Filters








4,368 Hits in 4.8 sec

Discovering Style Trends through Deep Visually Aware Latent Item Embeddings [article]

Murium Iqbal, Adair Kovac, Kamelia Aryafar
2018 arXiv   pre-print
In this paper, we explore Latent Dirichlet Allocation (LDA) and Polylingual Latent Dirichlet Allocation (PolyLDA), as a means to discover trending styles in Overstock from deep visual semantic features  ...  We then train LDA over these documents to discover the latent style in the images.  ...  Discovering the underlying style trends can help with both discovery of relevant items and inspirational finds.  ... 
arXiv:1804.08704v1 fatcat:eimohosc25gdvns6zdurpc5ady

Discovering Style Trends Through Deep Visually Aware Latent Item Embeddings

Murium Iqbal, Adair Kovac, Kamelia Aryafar
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we explore Latent Dirichlet Allocation (LDA) [1] and Polylingual Latent Dirichlet Allocation (PolyLDA) [6] , as a means to discover trending styles in Overstock 1 from deep visual semantic  ...  We then train LDA over these documents to discover the latent style in the images.  ...  Discovering the underlying style trends can help with both discovery of relevant items and inspirational finds.  ... 
doi:10.1109/cvprw.2018.00253 dblp:conf/cvpr/IqbalKA18 fatcat:ilf3oiaxrnc7vlfjifi2yaiufe

Ups and Downs

Ruining He, Julian McAuley
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
To uncover the complex and evolving visual factors that people consider when evaluating products, our method combines high-level visual features extracted from a deep convolutional neural network, users  ...  fashion trends across the 11-year span of our dataset.  ...  factors of user u, item i at time t (K ×1) fi Deep CNN visual features of item i (F × 1) E K × F embedding matrix E(t) K × F embedding matrix at time t β visual bias vector (visual bias = β, fi ) β(t)  ... 
doi:10.1145/2872427.2883037 dblp:conf/www/HeM16 fatcat:7rfv2qfmkjcltiybs7l3xybu74

Fashionista: A Fashion-aware Graphical System for Exploring Visually Similar Items [article]

Ruining He, Chunbin Lin, Julian McAuley
2016 arXiv   pre-print
that are not only visually similar to a given query, but which are also fashionable, as determined by visually-aware recommendation approaches.  ...  Methodologically, Fashionista learns a low-dimensional visual space as well as the evolution of fashion trends from large corpora of binary feedback data such as purchase histories of Women's Clothing  ...  Our model produces a visually-aware preference predictor that extends standard Matrix Factorization by modeling visual dimensions and non-visual (i.e., latent) dimensions simultaneously.  ... 
arXiv:1604.00071v1 fatcat:22umehggkvburaeuvvngjqsw3i

Fashionista

Ruining He, Chunbin Lin, Julian McAuley
2016 Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion  
that are not only visually similar to a given query, but which are also fashionable, as determined by visually-aware recommendation approaches.  ...  Methodologically, Fashionista learns a low-dimensional visual space as well as the evolution of fashion trends from large corpora of binary feedback data such as purchase histories of Women's Clothing  ...  Our model produces a visually-aware preference predictor that extends standard Matrix Factorization by modeling visual dimensions and non-visual (i.e., latent) dimensions simultaneously.  ... 
doi:10.1145/2872518.2890534 dblp:conf/www/HeLM16 fatcat:xtm4hdgwejgvdkp27z2ocwc75i

A Multimodal Recommender System for Large-scale Assortment Generation in E-commerce [article]

Murium Iqbal, Adair Kovac, Kamelia Aryafar
2018 arXiv   pre-print
Our experimental results show that complimentary style is best discovered over product sets when both visual and textual data are incorporated.  ...  We review the production pipeline for surfacing these visually-aware recommender systems and compare them through offline validations and large-scale online A/B tests on Overstock.  ...  To discover visually-aware trends, we use these documents with Latent Dirichlet Allocation (LDA) [3] .  ... 
arXiv:1806.11226v1 fatcat:2cnak27q7ndnjirvhso5m5cqpa

Mining Latent Structures for Multimedia Recommendation [article]

Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Shuhui Wang, Liang Wang
2021 arXiv   pre-print
Specifically, only collaborative item-item relationships are implicitly modeled through high-order item-user-item relations.  ...  latent item graphs.  ...  DeepStyle [23] disentangled category information from visual representations for learning style features of items and sensing preferences of users.  ... 
arXiv:2104.09036v1 fatcat:k25lruw2yjab7mumr6ew5eok44

