Filters








57,487 Hits in 2.6 sec

Image-based Recommendations on Styles and Substitutes [article]

Julian McAuley, Christopher Targett, Qinfeng Shi, Anton van den Hengel
2015 arXiv   pre-print
We cast this as a network inference problem defined on graphs of related images, and provide a large-scale dataset for the training and evaluation of the same.  ...  The system we develop is capable of recommending which clothes and accessories will go well together (and which will not), amongst a host of other applications.  ...  This research was supported by the Data 2 Decisions Cooperative Research Centre, and the Australian Research Council Discovery Projects funding scheme DP140102270.  ... 
arXiv:1506.04757v1 fatcat:uzj57pu6efdkrodd7n52t73npy

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  
We cast this as a network inference problem defined on graphs of related images, and provide a large-scale dataset for the training and evaluation of the same.  ...  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  ...  A visual dataset of styles and substitutes We have developed a dataset suitable for the purposes described above based on the Amazon web store.  ... 
doi:10.1145/2766462.2767755 dblp:conf/sigir/McAuleyTSH15 fatcat:z5xegwekdvhm5au6my6i64lfzq

Fashionista

Ruining He, Chunbin Lin, Julian McAuley
2016 Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion  
However, existing systems like Amazon and eBay still rely mainly on keyword search and recommending loosely consistent items (e.g. based on co-purchasing or browsing data), without an interface that makes  ...  In this paper, we attempt to fill this gap by designing and implementing an image-based query system, called Fashionista, which provides a graphical interface to help users efficiently explore those items  ...  There are also image search engines like Google Images that are either based on keywords or image similarity comparison. Such systems differ from ours in two key ways.  ... 
doi:10.1145/2872518.2890534 dblp:conf/www/HeLM16 fatcat:xtm4hdgwejgvdkp27z2ocwc75i

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

Ruining He, Chunbin Lin, Julian McAuley
2016 arXiv   pre-print
However, existing systems like Amazon and eBay still rely mainly on keyword search and recommending loosely consistent items (e.g. based on co-purchasing or browsing data), without an interface that makes  ...  In this paper, we attempt to fill this gap by designing and implementing an image-based query system, called Fashionista, which provides a graphical interface to help users efficiently explore those items  ...  There are also image search engines like Google Images that are either based on keywords or image similarity comparison. Such systems differ from ours in two key ways.  ... 
arXiv:1604.00071v1 fatcat:22umehggkvburaeuvvngjqsw3i

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

Murium Iqbal, Adair Kovac, Kamelia Aryafar
2018 arXiv   pre-print
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.  ...  The first system aims to maximize the visual-based style compatibility of the entire selection by making use of transfer learning and topic modeling.  ...  built on text-based attributes and visual words.  ... 
arXiv:1806.11226v1 fatcat:2cnak27q7ndnjirvhso5m5cqpa

Style-compatible Object Recommendation for Multi-room Indoor Scene Synthesis [article]

Yu He, Yun Cai, Yuan-Chen Guo, Zheng-Ning Liu, Shao-Kui Zhang, Song-Hai Zhang, Hong-Bo Fu, Sheng-Yong Chen
2020 arXiv   pre-print
Current state-of-the-art object selection approaches are based on convolutional neural networks (CNNs) and can produce realistic scenes for a single room.  ...  To address this issue, we treat the object selection problem as combinatorial optimization based on a Labeled LDA (L-LDA) model.  ...  aesthetic. en, we automatically assign a style template image selected from a collections of style templates for each room based on the given image, and extract 5-color pale e for them as style guidance  ... 
arXiv:2003.04187v2 fatcat:zcfq73r4dvgmpdml3kclahexdq

Apparel-based deep learning system design for apparel style recommendation

Congying Guan, Shengfeng Qin, Yang Long
2019 International Journal of Clothing Science and Technology  
) the new concept of apparel recommendation based on style meanings is technically applicable.  ...  images, and the other is to further predict apparel MEANINGs based on predicted ATTRIBUTEs.  ...  The recommendations are based on style genres and body shapes.  ... 
doi:10.1108/ijcst-02-2018-0019 fatcat:jcqgsnghfrddrkteuybnfryhfi

