, Bansal N, Dwivedi S, Kumar R, Manerikar P, Srinivasan B V (2019) Exemplar based experience transfer. In: Proceedings of the 24th international conference on intelligent user interfaces. ACM, pp 673–680
Mitchell T M (1999) Machine learning and data mining. Commun ACM 42(11):30–36
Moon T K (1996) The expectation-maximization algorithm. IEEE Signal Process Mag 13(6):47–60
Nowozin S, Lampert C H (2011) Structured learning and prediction in computer vision, vol 6 (3–4). Now Publishers Inc
O’Donovan P (2015) Learning design: aesthetic models for color, layout, and typography. Ph.D. Thesis. University of Toronto (Canada)
ODonovan P, Agarwala A, Hertzmann A (August 2014) Learning layouts for single-pagegraphic designs. IEEE Trans Vis Comput Graph 20(8):1200–1213
O’Donovan P, Agarwala A, Hertzmann A (2015) Designscape: design with interactive layout suggestions. In: Proceedings of the 33rd annual ACM conference on human factors in computing systems, CHI ’15. ACM, New York, pp 1221–1224
Osa T, Tangkaratt V, Sugiyama M (2019) Hierarchical reinforcement learning via advantage-weighted information maximization. arXiv:1901.01365
Pang X, Cao Y, Lau R W H, Chan A B (2016) Directing user attention via visual flow on web designs. ACM Trans Graph 35(6):240:1–240:11
Papernot N, McDaniel P, Goodfellow I, Jha S, Celik Z B, Swami A (2017) Practical black-box attacks against machine learning. In: Proceedings of the 2017 ACM on Asia conference on computer and communications security, pp 506–519
Patil A G, Ben-Eliezer O, Perel O, Averbuch-Elor H (2019) Read: recursive autoencoders for document layout generation. arXiv:1909.00302
Sandhaus P, Rabbath M, Boll S (2011) Employing aesthetic principles for automatic photo book layout. In: International conference on multimedia modeling. Springer, pp 84–95
Sutton R S, Precup D, Singh S (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1-2):181–211
Tarkesh H, Atighehchian A, Nookabadi A S (2009) Facility layout design using virtual multi-agent system. J Intell Manuf 20(4):347
Todi K, Weir D, Oulasvirta A (2016) Sketchplore: Sketch and explore with a layout optimiser. In: Proceedings of the 2016 ACM conference on designing interactive systems. ACM, pp 543–555
Vempati S, Malayil K T, et al. (2019) Enabling hyper-personalisation: automated ad creative generation and ranking for fashion e-commerce. arXiv:1908.10139
Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8 (3–4):279–292
White CC (2001) Markov decision processes. Springer
Yang X, Mei T, Xu Y-Q, Rui Y, Li S (2016) Automatic generation of visual-textual presentation layout. ACM Trans Multimed Comput Commun Applic (TOMM) 12(2):33
Zhang Y, Hu K, Ren P, Yang C, Xu W, Hua X-S (2017) Layout style modeling for automating banner design. In: Proceedings of the on thematic workshops of ACM multimedia 2017. ACM, pp 451–459
Zheng X, Qiao X, Cao Y, Lau Rynson WH (2019) Content-aware generative modeling of graphic design layouts. ACM Trans Graph (TOG) 38(4):133
Zhu C, Byrd R H, Lu P, Nocedal J (1997) Algorithm 778: L-bfgs-b: fortran subroutines for large-scale bound-constrained optimization. ACM Trans Math Softw (TOMS) 23(4):550–560
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Hao Hu and Chao Zhang contributed equally to this work.
Rights and permissions
About this article
Cite this article
Hu, H., Zhang, C. & Liang, Y. Banner layout retargeting with hierarchical reinforcement learning and variational autoencoder. Multimed Tools Appl 81, 34417–34438 (2022). https://doi.org/10.1007/s11042-022-13325-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13325-w