Filters








518 Hits in 6.3 sec

Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding from Fashion Images [article]

Wei-Lin Hsiao, Kristen Grauman
2017 arXiv   pre-print
We propose an unsupervised approach to learn a style-coherent representation.  ...  Given a collection of unlabeled fashion images, our approach mines for the latent styles, then summarizes outfits by how they mix those styles.  ...  This research is supported in part by NSF IIS-1065390 and a gift from Amazon.  ... 
arXiv:1707.03376v2 fatcat:34inhmiuefc55dhaqy46wg5xjq

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

Imke Grabe, Jichen Zhu, Manex Agirrezabal
2022 arXiv   pre-print
Showing that the developed system can generate images of maximum fitness visually resembling certain styles, our approach provides a promising direction to guide the search for style-coherent designs.  ...  Finding the latent vectors in the generator's latent space that correspond to a style is approached as an evolutionary search problem.  ...  Fashion styles Studies have addressed the phenomenon of styles in fashion from different angles, varying from weak [18, 8] to strong [25, 17] style annotations, as well as their unsupervised discovery  ... 
arXiv:2204.00592v2 fatcat:bmoxmyzseva4jperyii3eegrve

Creating Capsule Wardrobes from Fashion Images

Wei-Lin Hsiao, Kristen Grauman
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Finally, we present an unsupervised approach to learn visual compatibility from "in the wild" full body outfit photos; the compatibility metric translates well to cleaner catalog photos and improves over  ...  Given an inventory of candidate garments and accessories, the algorithm must assemble a minimal set of items that provides maximal mix-and-match outfits.  ...  However, whereas [17] seeks a style-coherent image embedding, we use correlated topic models to score novel combinations of garments for their compatibility.  ... 
doi:10.1109/cvpr.2018.00748 dblp:conf/cvpr/HsiaoG18 fatcat:otvjdqs2sfazlgppeeaybiwb4e

Creating Capsule Wardrobes from Fashion Images [article]

Wei-Lin Hsiao, Kristen Grauman
2018 arXiv   pre-print
Finally, we present an unsupervised approach to learn visual compatibility from "in the wild" full body outfit photos; the compatibility metric translates well to cleaner catalog photos and improves over  ...  Given an inventory of candidate garments and accessories, the algorithm must assemble a minimal set of items that provides maximal mix-and-match outfits.  ...  However, whereas [17] seeks a style-coherent image embedding, we use correlated topic models to score novel combinations of garments for their compatibility.  ... 
arXiv:1712.02662v2 fatcat:fmmget3peveuxmnc4tbd56bysu

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
Given the rapid development, this paper provides a 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 retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer,  ...  Different from previous studies that sought coarse style classification, Hsiao and Grauman [63] treated styles as discoverable latent factors by exploring style-coherent representation.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines – From Medical to Remote Sensing [article]

Ankan Dash, Junyi Ye, Guiling Wang
2021 arXiv   pre-print
We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a number of sectors.  ...  Therefore in this article we provide a comprehensive overview of the applications of GANs in a wide variety of disciplines.  ...  The image Generator creates a video from a set of latent variables. The Discriminator consists of three-dimensional convolutional layers.  ... 
arXiv:2110.01442v1 fatcat:mqpnqw2ysfdz7dneajiw33dbga

Deep generative models for musical audio synthesis [article]

M. Huzaifah, L. Wyse
2020 arXiv   pre-print
This paper is a review of developments in deep learning that are changing the practice of sound modelling.  ...  Recent generative deep learning systems for audio synthesis are able to learn models that can traverse arbitrary spaces of sound defined by the data they train on.  ...  Acknowledgements This research was supported by a Singapore MOE Tier 2 grant, "Learning Generative Recurrent Neural Networks," and by an NVIDIA Corporation Academic Programs GPU grant.  ... 
arXiv:2006.06426v2 fatcat:swt7npt3gnbj5ppzcf2ef3rose

From Street Photos to Fashion Trends: Leveraging User-Provided Noisy Labels for Fashion Understanding