Integrating text with video and 3D graphics

Jacek Jankowski, Krystian Samp, Izabela Irzynska, Marek Jozwowicz, Stefan Decker
2010 Proceedings of the 28th international conference on Human factors in computing systems - CHI '10  
(video and 3D) on text readability.  ...  This paper presents an investigation into the effects of varying (a) text drawing style (plain, billboard, Anti-Interference, shadow), (b) image polarity (positive and negative), and (c) background style  ...  SFI/08/CE/I1380 and Enterprise Ireland under Grant No. REI1004.  ... 
doi:10.1145/1753326.1753524 dblp:conf/chi/JankowskiSIJD10 fatcat:plhtdsi2njcmrclzojy6qhxuqm

Learning Context-Aware Outfit Recommendation

Ahed Abugabah, Xiaochun Cheng, Jianfeng Wang
2020 Symmetry  
Specifically, the proposed method is based on scene images to learn the compatibility from fashion or interior design images.  ...  The key to fashion recommendation is to capture the semantics behind customers' fit feedback as well as fashion visual style.  ...  Most the previous studies were based on the extraction of visual features [2] of clothing products, i.e., by determining the complementary or substitutional relationship of clothing from image features  ... 
doi:10.3390/sym12060873 fatcat:hmblbya7hzckhgsijyepn4nvra

Page 13 of SRELS Journal of Information Management Vol. 32, Issue 1 [page]

1995 SRELS Journal of Information Management  
Character Accuracy Ratio The accuracy ratio with regard to character substitutions and rejections based on the number of scanned characters. a) Substitutions and rejections : The ratio of character substitutions  ...  Number of Fonts resident : The maximum number of standard and optional type styles that are recognised by the unit.  ... 

PCI Matrix Based Image Reconstruction from Compressively Sensed Data

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Third, a substitution staggered L-Pyramid swell decay procedure is accommodated severable swell execution on pictures those outcomes in enhanced remaking execution.  ...  Contrasted and the CS-based recreation misuse typical swells with Gaussian detecting network and with existing swell decay system, the arranged approach gives snappier and higher picture reproduction in  ...  PCI Matrix Based Image Reconstruction from Compressively Sensed Data B. Mounika, B.  ... 
doi:10.35940/ijitee.i1142.0789s219 fatcat:j32v3kdu2jcjzbdrijax4dzvtq

A Review on Outfit Fashion Recommendation System

Bhagyshree Pravin Bhure, Pratiksha Tulshiram Bansod, Monali Shivram Amgaokar, Savita Pralhad Lodiwale, Anjali Pravin Orkey, Ashish Mohod
2021 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
Clients and sellers benefit from such recommendations. On the one hand, customers can make smarter shopping decisions and discover new articles of clothes that complement one other.  ...  Complex outfit recommendations, on the other hand, assist vendors in selling more products, which has an impact on their business.  ...  And provided Image-based recommendations on styles and substitutes. Hu et al. [2] conducted a preliminary investigation into personalised outfit recommendation.  ... 
doi:10.32628/cseit217368 fatcat:3dtsus7ai5eahgv3npmetw6m2y

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

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
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  ...  The fashion industry is on the verge of an unprecedented change.  ...  Recommenders Style recommenders do not focus on one item but on all clothing items in an image as a style and fashion instead.  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

Towards Syriac Digital Corpora: Evaluation of Tesseract 4.0 for Syriac OCR

Emily Chesley, Jillian Marcantonio, Abigail Pearson
2019 Hugoye: Journal of Syriac Studies  
In all type styles, human revision of the OCRed text is recommended when scholars desire an exact, error-free corpus.  ...  Three popular print types (S14, W64, and E22) representing the Syriac type styles Estrangela, Serto, and East Syriac were OCRed using Tesseract's two different OCR modes (Syriac Language and Syriac Script  ...  and is the recommended mode to use.  ... 
doi:10.31826/hug-2019-220105 fatcat:6vpekqarwffwxgaqdla5xh7cna

Style conditioned recommendations

Murium Iqbal, Kamelia Aryafar, Timothy Anderton
2019 Proceedings of the 13th ACM Conference on Recommender Systems - RecSys '19  
We show a 12% improvement on NDCG@20 over the traditional VAE based approach and an average 22% improvement on AUC across all classes for predicting user style profiles against our best performing baseline  ...  We propose Style Conditioned Recommendations (SCR) and introduce style injection as a method to diversify recommendations.  ...  Our system instead creates new recommendations of existing items based on a user's history and new preferences, allowing the user to explore the catalog of items under different assumed user style profiles  ... 
doi:10.1145/3298689.3347007 dblp:conf/recsys/IqbalAA19 fatcat:wcngwunznva7pmbyr6dlccwyd4
« Previous Showing results 1 — 15 out of 57,487 results