Survey for Trust-aware Recommender Systems: A Deep Learning Perspective [article]

Manqing Dong, Feng Yuan, Lina Yao, Xianzhi Wang, Xiwei Xu, Liming Zhu
2020 arXiv   pre-print
We focus on the work based on deep learning techniques, an emerging area in the recommendation research.  ...  This survey provides a systemic summary of three categories of trust-aware recommender systems: social-aware recommender systems that leverage users' social relationships; robust recommender systems that  ...  The video semantic embedding includes visual features and textual features, which are learned by pre-trained deep models.  ... 
arXiv:2004.03774v2 fatcat:q7mehir7hbbzpemw3q5fkby5ty

Learning Context-Aware Outfit Recommendation

Ahed Abugabah, Xiaochun Cheng, Jianfeng Wang
2020 Symmetry  
The key to fashion recommendation is to capture the semantics behind customers' fit feedback as well as fashion visual style.  ...  Since the style of clothing contains rich visual information such as color and shape, and the shape has symmetrical structure and asymmetrical structure, and users with different backgrounds have different  ...  We compose a representation for the user-item pair by combining the item embedding and their visual features.  ... 
doi:10.3390/sym12060873 fatcat:hmblbya7hzckhgsijyepn4nvra

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer, pose transformation, and physical simulation,  ...  comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes landmark detection, fashion parsing, and item  ...  [150] proposed to regress visual query to a latent space derived through matrix factorization for the known subjects and ratings.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation [article]

Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, Liang Wang
2022 arXiv   pre-print
discover candidate items.  ...  Based on the learned modality-aware latent item relationships, we perform graph convolutions that explicitly inject item affinities to modality-aware item representations.  ...  Different from existing content-aware methods, we discover the latent item relationships underlying multimodal features instead of directly using them as side information.  ... 
arXiv:2111.00678v2 fatcat:boqsb2twpjd45gbtol5tpkirqa

Trends in content-based recommendation

Pasquale Lops, Dietmar Jannach, Cataldo Musto, Toine Bogers, Marijn Koolen
2019 User modeling and user-adapted interaction  
The authors combine a variety of information sources-including item metadata as well as low-level visual features that are extracted through a deep neural network-and show the advantage of their combined  ...  Deep learning Deep Learning (DL) approaches offer a flexible framework to discover existing structures in item and user data, including external knowledge resources (Musto et al. 2018 ) and non-textual  ... 
doi:10.1007/s11257-019-09231-w fatcat:ftunw4mq5vgojifno3yqklfwbq

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation [article]

Le Wu, Xiangnan He, Xiang Wang, Kun Zhang, Meng Wang
2021 arXiv   pre-print
Influenced by the great success of deep learning in computer vision and language understanding, research in recommendation has shifted to inventing new recommender models based on neural networks.  ...  interaction data; 2) content enriched recommendation, which additionally utilizes the side information associated with users and items, like user profile and item knowledge graph; and 3) temporal/sequential  ...  FM has been extended to field-aware FM by expanding each feature with several Tree enhanced embedding for attentive cross feature aggregation TEM [11] latent embeddings based on the field aware property  ... 
arXiv:2104.13030v3 fatcat:7bzwaxcarrgbhe36teik2rhl6e

Research Commentary on Recommendations with Side Information: A Survey and Research Directions [article]

Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke
2019 arXiv   pre-print
One involves the different methodologies of recommendation: the memory-based methods, latent factor, representation learning, and deep learning models.  ...  To address these issues, a great number of recommendation algorithms have been proposed to leverage side information of users or items (e.g., social network and item category), demonstrating a high degree  ...  It learns item style representations by subtracting the corresponding item category representations from the visual features generated via CNN.  ... 
arXiv:1909.12807v2 fatcat:2nj4crzcd5attidhd3kneszmki

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

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
For each task, a time chart is provided to analyze the progress through the years.  ...  AUC FITB, Item, Type-aware embedding 22 Sun [472] Siamese CNN, Probabilistic matrix factorization Top/Bottom, Social circle, Style consistency 23 Z.  ...  Yang [511] Deep relational embedding Propa., Graph, 73.1% mR@5 Outfit, Personalized 75 X.  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i
« Previous Showing results 1 — 15 out of 4,368 results