Fu-Hsien Huang, Hsin-Min Lu, Yao-Wen Hsu
2021 IEEE Access  
A. IMAGE COLLECTION AND CLEANING We collected street fashion images together with their text labels from WEAR, 4 a popular fashion coordination website in Japan.  ...  We crawled 389,633 images with upload date, users' gender and country, user-provided clothing labels, clothing  ...  and discovery of style dynamics.  ... 
doi:10.1109/access.2021.3069245 fatcat:gp3dkzjd65g57ihfioyavokgbi

Reinforcement Learning with Prototypical Representations [article]

Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto
2021 arXiv   pre-print
This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.  ...  Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning a useful representation requires diverse data, while effective exploration is only possible  ...  Prototypical Representation Learning Our framework learns a visual encoder that maps pixels to continuous latent embeddings, as well as a basis within this latent space, as defined by a set of prototypical  ... 
arXiv:2102.11271v2 fatcat:b4g7sqj4xrcqrdxikkpdw72hfa

Context Encoders: Feature Learning by Inpainting [article]

Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
2016 arXiv   pre-print
We found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures.  ...  In order to succeed at this task, context encoders need to both understand the content of the entire image, as well as produce a plausible hypothesis for the missing part(s).  ...  Acknowledgements The authors would like to thank Amanda Buster for the artwork on  ... 
arXiv:1604.07379v2 fatcat:zcyc6zymyjgbljd6vtanzso6a4

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

Murium Iqbal, Adair Kovac, Kamelia Aryafar
2018 arXiv   pre-print
The first system aims to maximize the visual-based style compatibility of the entire selection by making use of transfer learning and topic modeling.  ...  together with the overall theme, style or ambiance of a space in mind.  ...  To facilitate style discovery from the images, we process them via prevalent deep learning techniques.  ... 
arXiv:1806.11226v1 fatcat:2cnak27q7ndnjirvhso5m5cqpa

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

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
The implementation of machine learning, computer vision, and artificial intelligence (AI) in fashion applications is opening lots of new opportunities for this industry.  ...  The fashion industry is on the verge of an unprecedented change.  ...  Item Recom. from full shot images [133] f) Explainable body shape-aware Recom. [326] g) Similar Street images [92] Figure 56 : 56 Figure 56: Outfit style recommenders. a) Style-coherent Street images  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

Compositional Transformers for Scene Generation [article]

Drew A. Hudson, C. Lawrence Zitnick
2021 arXiv   pre-print
We demonstrate GANformer2's strengths and qualities through a careful evaluation over a range of datasets, from multi-object CLEVR scenes to the challenging COCO images, showing it successfully achieves  ...  The network incorporates strong and explicit structural priors, to reflect the compositional nature of visual scenes, and synthesizes images through a sequential process.  ...  Acknowledgements We performed the experiments for the paper on AWS cloud, thanks to Stanford HAI credit award. Drew A. Hudson (Dor) is a PhD student at Stanford University and C.  ... 
arXiv:2111.08960v1 fatcat:mevc72ear5d77igl5hln72s6hm

Context Encoders: Feature Learning by Inpainting

Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Imagenet large scale visual recog- Unsupervised learning of spatiotemporally coherent metrics. nition challenge.  ...  sion to learn embeddings which perform well on a num- We evaluate the encoder and the decoder independently. ber of tasks [17, 34].  ... 
doi:10.1109/cvpr.2016.278 dblp:conf/cvpr/PathakKDDE16 fatcat:dpxpf3ircjgxzenfnmzyv6o6nu

Review of Disentanglement Approaches for Medical Applications – Towards Solving the Gordian Knot of Generative Models in Healthcare [article]

Jana Fragemann, Lynton Ardizzone, Jan Egger, Jens Kleesiek
2022 arXiv   pre-print
Encouraging the latent representation of a generative model to be disentangled offers new perspectives of control and interpretability.  ...  Furthermore, we summarize the different notions of disentanglement, review approaches to disentangle latent space representations and metrics to evaluate the degree of disentanglement.  ...  Acknowledgement We acknowledge the REACT-EU project KITE (Plattform für KI-Translation Essen).  ... 
arXiv:2203.11132v1 fatcat:fxrniu6dtjcz5cumwientkqh7i
« Previous Showing results 1 — 15 out of 518 results