Abstract
Recently, deep learning-based recommender systems have received increasing attention of researchers and demonstrate excellent results at solving various tasks in various areas. One of the last growing trends is learning the compatibility of items in a set and predicting the next item or several ones by input ones. Fashion compatibility modeling is one of the areas in which this task is being actively researched. Classical solutions are training on existing sets and are learning to recommend items that have been combined with each other before. This severely limits the number of possible combinations. GAN models proved to be the most effective for decreasing the impact of this problem and generating unseen combinations of items, but they also have several limitations. They use a fixed number of input and output items. However, real outfits contain a variable number of items. Also, they use unimodal or multimodal data to generate only visual features. However, this approach is not guaranteed to save content attributes of items during generation. We propose a multimodal transformer-based GAN with cross-modal attention to simultaneously explore visual features and textual attributes. We also propose to represent a set of items as a sequence of items to allow the model to decide how many items should be in the set. Experimenting on FOTOS dataset at the fill-in-the-blank task is showed that our method outperforms such strong baselines as Bi-LSTM-VSE, MGCM, HFGN, and others. Our model has reached 0.878 accuracy versus 0.724 of Bi-LSTM-VSE, 0.822 of MGCM, 0.826 of HFGN.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Han, X., Wu, Z., Jiang, Y.G., Davis, L.S.: Learning fashion compatibility with bidirectional LSTMs. In: MM 2017 - Proceedings of the 2017 ACM Multimedia Conference, July 2017, pp. 1078–1086 (2017). https://doi.org/10.1145/3123266.3123394
Song, X., Feng, F., Liu, J., Li, Z., Nie, L., Ma, J.: NeuroStylist: neural compatibility modeling for clothing matching. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 753–761 (2017). https://doi.org/10.1145/3123266.3123314
Yang, X., Ma, Y., Liao, L., Wang, M., Chua, T.S.: TransNFCM: translation-based neural fashion compatibility modeling. In: 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, December 2018, pp. 403–410 (2018). https://doi.org/10.1609/aaai.v33i01.3301403
Tangseng, P., Yamaguchi, K., Okatani, T.: Recommending outfits from personal closet. In: 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 2275–2279 (2017)
Lu, Z., Hu, Y., Chen, Y., Zeng, B.: Personalized outfit recommendation with learnable anchors. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12722–12731 (2021)
Li, X., Wang, X., He, X., Chen, L., Xiao, J., Chua, T.S.: Hierarchical fashion graph network for personalized outfit recommendation. In: SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, May 2020, pp. 159–168 (2020). https://doi.org/10.1145/3397271.3401080
Lu, Z., Hu, Y., Jiang, Y., Chen, Y., Zeng, B.: Learning binary code for personalized fashion recommendation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2019, pp. 10554–10562 (2019). https://doi.org/10.1109/CVPR.2019.01081
Cui, Z., Li, Z., Wu, S., Zhang, X., Wang, L.: Dressing as a whole: outfit compatibility learning based on node-wise graph neural networks. In: The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, February 2019, pp. 307–317 (2019). https://doi.org/10.1145/3308558.3313444
Cardoso, A., Daolio, F., Vargas, S.: Product characterisation towards personalisation: learning attributes from unstructured data to recommend fashion products. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, March 2018, pp. 80–89 (2018). https://doi.org/10.1145/3219819.3219888
Sagar, D., Garg, J., Kansal, P., Bhalla, S., Shah, R.R., Yu, Y.: PAI-BPR: personalized outfit recommendation scheme with attribute-wise interpretability. In: Proceedings - 2020 IEEE 6th International Conference on Multimedia Big Data, BigMM 2020, August 2020, pp. 221–230 (2020). https://doi.org/10.1109/BigMM50055.2020.00039
Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J.M., He, X.: A simple convolutional generative network for next item recommendation. In: WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining, vol. 19, pp. 582–590 (2018). https://doi.org/10.1145/3289600.3290975
Kumar, S., das Gupta, M.: c+GAN: complementary fashion item recommendation. In: KDD 2019: Workshop on AI for Fashion, June 2019. https://arxiv.org/abs/1906.05596v1. Accessed 21 Jan 2022
Kang, W.C., Fang, C., Wang, Z., McAuley, J.: Visually-aware fashion recommendation and design with generative image models. In: Proceedings - IEEE International Conference on Data Mining, ICDM, November 2017, pp. 207–216 (2017). https://doi.org/10.1109/ICDM.2017.30
Liu, L., Zhang, H., Ji, Y., Jonathan Wu, Q.M.: Toward AI fashion design: an attribute-GAN model for clothing match. Neurocomputing 341, 156–167 (2019). https://doi.org/10.1016/J.NEUCOM.2019.03.011
Liu, J., Song, X., Chen, Z., Ma, J.: MGCM: multi-modal generative compatibility modeling for clothing matching. Neurocomputing 414, 215–224 (2020). https://doi.org/10.1016/J.NEUCOM.2020.06.033
Yu, C., Hu, Y., Chen, Y., Zeng, B.: Personalized fashion design. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 2019, pp. 9045–9054 (2019). https://doi.org/10.1109/ICCV.2019.00914
Hsiao, W.L., Grauman, K.: Creating capsule wardrobes from fashion images. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, December 2017, pp. 7161–7170 (2017). https://doi.org/10.1109/CVPR.2018.00748
Dong, X., Jing, P., Song, X., Xu, X.S., Feng, F., Nie, L.: Personalized capsule wardrobe creation with garment and user modeling. In: MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia, October 2019, pp. 302–310 (2019). https://doi.org/10.1145/3343031.3350905
Zheng, N., Song, X., Niu, Q., Dong, X., Zhan, Y., Nie, L.: Collocation and try-on network: whether an outfit is compatible. In: MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia, October 2021, pp. 309–317 (2021). https://doi.org/10.1145/3474085.3475691
Dong, X., Wu, J., Song, X., Dai, H., Nie, L.: Fashion compatibility modeling through a multi-modal try-on-guided scheme. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, July 2020, pp. 771–780 (2020). https://doi.org/10.1145/3397271.3401047
Vasileva, M.I., Plummer, B.A., Dusad, K., Rajpal, S., Kumar, R., Forsyth, D.: Learning type-aware embeddings for fashion compatibility. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 405–421. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_24
Bettaney, E.M., Hardwick, S.R., Zisimopoulos, O., Chamberlain, B.P.: Fashion outfit generation for e-commerce. In: Dong, Y., Ifrim, G., Mladenić, D., Saunders, C., VanHoecke, S. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12461, pp. 339–354. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67670-4_21
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 5999–6009 (2017). https://arxiv.org/abs/1706.03762v5. Accessed 21 Jan 2022
Cheng, Y., Wang, R., Pan, Z., Feng, R., Zhang, Y.: Look, listen, and attend: co-attention network for self-supervised audio-visual representation learning. In: MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia, vol. 20, pp. 3884–3892 (2020). https://doi.org/10.1145/3394171.3413869
Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. In: 7th International Conference on Learning Representations. ICLR 2019, July 2018. https://arxiv.org/abs/1807.00734v3. Accessed 21 Jan 2022
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, October 2016, pp. 2813–2821 (2016). https://doi.org/10.1109/ICCV.2017.304
Acknowledgements
This research is financially supported by The Russian Science Foundation, Agreement №17-71-30029 with co-financing of Bank Saint Petersburg.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Volokha, V., Bochenina, K. (2022). Content-Aware Generative Model for Multi-item Outfit Recommendation. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13350. Springer, Cham. https://doi.org/10.1007/978-3-031-08751-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-08751-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08750-9
Online ISBN: 978-3-031-08751-6
eBook Packages: Computer ScienceComputer Science (R0)