978 Hits in 4.0 sec

Image-Based Recommendations on Styles and Substitutes

Julian McAuley, Christopher Targett, Qinfeng Shi, Anton van den Hengel
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
Our approach is not based on fine-grained modeling of user annotations but rather on capturing the largest dataset possible and developing a scalable method for uncovering human notions of the visual relationships  ...  Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance.  ...  [40] capture a notion of visual style when parsing clothing, but do so by retrieving visually similar items from a database. This idea was extended by Kiapour et al.  ... 
doi:10.1145/2766462.2767755 dblp:conf/sigir/McAuleyTSH15 fatcat:z5xegwekdvhm5au6my6i64lfzq

Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences

Andreas Veit, Balazs Kovacs, Sean Bell, Julian McAuley, Kavita Bala, Serge Belongie
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
To answer these types of questions, one has to go beyond learning visual similarity and learn a visual notion of compatibility across categories.  ...  Our results indicate that the proposed framework is capable of learning semantic information about visual style and is able to generate outfits of clothes, with items from different categories, that go  ...  Many of the relationships in the co-purchase graph are not based on visual similarity, but on an implicit human judgment of compatibility.  ... 
doi:10.1109/iccv.2015.527 dblp:conf/iccv/VeitKBMBB15 fatcat:wjam2yovg5fupj5j3niejoxdfe

Image-based Recommendations on Styles and Substitutes [article]

Julian McAuley, Christopher Targett, Qinfeng Shi, Anton van den Hengel
2015 arXiv   pre-print
Our approach is not based on fine-grained modeling of user annotations but rather on capturing the largest dataset possible and developing a scalable method for uncovering human notions of the visual relationships  ...  Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance.  ...  outfits to predicting which books will be co-purchased based on their cover art.  ... 
arXiv:1506.04757v1 fatcat:uzj57pu6efdkrodd7n52t73npy

E-commerce Sites with Outfit Composition using Deep Learning Method

Our approach has first implemented a system of encoding visual characteristics with the help of deep convolution network for complicated contents because it is not possible to list or to label every attribute  ...  The fashion industry has developed in many fields and its growth is making an enormous promote in article of clothing company and e-commerce entity.  ...  The proposed method used similarity based retrieval technique [5] . Experimental results obtained were beneficial in finding the scenario.  ... 
doi:10.35940/ijitee.j1146.0881019 fatcat:npb5t64nrvgtti2rj7aenlqozi

Smart Fashion: A Review of AI Applications in the Fashion Apparel Industry [article]

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
The fashion industry is on the verge of an unprecedented change.  ...  Such structured task-based multi-label classification of fashion research articles provides researchers with explicit research directions and facilitates their access to the related studies, improving  ...  They can be content-based recommender systems that retrieve similar articles based on visual features of images or semantic attributes.  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

Modeling Visual Compatibility through Hierarchical Mid-level Elements [article]

Jose Oramas, Tinne Tuytelaars
2016 arXiv   pre-print
Experiments on the massive Amazon dataset show the strength of our method at describing object classes and the characteristics that drive the compatibility between them.  ...  At the top-level, the proposed method discovers patterns of co-occurring activations of base-level elements that define visual compatibility between pairs of object classes.  ...  This can be retrieved effectively via an inverted file index. As a result, we obtain a set of base-level visual elements V c which describe different visual characteristics of instances of class c.  ... 
arXiv:1604.00036v1 fatcat:akzscqo2pzbodi3gjk32j7ds5i

Choosing the Right Model: A Comprehensive Analysis of Outfit Recommendation Systems

Gursimran Kaur, Hrithik Malhotra, Tanmaya Gupta
2021 International Journal of Computer Applications  
There is an introduction to the the three types of Recommendation Systems that are present: Content based, Collaborative Filtering and Hybrid Models, and a discussion on their pros and cons.  ...  The need for presenting Outfit recommendation models and the importance of their accuracy is presented. Finally, a comprehensive survey of 4 types of Fashion Recommendation Systems: 1.)  ...  A retrieval system using the colour and attribute information shows improved clothing retrieval results and solves the cross-scenario retrieval problem of similar items of clothing.  ... 
doi:10.5120/ijca2021921413 fatcat:ze6npdmhzba7zky5jva57cvyse

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
Fashion is the way we present ourselves to the world and has become one of the world's largest industries.  ...  pose transformation, and physical simulation, and (4) Fashion recommendation comprises fashion compatibility, outfit matching, and hairstyle suggestion.  ...  The visually similar items were retrieved by summing up the overlap similarities. Notably, [86, 122, 190] are based on hand-crafted features.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

Interpretable Partitioned Embedding for Customized Fashion Outfit Composition [article]

