Similar articles

Abstract: multimedia content is an integral part of alibaba‘s business ecosystem and is in great demand. The production of multimedia content usually requires high technology and much money. With the rapid development of artificial intelligence (AI) technology in recent years, to meet the design requirements of multimedia content, many AI auxiliary tools for the production of multimedia content have emerged and become more and more widely used in alibaba‘s business ecology. Related applications include mainly auxiliary design, graphic design, video generation, and page production. In this report, a general pipeline of the AI auxiliary tools is introduced. Four representative tools applied in the alibaba Group are presented for the applications mentioned above. The value brought by multimedia content design combined with AI technology has been well verified in business through these tools. This reflects the great role played by AI technology in promoting the production of multimedia content. The application prospects of the combination of multimedia content design and AI are also indicated.

智能多媒体内容设计在阿里巴巴的应用

[1]Azadi S, Fisher M, Kim VG, et al., 2018. Multi-content GAN for few-shot font style transfer. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.7564-7573.

[2]Bradski G, Kaehler A, 2008. Learning OpenCV: Computer Vision with the OpenCV Library. O‘Reilly Media, Inc.

[3]Bretan M, Weinberg G, Heck L, 2016. A unit selection methodology for music generation using deep neural networks. https://arxiv.org/abs/1612.03789

[4]Cao Z, Simon T, Wei SE, et al., 2017. Realtime multi-person 2D pose estimation using part affinity fields. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.7291-7299.

[5]Chen LC, Zhu YK, Papandreou G, et al., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. https://arxiv.org/abs/1802.02611

[6]Chollet F, 2017. Xception: deep learning with depthwise separable convolutions. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.1251-1258.

[7]Goodfellow IJ, Pouget-Abadie J, Mirza M, et al., 2014. Generative adversarial nets. Proc 27^th Int Conf on Neural Information Processing Systems, p.2672-2680.

[8]He KM, Zhang XY, Ren SQ, et al., 2016. Deep residual learning for image recognition. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.770-778.

[9]He KM, Gkioxari G, Doll‘ar P, et al., 2017. Mask R-CNN. Proc IEEE Int Conf on Computer Vision, p.2961-2969.

[10]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.

[11]Huang X, Peng YX, 2019. TPCKT: two-level progressive cross-media knowledge transfer. IEEE Trans Multim, 21(11):2850-2862.

[12]Kim KS, Zhang DN, Kang MC, et al., 2013. Improved simple linear iterative clustering superpixels. IEEE Int Symp on Consumer Electronics, p.259-260.

[13]Levin A, Lischinski D, Weiss Y, 2007. A closed-form solution to natural image matting. IEEE Trans Patt Anal Mach Intell, 30(2):228-242.

[14]Lin TY, Doll‘ar P, Girshick R, et al., 2017. Feature pyramid networks for object detection. Proc Conf on Computer Vision and Pattern Recognition, p.2117-2125.

[15]Ngiam J, Khosla A, Kim M, et al., 2011. Multimodal deep learning. Proc 28^th Int Conf on Machine Learning, p.689-696.

[16]Papandreou G, Zhu T, Chen LC, et al., 2018. PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. https://arxiv.org/abs/1803.08225

[17]Peng YX, Zhu WW, Zhao Y, et al., 2017. Cross-media analysis and reasoning: advances and directions. Front Inform Technol Electron Eng, 18(1):44-57.

[18]Peng YX, Huang X, Zhao YZ, 2018. An overview of cross-media retrieval: concepts, methodologies, benchmarks, and challenges. IEEE Trans Circ Syst Video Technol, 28(9):2372-2385.

[19]Peng YX, Qi JW, Huang X, 2019. Current research status and prospects on multimedia content understanding. J Comput Res Devel, 56(1):187-212 (in Chinese).

[20]Ren SQ, He KM, Girshick R, et al., 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Patt Anal Mach Intell, 39(6):1137-1149.

[21]Ristani E, Tomasi C, 2018. Features for multi-target multi-camera tracking and re-identification. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.6036-6046.

[22]Rother C, Kolmogorov V, Blake A, 2004. “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans Graph, 23(3):309-314.

[23]Simonyan K, Zisserman A, 2015. Very deep convolutional networks for large-scale image recognition. https://arxiv.org/abs/1409.1556

[24]Song SJ, Zhang W, Liu JY, et al., 2019. Unsupervised person image generation with semantic parsing transformation. https://arxiv.org/abs/1904.03379

[25]Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Advances in Neural Information Processing Systems, p.5998-6008.

[26]Xia FT, Wang P, Chen XJ, et al., 2017. Joint multi-person pose estimation and semantic part segmentation. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.6769-6778.

[27]Zhang SF, Zhu XY, Lei Z, et al., 2017. S³FD: single shot scale-invariant face detector. Proc IEEE Int Conf on Computer Vision, p.192-201.

[28]Zhou BL, Khosla A, Lapedriza A, et al., 2016. Learning deep features for discriminative localization. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.2921-2929.

[29]Zhu JY, Park T, Isola P, et al., 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. Proc IEEE Int Conf on Computer Vision, p.2223-2232.