Zunlei Feng, Zhenyun Yu, Yezhou Yang, Yongcheng Jing, Junxiao Jiang, Mingli Song
2018 arXiv   pre-print
However, the unexplainable characteristic makes such deep learning based approach cannot meet the the designer, businesses and consumers' urge to comprehend the importance of different attributes in an  ...  To realize interpretable and customized fashion outfit compositions, we propose a partitioned embedding network to learn interpretable representations from clothing items.  ...  There have been a number of research studies on clothes retrieval and recommendation [6, 8, 10, 11, 16, 27] , clothing category classification [3, 13, 17, 23, 28] , attribute prediction [1, 2, 4, 29  ... 
arXiv:1806.04845v4 fatcat:j5rize2o6bgcphq6ryp2hs3xoy

Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space [article]

Imke Grabe, Jichen Zhu, Manex Agirrezabal
2022 arXiv   pre-print
A Gaussian mixture model is applied to identify fashion styles based on the higher-layer representations of outfits in a clothing-specific attribute prediction model.  ...  Over generations, a genetic algorithm optimizes a population of designs to increase their probability of belonging to one of the Gaussian mixture components or styles.  ...  Hence, an embedding is retrieved for one image per outfit in the dataset.  ... 
arXiv:2204.00592v2 fatcat:bmoxmyzseva4jperyii3eegrve

Self-supervised Visual Attribute Learning for Fashion Compatibility [article]

Donghyun Kim, Kuniaki Saito, Samarth Mishra, Stan Sclaroff, Kate Saenko, Bryan A Plummer
2021 arXiv   pre-print
We evaluate our approach on fashion compatibility using Polyvore Outfits and In-Shop Clothing Retrieval using Deepfashion, improving upon prior SSL methods by 9.5-16%, and even outperforming some supervised  ...  approaches on Polyvore Outfits despite using no labels.  ...  Performance is measured based on how often the choice was correct. Fashion Retrieval. We also explore the fashion retrieval task.  ... 
arXiv:2008.00348v2 fatcat:n6tpfsjkujcdlmiltmgdvgccge

What Dress Fits Me Best?

Shintami Chusnul Hidayati, Cheng-Chun Hsu, Yu-Ting Chang, Kai-Lung Hua, Jianlong Fu, Wen-Huang Cheng
2018 2018 ACM Multimedia Conference on Multimedia Conference - MM '18  
Clothing is an integral part of life. Also, it is always an uneasy task for people to make decisions on what to wear.  ...  ., hourglass, rectangle, round and inverted triangle) and selecting the types of clothes that will accentuate the body's good features.  ...  style clusters that group visually similar clothing images in the same cluster.  ... 
doi:10.1145/3240508.3240546 dblp:conf/mm/HidayatiHCHFC18 fatcat:kec6tusv45bddjenxsunfcpwvu

From Culture to Clothing: Discovering the World Events Behind A Century of Fashion Images [article]

Wei-Lin Hsiao, Kristen Grauman
2021 arXiv   pre-print
Furthermore, on two image datasets we apply our model to improve the concrete vision tasks of visual style forecasting and photo timestamping.  ...  choice of clothing.  ...  We also thank the authors of [5] for kindly sharing their data and code with us.  ... 
arXiv:2102.01690v2 fatcat:kwttluwjnfgexelqv3wftidjxm

PAI-BPR: Personalized Outfit Recommendation Scheme with Attribute-wise Interpretability [article]

Dikshant Sagar, Jatin Garg, Prarthana Kansal, Sejal Bhalla, Rajiv Ratn Shah, Yi Yu
2020 arXiv   pre-print
Fashion is an important part of human experience. Events such as interviews, meetings, marriages, etc. are often based on clothing styles.  ...  Thus, it necessitates an outfit compatibility model to aid people in clothing recommendation.  ...  [8] proposed a general framework to extract visual features which model the human visual preference for a given pair of objects based on the Amazon real-world co-purchase dataset while Song et al.  ... 
arXiv:2008.01780v1 fatcat:4mn7pronyfcrdpivngbsyax5d4

Fashion Recommendation Systems, Models and Methods: A Review

Samit Chakraborty, Md. Saiful Hoque, Naimur Rahman Jeem, Manik Chandra Biswas, Deepayan Bardhan, Edgar Lobaton
2021 Informatics  
Despite its huge potential, the number of academic articles on this topic is limited.  ...  Image-based fashion recommendation systems (FRSs) have attracted a huge amount of attention from fast fashion retailers as they provide a personalized shopping experience to consumers.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/informatics8030049 fatcat:2djpad5hwraqnb6v24pg4b4a5m
« Previous Showing results 1 — 15 out of 978 results